ID: 1
Title: SPRING: GPT-4 Out-performs RL Algorithms by Studying Papers and Reasoning
PDF: https://arxiv.org/pdf/2305.15486
Abstract: Open-world survival games pose significant challenges for AI algorithms due to their multi-tasking, deep exploration, and goal prioritization requirements. Despite reinforcement learning (RL) being popular for solving games, its high sample complexity limits its effectiveness in complex open-world games like Crafter or Minecraft. We propose a novel approach, SPRING, to read the game's original academic paper and use the knowledge learned to reason and play the game through a large language model (LLM). Prompted with the LaTeX source as game context and a description of the agent's current observation, our SPRING framework employs a directed acyclic graph (DAG) with game-related questions as nodes and dependencies as edges. We identify the optimal action to take in the environment by traversing the DAG and calculating LLM responses for each node in topological order, with the LLM's answer to final node directly translating to environment actions. In our experiments, we study the quality of in-context "reasoning" induced by different forms of prompts under the setting of the Crafter open-world environment. Our experiments suggest that LLMs, when prompted with consistent chain-of-thought, have great potential in completing sophisticated high-level trajectories. Quantitatively, SPRING with GPT-4 outperforms all state-of-the-art RL baselines, trained for 1M steps, without any training. Finally, we show the potential of games as a test bed for LLMs.
ID: 2
Title: Automated Refugee Case Analysis: An NLP Pipeline for Supporting Legal Practitioners
PDF: https://arxiv.org/pdf/2305.15533
Abstract: In this paper, we introduce an end-to-end pipeline for retrieving, processing, and extracting targeted information from legal cases. We investigate an under-studied legal domain with a case study on refugee law in Canada. Searching case law for past similar cases is a key part of legal work for both lawyers and judges, the potential end-users of our prototype. While traditional named-entity recognition labels such as dates provide meaningful information in legal work, we propose to extend existing models and retrieve a total of 19 useful categories of items from refugee cases. After creating a novel data set of cases, we perform information extraction based on state-of-the-art neural named-entity recognition (NER). We test different architectures including two transformer models, using contextual and non-contextual embeddings, and compare general purpose versus domain-specific pre-training. The results demonstrate that models pre-trained on legal data perform best despite their smaller size, suggesting that domain matching had a larger effect than network architecture. We achieve a F1 score above 90% on five of the targeted categories and over 80% on four further categories.
ID: 3
Title: Harnessing the Power of Large Language Models for Natural Language to First-Order Logic Translation
PDF: https://arxiv.org/pdf/2305.15541
Abstract: Translating natural language sentences to first-order logic (NL-FOL translation) is a longstanding challenge in the NLP and formal logic literature. This paper introduces LogicLLaMA, a LLaMA-7B model fine-tuned for NL-FOL translation using LoRA on a single GPU. LogicLLaMA is capable of directly translating natural language into FOL rules, which outperforms GPT-3.5. LogicLLaMA is also equipped to correct FOL rules predicted by GPT-3.5, and can achieve similar performance as GPT-4 with a fraction of the cost. This correction ability was achieved by a novel supervised fine-tuning (SFT) + reinforcement learning with human feedback (RLHF) framework, which initially trains on synthetically perturbed NL-FOL pairs to encourage chain-of-thought reasoning and then fine-tunes with RLHF on GPT-3.5 outputs using a FOL verifier as the reward model.
ID: 4
Title: Non-Parametric Learning of Stochastic Differential Equations with Fast Rates of Convergence
PDF: https://arxiv.org/pdf/2305.15557
Abstract: We propose a novel non-parametric learning paradigm for the identification of drift and diffusion coefficients of non-linear stochastic differential equations, which relies upon discrete-time observations of the state. The key idea essentially consists of fitting a RKHS-based approximation of the corresponding Fokker-Planck equation to such observations, yielding theoretical estimates of learning rates which, unlike previous works, become increasingly tighter when the regularity of the unknown drift and diffusion coefficients becomes higher. Our method being kernel-based, offline pre-processing may in principle be profitably leveraged to enable efficient numerical implementation.
ID: 5
Title: Sound Design Strategies for Latent Audio Space Explorations Using Deep Learning Architectures
PDF: https://arxiv.org/pdf/2305.15571
Abstract: The research in Deep Learning applications in sound and music computing have gathered an interest in the recent years; however, there is still a missing link between these new technologies and on how they can be incorporated into real-world artistic practices. In this work, we explore a well-known Deep Learning architecture called Variational Autoencoders (VAEs). These architectures have been used in many areas for generating latent spaces where data points are organized so that similar data points locate closer to each other. Previously, VAEs have been used for generating latent timbre spaces or latent spaces of symbolic music excepts. Applying VAE to audio features of timbre requires a vocoder to transform the timbre generated by the network to an audio signal, which is computationally expensive. In this work, we apply VAEs to raw audio data directly while bypassing audio feature extraction. This approach allows the practitioners to use any audio recording while giving flexibility and control over the aesthetics through dataset curation. The lower computation time in audio signal generation allows the raw audio approach to be incorporated into real-time applications. In this work, we propose three strategies to explore latent spaces of audio and timbre for sound design applications. By doing so, our aim is to initiate a conversation on artistic approaches and strategies to utilize latent audio spaces in sound and music practices.
ID: 6
Title: Unsupervised Semantic Correspondence Using Stable Diffusion
PDF: https://arxiv.org/pdf/2305.15581
Abstract: Text-to-image diffusion models are now capable of generating images that are often indistinguishable from real images. To generate such images, these models must understand the semantics of the objects they are asked to generate. In this work we show that, without any training, one can leverage this semantic knowledge within diffusion models to find semantic correspondences -- locations in multiple images that have the same semantic meaning. Specifically, given an image, we optimize the prompt embeddings of these models for maximum attention on the regions of interest. These optimized embeddings capture semantic information about the location, which can then be transferred to another image. By doing so we obtain results on par with the strongly supervised state of the art on the PF-Willow dataset and significantly outperform (20.9% relative for the SPair-71k dataset) any existing weakly or unsupervised method on PF-Willow, CUB-200 and SPair-71k datasets.
ID: 7
Title: Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps
PDF: https://arxiv.org/pdf/2305.15583
Abstract: Denoising Diffusion Probabilistic Models (DDPM) have shown remarkable efficacy in the synthesis of high-quality images. However, their inference process characteristically requires numerous, potentially hundreds, of iterative steps, which could lead to the problem of exposure bias due to the accumulation of prediction errors over iterations. Previous work has attempted to mitigate this issue by perturbing inputs during training, which consequently mandates the retraining of the DDPM. In this work, we conduct a systematic study of exposure bias in diffusion models and, intriguingly, we find that the exposure bias could be alleviated with a new sampling method, without retraining the model. We empirically and theoretically show that, during inference, for each backward time step
ID: 8
Title: Manifold Diffusion Fields
PDF: https://arxiv.org/pdf/2305.15586
Abstract: We present Manifold Diffusion Fields (MDF), an approach to learn generative models of continuous functions defined over Riemannian manifolds. Leveraging insights from spectral geometry analysis, we define an intrinsic coordinate system on the manifold via the eigen-functions of the Laplace-Beltrami Operator. MDF represents functions using an explicit parametrization formed by a set of multiple input-output pairs. Our approach allows to sample continuous functions on manifolds and is invariant with respect to rigid and isometric transformations of the manifold. Empirical results on several datasets and manifolds show that MDF can capture distributions of such functions with better diversity and fidelity than previous approaches.
ID: 9
Title: Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models
PDF: https://arxiv.org/pdf/2305.15594
Abstract: Large language models (LLMs) are excellent in-context learners. However, the sensitivity of data contained in prompts raises privacy concerns. Our work first shows that these concerns are valid: we instantiate a simple but highly effective membership inference attack against the data used to prompt LLMs. To address this vulnerability, one could forego prompting and resort to fine-tuning LLMs with known algorithms for private gradient descent. However, this comes at the expense of the practicality and efficiency offered by prompting. Therefore, we propose to privately learn to prompt. We first show that soft prompts can be obtained privately through gradient descent on downstream data. However, this is not the case for discrete prompts. Thus, we orchestrate a noisy vote among an ensemble of LLMs presented with different prompts, i.e., a flock of stochastic parrots. The vote privately transfers the flock's knowledge into a single public prompt. We show that LLMs prompted with our private algorithms closely match the non-private baselines. For example, using GPT3 as the base model, we achieve a downstream accuracy of 92.7% on the sst2 dataset with (
ID: 10
Title: Reversible and irreversible bracket-based dynamics for deep graph neural networks
PDF: https://arxiv.org/pdf/2305.15616
Abstract: Recent works have shown that physics-inspired architectures allow the training of deep graph neural networks (GNNs) without oversmoothing. The role of these physics is unclear, however, with successful examples of both reversible (e.g., Hamiltonian) and irreversible (e.g., diffusion) phenomena producing comparable results despite diametrically opposed mechanisms, and further complications arising due to empirical departures from mathematical theory. This work presents a series of novel GNN architectures based upon structure-preserving bracket-based dynamical systems, which are provably guaranteed to either conserve energy or generate positive dissipation with increasing depth. It is shown that the theoretically principled framework employed here allows for inherently explainable constructions, which contextualize departures from theory in current architectures and better elucidate the roles of reversibility and irreversibility in network performance.
ID: 11
Title: Debias Coarsely, Sample Conditionally: Statistical Downscaling through Optimal Transport and Probabilistic Diffusion Models
PDF: https://arxiv.org/pdf/2305.15618
Abstract: We introduce a two-stage probabilistic framework for statistical downscaling between unpaired data. Statistical downscaling seeks a probabilistic map to transform low-resolution data from a (possibly biased) coarse-grained numerical scheme to high-resolution data that is consistent with a high-fidelity scheme. Our framework tackles the problem by tandeming two transformations: a debiasing step that is performed by an optimal transport map, and an upsampling step that is achieved by a probabilistic diffusion model with \textit{a posteriori} conditional sampling. This approach characterizes a conditional distribution without the need for paired data, and faithfully recovers relevant physical statistics from biased samples. We demonstrate the utility of the proposed approach on one- and two-dimensional fluid flow problems, which are representative of the core difficulties present in numerical simulations of weather and climate. Our method produces realistic high-resolution outputs from low-resolution inputs, by upsampling resolutions of
ID: 12
Title: Revisiting Generalized p-Laplacian Regularized Framelet GCNs: Convergence, Energy Dynamic and Training with Non-Linear Diffusion
PDF: https://arxiv.org/pdf/2305.15639
Abstract: This work presents a comprehensive theoretical analysis of graph p-Laplacian based framelet network (pL-UFG) to establish a solid understanding of its properties. We begin by conducting a convergence analysis of the p-Laplacian based implicit layer integrated after the framelet convolution, providing insights into the asymptotic behavior of pL-UFG. By exploring the generalized Dirichlet energy of pL-UFG, we demonstrate that the Dirichlet energy remains non-zero, ensuring the avoidance of over-smoothing issues in pL-UFG as it approaches convergence. Furthermore, we elucidate the dynamic energy perspective through which the implicit layer in pL-UFG synergizes with graph framelets, enhancing the model's adaptability to both homophilic and heterophilic data. Remarkably, we establish that the implicit layer can be interpreted as a generalized non-linear diffusion process, enabling training using diverse schemes. These multifaceted analyses lead to unified conclusions that provide novel insights for understanding and implementing pL-UFG, contributing to advancements in the field of graph-based deep learning.
ID: 13
Title: Zero-shot Generation of Training Data with Denoising Diffusion Probabilistic Model for Handwritten Chinese Character Recognition
PDF: https://arxiv.org/pdf/2305.15660
Abstract: There are more than 80,000 character categories in Chinese while most of them are rarely used. To build a high performance handwritten Chinese character recognition (HCCR) system supporting the full character set with a traditional approach, many training samples need be collected for each character category, which is both time-consuming and expensive. In this paper, we propose a novel approach to transforming Chinese character glyph images generated from font libraries to handwritten ones with a denoising diffusion probabilistic model (DDPM). Training from handwritten samples of a small character set, the DDPM is capable of mapping printed strokes to handwritten ones, which makes it possible to generate photo-realistic and diverse style handwritten samples of unseen character categories. Combining DDPM-synthesized samples of unseen categories with real samples of other categories, we can build an HCCR system to support the full character set. Experimental results on CASIA-HWDB dataset with 3,755 character categories show that the HCCR systems trained with synthetic samples perform similarly with the one trained with real samples in terms of recognition accuracy. The proposed method has the potential to address HCCR with a larger vocabulary.
ID: 14
Title: BookGPT: A General Framework for Book Recommendation Empowered by Large Language Model
PDF: https://arxiv.org/pdf/2305.15673
Abstract: With the continuous development and change exhibited by large language model (LLM) technology, represented by generative pretrained transformers (GPTs), many classic scenarios in various fields have re-emerged with new opportunities. This paper takes ChatGPT as the modeling object, incorporates LLM technology into the typical book resource understanding and recommendation scenario for the first time, and puts it into practice. By building a ChatGPT-like book recommendation system (BookGPT) framework based on ChatGPT, this paper attempts to apply ChatGPT to recommendation modeling for three typical tasks, book rating recommendation, user rating recommendation, and book summary recommendation, and explores the feasibility of LLM technology in book recommendation scenarios. At the same time, based on different evaluation schemes for book recommendation tasks and the existing classic recommendation models, this paper discusses the advantages and disadvantages of the BookGPT in book recommendation scenarios and analyzes the opportunities and improvement directions for subsequent LLMs in these scenarios.
ID: 15
Title: Cross-view Action Recognition Understanding From Exocentric to Egocentric Perspective
PDF: https://arxiv.org/pdf/2305.15699
Abstract: Understanding action recognition in egocentric videos has emerged as a vital research topic with numerous practical applications. With the limitation in the scale of egocentric data collection, learning robust deep learning-based action recognition models remains difficult. Transferring knowledge learned from the large-scale exocentric data to the egocentric data is challenging due to the difference in videos across views. Our work introduces a novel cross-view learning approach to action recognition (CVAR) that effectively transfers knowledge from the exocentric to the egocentric view. First, we introduce a novel geometric-based constraint into the self-attention mechanism in Transformer based on analyzing the camera positions between two views. Then, we propose a new cross-view self-attention loss learned on unpaired cross-view data to enforce the self-attention mechanism learning to transfer knowledge across views. Finally, to further improve the performance of our cross-view learning approach, we present the metrics to measure the correlations in videos and attention maps effectively. Experimental results on standard egocentric action recognition benchmarks, i.e., Charades-Ego, EPIC-Kitchens-55, and EPIC-Kitchens-100, have shown our approach's effectiveness and state-of-the-art performance.
ID: 16
Title: Knowledge Diffusion for Distillation
PDF: https://arxiv.org/pdf/2305.15712
Abstract: The representation gap between teacher and student is an emerging topic in knowledge distillation (KD). To reduce the gap and improve the performance, current methods often resort to complicated training schemes, loss functions, and feature alignments, which are task-specific and feature-specific. In this paper, we state that the essence of these methods is to discard the noisy information and distill the valuable information in the feature, and propose a novel KD method dubbed DiffKD, to explicitly denoise and match features using diffusion models. Our approach is based on the observation that student features typically contain more noises than teacher features due to the smaller capacity of student model. To address this, we propose to denoise student features using a diffusion model trained by teacher features. This allows us to perform better distillation between the refined clean feature and teacher feature. Additionally, we introduce a light-weight diffusion model with a linear autoencoder to reduce the computation cost and an adpative noise matching module to improve the denoising performance. Extensive experiments demonstrate that DiffKD is effective across various types of features and achieves state-of-the-art performance consistently on image classification, object detection, and semantic segmentation tasks. Code will be available at https://github.com/hunto/DiffKD.
ID: 17
Title: The False Promise of Imitating Proprietary LLMs
PDF: https://arxiv.org/pdf/2305.15717
Abstract: An emerging method to cheaply improve a weaker language model is to finetune it on outputs from a stronger model, such as a proprietary system like ChatGPT (e.g., Alpaca, Self-Instruct, and others). This approach looks to cheaply imitate the proprietary model's capabilities using a weaker open-source model. In this work, we critically analyze this approach. We first finetune a series of LMs that imitate ChatGPT using varying base model sizes (1.5B--13B), data sources, and imitation data amounts (0.3M--150M tokens). We then evaluate the models using crowd raters and canonical NLP benchmarks. Initially, we were surprised by the output quality of our imitation models -- they appear far better at following instructions, and crowd workers rate their outputs as competitive with ChatGPT. However, when conducting more targeted automatic evaluations, we find that imitation models close little to none of the gap from the base LM to ChatGPT on tasks that are not heavily supported in the imitation data. We show that these performance discrepancies may slip past human raters because imitation models are adept at mimicking ChatGPT's style but not its factuality. Overall, we conclude that model imitation is a false promise: there exists a substantial capabilities gap between open and closed LMs that, with current methods, can only be bridged using an unwieldy amount of imitation data or by using more capable base LMs. In turn, we argue that the highest leverage action for improving open-source models is to tackle the difficult challenge of developing better base LMs, rather than taking the shortcut of imitating proprietary systems.
ID: 18
Title: Efficient Neural Music Generation
PDF: https://arxiv.org/pdf/2305.15719
Abstract: Recent progress in music generation has been remarkably advanced by the state-of-the-art MusicLM, which comprises a hierarchy of three LMs, respectively, for semantic, coarse acoustic, and fine acoustic modelings. Yet, sampling with the MusicLM requires processing through these LMs one by one to obtain the fine-grained acoustic tokens, making it computationally expensive and prohibitive for a real-time generation. Efficient music generation with a quality on par with MusicLM remains a significant challenge. In this paper, we present MeLoDy (M for music; L for LM; D for diffusion), an LM-guided diffusion model that generates music audios of state-of-the-art quality meanwhile reducing 95.7% or 99.6% forward passes in MusicLM, respectively, for sampling 10s or 30s music. MeLoDy inherits the highest-level LM from MusicLM for semantic modeling, and applies a novel dual-path diffusion (DPD) model and an audio VAE-GAN to efficiently decode the conditioning semantic tokens into waveform. DPD is proposed to simultaneously model the coarse and fine acoustics by incorporating the semantic information into segments of latents effectively via cross-attention at each denoising step. Our experimental results suggest the superiority of MeLoDy, not only in its practical advantages on sampling speed and infinitely continuable generation, but also in its state-of-the-art musicality, audio quality, and text correlation.
ID: 19
Title: Comparative Study of Pre-Trained BERT Models for Code-Mixed Hindi-English Data
PDF: https://arxiv.org/pdf/2305.15722
Abstract: The term "Code Mixed" refers to the use of more than one language in the same text. This phenomenon is predominantly observed on social media platforms, with an increasing amount of adaptation as time goes on. It is critical to detect foreign elements in a language and process them correctly, as a considerable number of individuals are using code-mixed languages that could not be comprehended by understanding one of those languages. In this work, we focus on low-resource Hindi-English code-mixed language and enhancing the performance of different code-mixed natural language processing tasks such as sentiment analysis, emotion recognition, and hate speech identification. We perform a comparative analysis of different Transformer-based language Models pre-trained using unsupervised approaches. We have included the code-mixed models like HingBERT, HingRoBERTa, HingRoBERTa-Mixed, mBERT, and non-code-mixed models like AlBERT, BERT, and RoBERTa for comparative analysis of code-mixed Hindi-English downstream tasks. We report state-of-the-art results on respective datasets using HingBERT-based models which are specifically pre-trained on real code-mixed text. Our HingBERT-based models provide significant improvements thus highlighting the poor performance of vanilla BERT models on code-mixed text.
ID: 20
Title: CLIP3Dstyler: Language Guided 3D Arbitrary Neural Style Transfer
PDF: https://arxiv.org/pdf/2305.15732
Abstract: In this paper, we propose a novel language-guided 3D arbitrary neural style transfer method (CLIP3Dstyler). We aim at stylizing any 3D scene with an arbitrary style from a text description, and synthesizing the novel stylized view, which is more flexible than the image-conditioned style transfer. Compared with the previous 2D method CLIPStyler, we are able to stylize a 3D scene and generalize to novel scenes without re-train our model. A straightforward solution is to combine previous image-conditioned 3D style transfer and text-conditioned 2D style transfer \bigskip methods. However, such a solution cannot achieve our goal due to two main challenges. First, there is no multi-modal model matching point clouds and language at different feature scales (\eg low-level, high-level). Second, we observe a style mixing issue when we stylize the content with different style conditions from text prompts. To address the first issue, we propose a 3D stylization framework to match the point cloud features with text features in local and global views. For the second issue, we propose an improved directional divergence loss to make arbitrary text styles more distinguishable as a complement to our framework. We conduct extensive experiments to show the effectiveness of our model on text-guided 3D scene style transfer.
ID: 21
Title: Union Subgraph Neural Networks
PDF: https://arxiv.org/pdf/2305.15747
Abstract: Graph Neural Networks (GNNs) are widely used for graph representation learning in many application domains. The expressiveness of vanilla GNNs is upper-bounded by 1-dimensional Weisfeiler-Leman (1-WL) test as they operate on rooted subtrees through iterative message passing. In this paper, we empower GNNs by injecting neighbor-connectivity information extracted from a new type of substructure. We first investigate different kinds of connectivities existing in a local neighborhood and identify a substructure called union subgraph, which is able to capture the complete picture of the 1-hop neighborhood of an edge. We then design a shortest-path-based substructure descriptor that possesses three nice properties and can effectively encode the high-order connectivities in union subgraphs. By infusing the encoded neighbor connectivities, we propose a novel model, namely Union Subgraph Neural Network (UnionSNN), which is proven to be strictly more powerful than 1-WL in distinguishing non-isomorphic graphs. Additionally, the local encoding from union subgraphs can also be injected into arbitrary message-passing neural networks (MPNNs) and Transformer-based models as a plugin. Extensive experiments on 17 benchmarks of both graph-level and node-level tasks demonstrate that UnionSNN outperforms state-of-the-art baseline models, with competitive computational efficiency. The injection of our local encoding to existing models is able to boost the performance by up to 11.09%.
ID: 22
Title: T2TD: Text-3D Generation Model based on Prior Knowledge Guidance
PDF: https://arxiv.org/pdf/2305.15753
Abstract: In recent years, 3D models have been utilized in many applications, such as auto-driver, 3D reconstruction, VR, and AR. However, the scarcity of 3D model data does not meet its practical demands. Thus, generating high-quality 3D models efficiently from textual descriptions is a promising but challenging way to solve this problem. In this paper, inspired by the ability of human beings to complement visual information details from ambiguous descriptions based on their own experience, we propose a novel text-3D generation model (T2TD), which introduces the related shapes or textual information as the prior knowledge to improve the performance of the 3D generation model. In this process, we first introduce the text-3D knowledge graph to save the relationship between 3D models and textual semantic information, which can provide the related shapes to guide the target 3D model generation. Second, we integrate an effective causal inference model to select useful feature information from these related shapes, which removes the unrelated shape information and only maintains feature information that is strongly relevant to the textual description. Meanwhile, to effectively integrate multi-modal prior knowledge into textual information, we adopt a novel multi-layer transformer structure to progressively fuse related shape and textual information, which can effectively compensate for the lack of structural information in the text and enhance the final performance of the 3D generation model. The final experimental results demonstrate that our approach significantly improves 3D model generation quality and outperforms the SOTA methods on the text2shape datasets.
ID: 23
Title: UniTRec: A Unified Text-to-Text Transformer and Joint Contrastive Learning Framework for Text-based Recommendation
PDF: https://arxiv.org/pdf/2305.15756
Abstract: Prior study has shown that pretrained language models (PLM) can boost the performance of text-based recommendation. In contrast to previous works that either use PLM to encode user history as a whole input text, or impose an additional aggregation network to fuse multi-turn history representations, we propose a unified local- and global-attention Transformer encoder to better model two-level contexts of user history. Moreover, conditioned on user history encoded by Transformer encoders, our framework leverages Transformer decoders to estimate the language perplexity of candidate text items, which can serve as a straightforward yet significant contrastive signal for user-item text matching. Based on this, our framework, UniTRec, unifies the contrastive objectives of discriminative matching scores and candidate text perplexity to jointly enhance text-based recommendation. Extensive evaluation shows that UniTRec delivers SOTA performance on three text-based recommendation tasks. Code is available at https://github.com/Veason-silverbullet/UniTRec.
ID: 24
Title: MERGE: Fast Private Text Generation
PDF: https://arxiv.org/pdf/2305.15769
Abstract: Recent years have seen increasing concerns about the private inference of NLP services and Transformer models. However, existing two-party privacy-preserving methods solely consider NLU scenarios, while the private inference of text generation such as translation, dialogue, and code completion remains unsolved. Besides, while migrated to NLG models, existing privacy-preserving methods perform poorly in terms of inference speed, and suffer from the convergence problem during the training stage. To address these issues, we propose MERGE, a fast private text generation framework for Transformer-based language models. Specifically, MERGE reuse the output hidden state as the word embedding to bypass the embedding computation, and reorganize the linear operations in the Transformer module to accelerate the forward procedure. Based on these two optimizations, extensive experiments show that MERGE can achieve a 26.5x speedup under the sequence length 512, and reduce 80% communication bytes, with an up to 10x speedup to existing state-of-art models.
ID: 25
Title: On the Planning Abilities of Large Language Models -- A Critical Investigation
PDF: https://arxiv.org/pdf/2305.15771
Abstract: Intrigued by the claims of emergent reasoning capabilities in LLMs trained on general web corpora, in this paper, we set out to investigate their planning capabilities. We aim to evaluate (1) the effectiveness of LLMs in generating plans autonomously in commonsense planning tasks and (2) the potential of LLMs as a source of heuristic guidance for other agents (AI planners) in their planning tasks. We conduct a systematic study by generating a suite of instances on domains similar to the ones employed in the International Planning Competition and evaluate LLMs in two distinct modes: autonomous and heuristic. Our findings reveal that LLMs' ability to generate executable plans autonomously is rather limited, with the best model (GPT-4) having an average success rate of ~12% across the domains. However, the results in the heuristic mode show more promise. In the heuristic mode, we demonstrate that LLM-generated plans can improve the search process for underlying sound planners and additionally show that external verifiers can help provide feedback on the generated plans and back-prompt the LLM for better plan generation.
ID: 26
Title: Multi-scale Efficient Graph-Transformer for Whole Slide Image Classification
PDF: https://arxiv.org/pdf/2305.15773
Abstract: The multi-scale information among the whole slide images (WSIs) is essential for cancer diagnosis. Although the existing multi-scale vision Transformer has shown its effectiveness for learning multi-scale image representation, it still cannot work well on the gigapixel WSIs due to their extremely large image sizes. To this end, we propose a novel Multi-scale Efficient Graph-Transformer (MEGT) framework for WSI classification. The key idea of MEGT is to adopt two independent Efficient Graph-based Transformer (EGT) branches to process the low-resolution and high-resolution patch embeddings (i.e., tokens in a Transformer) of WSIs, respectively, and then fuse these tokens via a multi-scale feature fusion module (MFFM). Specifically, we design an EGT to efficiently learn the local-global information of patch tokens, which integrates the graph representation into Transformer to capture spatial-related information of WSIs. Meanwhile, we propose a novel MFFM to alleviate the semantic gap among different resolution patches during feature fusion, which creates a non-patch token for each branch as an agent to exchange information with another branch by cross-attention. In addition, to expedite network training, a novel token pruning module is developed in EGT to reduce the redundant tokens. Extensive experiments on TCGA-RCC and CAMELYON16 datasets demonstrate the effectiveness of the proposed MEGT.
ID: 27
Title: Concept-Centric Transformers: Concept Transformers with Object-Centric Concept Learning for Interpretability
PDF: https://arxiv.org/pdf/2305.15775
Abstract: Attention mechanisms have greatly improved the performance of deep-learning models on visual, NLP, and multimodal tasks while also providing tools to aid in the model's interpretability. In particular, attention scores over input regions or concrete image features can be used to measure how much the attended elements contribute to the model inference. The recently proposed Concept Transformer (CT) generalizes the Transformer attention mechanism from such low-level input features to more abstract, intermediate-level latent concepts that better allow human analysts to more directly assess an explanation for the reasoning of the model about any particular output classification. However, the concept learning employed by CT implicitly assumes that across every image in a class, each image patch makes the same contribution to concepts that characterize membership in that class. Instead of using the CT's image-patch-centric concepts, object-centric concepts could lead to better classification performance as well as better explainability. Thus, we propose Concept-Centric Transformers (CCT), a new family of concept transformers that provides more robust explanations and performance by integrating a novel concept-extraction module based on object-centric learning. We test our proposed CCT against the CT and several other existing approaches on classification problems for MNIST (odd/even), CIFAR100 (super-classes), and CUB-200-2011 (bird species). Our experiments demonstrate that CCT not only achieves significantly better classification accuracy than all selected benchmark classifiers across all three of our test problems, but it generates more consistent concept-based explanations of classification output when compared to CT.
ID: 28
Title: Custom-Edit: Text-Guided Image Editing with Customized Diffusion Models
PDF: https://arxiv.org/pdf/2305.15779
Abstract: Text-to-image diffusion models can generate diverse, high-fidelity images based on user-provided text prompts. Recent research has extended these models to support text-guided image editing. While text guidance is an intuitive editing interface for users, it often fails to ensure the precise concept conveyed by users. To address this issue, we propose Custom-Edit, in which we (i) customize a diffusion model with a few reference images and then (ii) perform text-guided editing. Our key discovery is that customizing only language-relevant parameters with augmented prompts improves reference similarity significantly while maintaining source similarity. Moreover, we provide our recipe for each customization and editing process. We compare popular customization methods and validate our findings on two editing methods using various datasets.
ID: 29
Title: Service Composition in the ChatGPT Era
PDF: https://arxiv.org/pdf/2305.15788
Abstract: The paper speculates about how ChatGPT-like systems can support the field of automated service composition and identifies new research areas to explore in order to take advantage of such tools in the field of service-oriented composition.
ID: 30
Title: On Architectural Compression of Text-to-Image Diffusion Models
PDF: https://arxiv.org/pdf/2305.15798
Abstract: Exceptional text-to-image (T2I) generation results of Stable Diffusion models (SDMs) come with substantial computational demands. To resolve this issue, recent research on efficient SDMs has prioritized reducing the number of sampling steps and utilizing network quantization. Orthogonal to these directions, this study highlights the power of classical architectural compression for general-purpose T2I synthesis by introducing block-removed knowledge-distilled SDMs (BK-SDMs). We eliminate several residual and attention blocks from the U-Net of SDMs, obtaining over a 30% reduction in the number of parameters, MACs per sampling step, and latency. We conduct distillation-based pretraining with only 0.22M LAION pairs (fewer than 0.1% of the full training pairs) on a single A100 GPU. Despite being trained with limited resources, our compact models can imitate the original SDM by benefiting from transferred knowledge and achieve competitive results against larger multi-billion parameter models on the zero-shot MS-COCO benchmark. Moreover, we demonstrate the applicability of our lightweight pretrained models in personalized generation with DreamBooth finetuning.
ID: 31
Title: ChatGPT for PLC/DCS Control Logic Generation
PDF: https://arxiv.org/pdf/2305.15809
Abstract: Large language models (LLMs) providing generative AI have become popular to support software engineers in creating, summarizing, optimizing, and documenting source code. It is still unknown how LLMs can support control engineers using typical control programming languages in programming tasks. Researchers have explored GitHub CoPilot or DeepMind AlphaCode for source code generation but did not yet tackle control logic programming. The contribution of this paper is an exploratory study, for which we created 100 LLM prompts in 10 representative categories to analyze control logic generation for of PLCs and DCS from natural language. We tested the prompts by generating answers with ChatGPT using the GPT-4 LLM. It generated syntactically correct IEC 61131-3 Structured Text code in many cases and demonstrated useful reasoning skills that could boost control engineer productivity. Our prompt collection is the basis for a more formal LLM benchmark to test and compare such models for control logic generation.
ID: 32
Title: PDE+: Enhancing Generalization via PDE with Adaptive Distributional Diffusion
PDF: https://arxiv.org/pdf/2305.15835
Abstract: The generalization of neural networks is a central challenge in machine learning, especially concerning the performance under distributions that differ from training ones. Current methods, mainly based on the data-driven paradigm such as data augmentation, adversarial training, and noise injection, may encounter limited generalization due to model non-smoothness. In this paper, we propose to investigate generalization from a Partial Differential Equation (PDE) perspective, aiming to enhance it directly through the underlying function of neural networks, rather than focusing on adjusting input data. Specifically, we first establish the connection between neural network generalization and the smoothness of the solution to a specific PDE, namely ``transport equation''. Building upon this, we propose a general framework that introduces adaptive distributional diffusion into transport equation to enhance the smoothness of its solution, thereby improving generalization. In the context of neural networks, we put this theoretical framework into practice as PDE+ (\textbf{PDE} with \textbf{A}daptive \textbf{D}istributional \textbf{D}iffusion) which diffuses each sample into a distribution covering semantically similar inputs. This enables better coverage of potentially unobserved distributions in training, thus improving generalization beyond merely data-driven methods. The effectiveness of PDE+ is validated in extensive settings, including clean samples and various corruptions, demonstrating its superior performance compared to SOTA methods.
ID: 33
Title: Text-to-Motion Retrieval: Towards Joint Understanding of Human Motion Data and Natural Language
PDF: https://arxiv.org/pdf/2305.15842
Abstract: Due to recent advances in pose-estimation methods, human motion can be extracted from a common video in the form of 3D skeleton sequences. Despite wonderful application opportunities, effective and efficient content-based access to large volumes of such spatio-temporal skeleton data still remains a challenging problem. In this paper, we propose a novel content-based text-to-motion retrieval task, which aims at retrieving relevant motions based on a specified natural-language textual description. To define baselines for this uncharted task, we employ the BERT and CLIP language representations to encode the text modality and successful spatio-temporal models to encode the motion modality. We additionally introduce our transformer-based approach, called Motion Transformer (MoT), which employs divided space-time attention to effectively aggregate the different skeleton joints in space and time. Inspired by the recent progress in text-to-image/video matching, we experiment with two widely-adopted metric-learning loss functions. Finally, we set up a common evaluation protocol by defining qualitative metrics for assessing the quality of the retrieved motions, targeting the two recently-introduced KIT Motion-Language and HumanML3D datasets. The code for reproducing our results is available at https://github.com/mesnico/text-to-motion-retrieval.
ID: 34
Title: TabGSL: Graph Structure Learning for Tabular Data Prediction
PDF: https://arxiv.org/pdf/2305.15843
Abstract: This work presents a novel approach to tabular data prediction leveraging graph structure learning and graph neural networks. Despite the prevalence of tabular data in real-world applications, traditional deep learning methods often overlook the potentially valuable associations between data instances. Such associations can offer beneficial insights for classification tasks, as instances may exhibit similar patterns of correlations among features and target labels. This information can be exploited by graph neural networks, necessitating robust graph structures. However, existing studies primarily focus on improving graph structure from noisy data, largely neglecting the possibility of deriving graph structures from tabular data. We present a novel solution, Tabular Graph Structure Learning (TabGSL), to enhance tabular data prediction by simultaneously learning instance correlation and feature interaction within a unified framework. This is achieved through a proposed graph contrastive learning module, along with transformer-based feature extractor and graph neural network. Comprehensive experiments conducted on 30 benchmark tabular datasets demonstrate that TabGSL markedly outperforms both tree-based models and recent deep learning-based tabular models. Visualizations of the learned instance embeddings further substantiate the effectiveness of TabGSL.
ID: 35
Title: Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation
PDF: https://arxiv.org/pdf/2305.15852
Abstract: Large language models (large LMs) are susceptible to producing text with hallucinated content. Self-contradiction, where the LM generates two contradictory sentences within the same context, is an important form of hallucination. In this work, we present a comprehensive analysis on self-contradiction for state-of-the-art, instruction-tuned LMs, including evaluation, detection, and mitigation. To effectively trigger self-contradictions, we design a framework that constrains LMs to generate appropriate sentence pairs. Our evaluation on these sentence pairs reveals that self-contradictions occur frequently across different LMs for both famous and lesser-known topics. Next, we prompt the LMs to detect self-contradictions. Our results indicate that ChatGPT and GPT-4 are able to accurately identify self-contradictions, while Vicuna-13B struggles to do so. For example, with our best prompting method, ChatGPT achieves 91.0% precision and 80.5% recall on the sentence pairs generated by itself. To automatically mitigate self-contradictions, we develop an iterative algorithm that prompts the LMs to remove the detected self-contradictions from the generated text. Our algorithm successfully revises the text such that self-contradictions are significantly reduced, while maintaining its fluency and informativeness. Importantly, our entire pipeline of triggering, detecting, and mitigating self-contradictions is applicable to black-box LMs and does not require any external grounded knowledge.
ID: 36
Title: Confronting Ambiguity in 6D Object Pose Estimation via Score-Based Diffusion on SE(3)
PDF: https://arxiv.org/pdf/2305.15873
Abstract: Addressing accuracy limitations and pose ambiguity in 6D object pose estimation from single RGB images presents a significant challenge, particularly due to object symmetries or occlusions. In response, we introduce a novel score-based diffusion method applied to the
ID: 37
Title: Linguistic Properties of Truthful Response
PDF: https://arxiv.org/pdf/2305.15875
Abstract: We investigate the phenomenon of an LLM's untruthful response using a large set of 220 handcrafted linguistic features. We focus on GPT-3 models and find that the linguistic profiles of responses are similar across model sizes. That is, how varying-sized LLMs respond to given prompts stays similar on the linguistic properties level. We expand upon this finding by training support vector machines that rely only upon the stylistic components of model responses to classify the truthfulness of statements. Though the dataset size limits our current findings, we present promising evidence that truthfulness detection is possible without evaluating the content itself.
ID: 38
Title: Generative Adversarial Reduced Order Modelling
PDF: https://arxiv.org/pdf/2305.15881
Abstract: In this work, we present GAROM, a new approach for reduced order modelling (ROM) based on generative adversarial networks (GANs). GANs have the potential to learn data distribution and generate more realistic data. While widely applied in many areas of deep learning, little research is done on their application for ROM, i.e. approximating a high-fidelity model with a simpler one. In this work, we combine the GAN and ROM framework, by introducing a data-driven generative adversarial model able to learn solutions to parametric differential equations. The latter is achieved by modelling the discriminator network as an autoencoder, extracting relevant features of the input, and applying a conditioning mechanism to the generator and discriminator networks specifying the differential equation parameters. We show how to apply our methodology for inference, provide experimental evidence of the model generalisation, and perform a convergence study of the method.
ID: 39
Title: MixFormerV2: Efficient Fully Transformer Tracking
PDF: https://arxiv.org/pdf/2305.15896
Abstract: Transformer-based trackers have achieved strong accuracy on the standard benchmarks. However, their efficiency remains an obstacle to practical deployment on both GPU and CPU platforms. In this paper, to overcome this issue, we propose a fully transformer tracking framework, coined as \emph{MixFormerV2}, without any dense convolutional operation and complex score prediction module. Our key design is to introduce four special prediction tokens and concatenate them with the tokens from target template and search areas. Then, we apply the unified transformer backbone on these mixed token sequence. These prediction tokens are able to capture the complex correlation between target template and search area via mixed attentions. Based on them, we can easily predict the tracking box and estimate its confidence score through simple MLP heads. To further improve the efficiency of MixFormerV2, we present a new distillation-based model reduction paradigm, including dense-to-sparse distillation and deep-to-shallow distillation. The former one aims to transfer knowledge from the dense-head based MixViT to our fully transformer tracker, while the latter one is used to prune some layers of the backbone. We instantiate two types of MixForemrV2, where the MixFormerV2-B achieves an AUC of 70.6% on LaSOT and an AUC of 57.4% on TNL2k with a high GPU speed of 165 FPS, and the MixFormerV2-S surpasses FEAR-L by 2.7% AUC on LaSOT with a real-time CPU speed.
ID: 40
Title: Latent Diffusion Model Based Foley Sound Generation System For DCASE Challenge 2023 Task 7
PDF: https://arxiv.org/pdf/2305.15905
Abstract: Foley sound generation aims to synthesise the background sound for multimedia content, which involves computationally modelling sound effects with specialized techniques. In this work, we proposed a diffusion based generative model for DCASE 2023 challenge task 7: Foley Sound Synthesis. The proposed system is based on AudioLDM, which is a diffusion-based text-to-audio generation model. To alleviate the data scarcity of the task 7 training set, our model is initially trained with large-scale datasets and downstream into this DCASE task via transfer learning. We have observed that the feature extracted by the encoder can significantly affect the performance of the generation model. Hence, we improve the results by leveraging the input label with related text embedding features obtained by a large language model, i.e., contrastive language-audio pretraining (CLAP). In addition, we utilize a filtering strategy to further refine the output, i.e. by selecting the best results from the candidate clips generated in terms of the similarity score between the sound and target labels. The overall system achieves a Frechet audio distance (FAD) score of 4.765 on average among all seven different classes, substantially outperforming the baseline system which achieves a FAD score of 9.7.
ID: 41
Title: Response Generation in Longitudinal Dialogues: Which Knowledge Representation Helps?
PDF: https://arxiv.org/pdf/2305.15908
Abstract: Longitudinal Dialogues (LD) are the most challenging type of conversation for human-machine dialogue systems. LDs include the recollections of events, personal thoughts, and emotions specific to each individual in a sparse sequence of dialogue sessions. Dialogue systems designed for LDs should uniquely interact with the users over multiple sessions and long periods of time (e.g. weeks), and engage them in personal dialogues to elaborate on their feelings, thoughts, and real-life events. In this paper, we study the task of response generation in LDs. We evaluate whether general-purpose Pre-trained Language Models (PLM) are appropriate for this purpose. We fine-tune two PLMs, GePpeTto (GPT-2) and iT5, using a dataset of LDs. We experiment with different representations of the personal knowledge extracted from LDs for grounded response generation, including the graph representation of the mentioned events and participants. We evaluate the performance of the models via automatic metrics and the contribution of the knowledge via the Integrated Gradients technique. We categorize the natural language generation errors via human evaluations of contextualization, appropriateness and engagement of the user.
ID: 42
Title: Emergence of a phonological bias in ChatGPT
PDF: https://arxiv.org/pdf/2305.15929
Abstract: Current large language models, such as OpenAI's ChatGPT, have captured the public's attention because how remarkable they are in the use of language. Here, I demonstrate that ChatGPT displays phonological biases that are a hallmark of human language processing. More concretely, just like humans, ChatGPT has a consonant bias. That is, the chatbot has a tendency to use consonants over vowels to identify words. This is observed across languages that differ in their relative distribution of consonants and vowels such as English and Spanish. Despite the differences in how current artificial intelligence language models are trained to process linguistic stimuli and how human infants acquire language, such training seems to be enough for the emergence of a phonological bias in ChatGPT
ID: 43
Title: End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes
PDF: https://arxiv.org/pdf/2305.15930
Abstract: Meta-Bayesian optimisation (meta-BO) aims to improve the sample efficiency of Bayesian optimisation by leveraging data from related tasks. While previous methods successfully meta-learn either a surrogate model or an acquisition function independently, joint training of both components remains an open challenge. This paper proposes the first end-to-end differentiable meta-BO framework that generalises neural processes to learn acquisition functions via transformer architectures. We enable this end-to-end framework with reinforcement learning (RL) to tackle the lack of labelled acquisition data. Early on, we notice that training transformer-based neural processes from scratch with RL is challenging due to insufficient supervision, especially when rewards are sparse. We formalise this claim with a combinatorial analysis showing that the widely used notion of regret as a reward signal exhibits a logarithmic sparsity pattern in trajectory lengths. To tackle this problem, we augment the RL objective with an auxiliary task that guides part of the architecture to learn a valid probabilistic model as an inductive bias. We demonstrate that our method achieves state-of-the-art regret results against various baselines in experiments on standard hyperparameter optimisation tasks and also outperforms others in the real-world problems of mixed-integer programming tuning, antibody design, and logic synthesis for electronic design automation.
ID: 44
Title: Anomaly Detection with Conditioned Denoising Diffusion Models
PDF: https://arxiv.org/pdf/2305.15956
Abstract: Reconstruction-based methods have struggled to achieve competitive performance on anomaly detection. In this paper, we introduce Denoising Diffusion Anomaly Detection (DDAD). We propose a novel denoising process for image reconstruction conditioned on a target image. This results in a coherent restoration that closely resembles the target image. Subsequently, our anomaly detection framework leverages this conditioning where the target image is set as the input image to guide the denoising process, leading to defectless reconstruction while maintaining nominal patterns. We localise anomalies via a pixel-wise and feature-wise comparison of the input and reconstructed image. Finally, to enhance the effectiveness of feature comparison, we introduce a domain adaptation method that utilises generated examples from our conditioned denoising process to fine-tune the feature extractor. The veracity of the approach is demonstrated on various datasets including MVTec and VisA benchmarks, achieving state-of-the-art results of 99.5% and 99.3% image-level AUROC respectively.
ID: 45
Title: DiffCLIP: Leveraging Stable Diffusion for Language Grounded 3D Classification
PDF: https://arxiv.org/pdf/2305.15957
Abstract: Large pre-trained models have had a significant impact on computer vision by enabling multi-modal learning, where the CLIP model has achieved impressive results in image classification, object detection, and semantic segmentation. However, the model's performance on 3D point cloud processing tasks is limited due to the domain gap between depth maps from 3D projection and training images of CLIP. This paper proposes DiffCLIP, a new pre-training framework that incorporates stable diffusion with ControlNet to minimize the domain gap in the visual branch. Additionally, a style-prompt generation module is introduced for few-shot tasks in the textual branch. Extensive experiments on the ModelNet10, ModelNet40, and ScanObjectNN datasets show that DiffCLIP has strong abilities for 3D understanding. By using stable diffusion and style-prompt generation, DiffCLIP achieves an accuracy of 43.2% for zero-shot classification on OBJ_BG of ScanObjectNN, which is state-of-the-art performance, and an accuracy of 80.6% for zero-shot classification on ModelNet10, which is comparable to state-of-the-art performance.
ID: 46
Title: Efficient Document Embeddings via Self-Contrastive Bregman Divergence Learning
PDF: https://arxiv.org/pdf/2305.16031
Abstract: Learning quality document embeddings is a fundamental problem in natural language processing (NLP), information retrieval (IR), recommendation systems, and search engines. Despite recent advances in the development of transformer-based models that produce sentence embeddings with self-contrastive learning, the encoding of long documents (Ks of words) is still challenging with respect to both efficiency and quality considerations. Therefore, we train Longfomer-based document encoders using a state-of-the-art unsupervised contrastive learning method (SimCSE). Further on, we complement the baseline method -- siamese neural network -- with additional convex neural networks based on functional Bregman divergence aiming to enhance the quality of the output document representations. We show that overall the combination of a self-contrastive siamese network and our proposed neural Bregman network outperforms the baselines in two linear classification settings on three long document topic classification tasks from the legal and biomedical domains.
ID: 47
Title: Detecting Adversarial Data by Probing Multiple Perturbations Using Expected Perturbation Score
PDF: https://arxiv.org/pdf/2305.16035
Abstract: Adversarial detection aims to determine whether a given sample is an adversarial one based on the discrepancy between natural and adversarial distributions. Unfortunately, estimating or comparing two data distributions is extremely difficult, especially in high-dimension spaces. Recently, the gradient of log probability density (a.k.a., score) w.r.t. the sample is used as an alternative statistic to compute. However, we find that the score is sensitive in identifying adversarial samples due to insufficient information with one sample only. In this paper, we propose a new statistic called expected perturbation score (EPS), which is essentially the expected score of a sample after various perturbations. Specifically, to obtain adequate information regarding one sample, we perturb it by adding various noises to capture its multi-view observations. We theoretically prove that EPS is a proper statistic to compute the discrepancy between two samples under mild conditions. In practice, we can use a pre-trained diffusion model to estimate EPS for each sample. Last, we propose an EPS-based adversarial detection (EPS-AD) method, in which we develop EPS-based maximum mean discrepancy (MMD) as a metric to measure the discrepancy between the test sample and natural samples. We also prove that the EPS-based MMD between natural and adversarial samples is larger than that among natural samples. Extensive experiments show the superior adversarial detection performance of our EPS-AD.
ID: 48
Title: GenerateCT: Text-Guided 3D Chest CT Generation
PDF: https://arxiv.org/pdf/2305.16037
Abstract: Generative modeling has experienced substantial progress in recent years, particularly in text-to-image and text-to-video synthesis. However, the medical field has not yet fully exploited the potential of large-scale foundational models for synthetic data generation. In this paper, we introduce GenerateCT, the first method for text-conditional computed tomography (CT) generation, addressing the limitations in 3D medical imaging research and making our entire framework open-source. GenerateCT consists of a pre-trained large language model, a transformer-based text-conditional 3D chest CT generation architecture, and a text-conditional spatial super-resolution diffusion model. We also propose CT-ViT, which efficiently compresses CT volumes while preserving auto-regressiveness in-depth, enabling the generation of 3D CT volumes with variable numbers of axial slices. Our experiments demonstrate that GenerateCT can produce realistic, high-resolution, and high-fidelity 3D chest CT volumes consistent with medical language text prompts. We further investigate the potential of GenerateCT by training a model using generated CT volumes for multi-abnormality classification of chest CT volumes. Our contributions provide a valuable foundation for future research in text-conditional 3D medical image generation and have the potential to accelerate advancements in medical imaging research. Our code, pre-trained models, and generated data are available at https://github.com/ibrahimethemhamamci/GenerateCT.
ID: 49
Title: Local Randomized Neural Networks with Discontinuous Galerkin Methods for Diffusive-Viscous Wave Equation
PDF: https://arxiv.org/pdf/2305.16060
Abstract: The diffusive-viscous wave equation is an advancement in wave equation theory, as it accounts for both diffusion and viscosity effects. This has a wide range of applications in geophysics, such as the attenuation of seismic waves in fluid-saturated solids and frequency-dependent phenomena in porous media. Therefore, the development of an efficient numerical method for the equation is of both theoretical and practical importance. Recently, local randomized neural networks with discontinuous Galerkin (LRNN-DG) methods have been introduced in \cite{Sun2022lrnndg} to solve elliptic and parabolic equations. Numerical examples suggest that LRNN-DG can achieve high accuracy, and can handle time-dependent problems naturally and efficiently by using a space-time framework. In this paper, we develop LRNN-DG methods for solving the diffusive-viscous wave equation and present numerical experiments with several cases. The numerical results show that the proposed methods can solve the diffusive-viscous wave equation more accurately with less computing costs than traditional methods.
ID: 50
Title: VioLA: Unified Codec Language Models for Speech Recognition, Synthesis, and Translation
PDF: https://arxiv.org/pdf/2305.16107
Abstract: Recent research shows a big convergence in model architecture, training objectives, and inference methods across various tasks for different modalities. In this paper, we propose VioLA, a single auto-regressive Transformer decoder-only network that unifies various cross-modal tasks involving speech and text, such as speech-to-text, text-to-text, text-to-speech, and speech-to-speech tasks, as a conditional codec language model task via multi-task learning framework. To accomplish this, we first convert all the speech utterances to discrete tokens (similar to the textual data) using an offline neural codec encoder. In such a way, all these tasks are converted to token-based sequence conversion problems, which can be naturally handled with one conditional language model. We further integrate task IDs (TID) and language IDs (LID) into the proposed model to enhance the modeling capability of handling different languages and tasks. Experimental results demonstrate that the proposed VioLA model can support both single-modal and cross-modal tasks well, and the decoder-only model achieves a comparable and even better performance than the strong baselines.
ID: 51
Title: CACTUS: A Computational Framework for Generating Realistic White Matter Microstructure Substrates
PDF: https://arxiv.org/pdf/2305.16109
Abstract: Monte-Carlo diffusion simulations are a powerful tool for validating tissue microstructure models by generating synthetic diffusion-weighted magnetic resonance images (DW-MRI) in controlled environments. This is fundamental for understanding the link between micrometre-scale tissue properties and DW-MRI signals measured at the millimetre-scale, optimising acquisition protocols to target microstructure properties of interest, and exploring the robustness and accuracy of estimation methods. However, accurate simulations require substrates that reflect the main microstructural features of the studied tissue. To address this challenge, we introduce a novel computational workflow, CACTUS (Computational Axonal Configurator for Tailored and Ultradense Substrates), for generating synthetic white matter substrates. Our approach allows constructing substrates with higher packing density than existing methods, up to 95 % intra-axonal volume fraction, and larger voxel sizes of up to (500um) 3 with rich fibre complexity. CACTUS generates bundles with angular dispersion, bundle crossings, and variations along the fibres of their inner and outer radii and g-ratio. We achieve this by introducing a novel global cost function and a fibre radial growth approach that allows substrates to match predefined targeted characteristics and mirror those reported in histological studies. CACTUS improves the development of complex synthetic substrates, paving the way for future applications in microstructure imaging.
ID: 52
Title: Unifying GANs and Score-Based Diffusion as Generative Particle Models
PDF: https://arxiv.org/pdf/2305.16150
Abstract: Particle-based deep generative models, such as gradient flows and score-based diffusion models, have recently gained traction thanks to their striking performance. Their principle of displacing particle distributions by differential equations is conventionally seen as opposed to the previously widespread generative adversarial networks (GANs), which involve training a pushforward generator network. In this paper, we challenge this interpretation and propose a novel framework that unifies particle and adversarial generative models by framing generator training as a generalization of particle models. This suggests that a generator is an optional addition to any such generative model. Consequently, integrating a generator into a score-based diffusion model and training a GAN without a generator naturally emerge from our framework. We empirically test the viability of these original models as proofs of concepts of potential applications of our framework.
ID: 53
Title: PPGenCDR: A Stable and Robust Framework for Privacy-Preserving Cross-Domain Recommendation
PDF: https://arxiv.org/pdf/2305.16163
Abstract: Privacy-preserving cross-domain recommendation (PPCDR) refers to preserving the privacy of users when transferring the knowledge from source domain to target domain for better performance, which is vital for the long-term development of recommender systems. Existing work on cross-domain recommendation (CDR) reaches advanced and satisfying recommendation performance, but mostly neglects preserving privacy. To fill this gap, we propose a privacy-preserving generative cross-domain recommendation (PPGenCDR) framework for PPCDR. PPGenCDR includes two main modules, i.e., stable privacy-preserving generator module, and robust cross-domain recommendation module. Specifically, the former isolates data from different domains with a generative adversarial network (GAN) based model, which stably estimates the distribution of private data in the source domain with Renyi differential privacy (RDP) technique. Then the latter aims to robustly leverage the perturbed but effective knowledge from the source domain with the raw data in target domain to improve recommendation performance. Three key modules, i.e., (1) selective privacy preserver, (2) GAN stabilizer, and (3) robustness conductor, guarantee the cost-effective trade-off between utility and privacy, the stability of GAN when using RDP, and the robustness of leveraging transferable knowledge accordingly. The extensive empirical studies on Douban and Amazon datasets demonstrate that PPGenCDR significantly outperforms the state-of-the-art recommendation models while preserving privacy.
ID: 54
Title: Abstractive Summary Generation for the Urdu Language
PDF: https://arxiv.org/pdf/2305.16195
Abstract: Abstractive summary generation is a challenging task that requires the model to comprehend the source text and generate a concise and coherent summary that captures the essential information. In this paper, we explore the use of an encoder/decoder approach for abstractive summary generation in the Urdu language. We employ a transformer-based model that utilizes self-attention mechanisms to encode the input text and generate a summary. Our experiments show that our model can produce summaries that are grammatically correct and semantically meaningful. We evaluate our model on a publicly available dataset and achieve state-of-the-art results in terms of Rouge scores. We also conduct a qualitative analysis of our model's output to assess its effectiveness and limitations. Our findings suggest that the encoder/decoder approach is a promising method for abstractive summary generation in Urdu and can be extended to other languages with suitable modifications.
ID: 55
Title: Diversity-Aware Coherence Loss for Improving Neural Topic Models
PDF: https://arxiv.org/pdf/2305.16199
Abstract: The standard approach for neural topic modeling uses a variational autoencoder (VAE) framework that jointly minimizes the KL divergence between the estimated posterior and prior, in addition to the reconstruction loss. Since neural topic models are trained by recreating individual input documents, they do not explicitly capture the coherence between topic words on the corpus level. In this work, we propose a novel diversity-aware coherence loss that encourages the model to learn corpus-level coherence scores while maintaining a high diversity between topics. Experimental results on multiple datasets show that our method significantly improves the performance of neural topic models without requiring any pretraining or additional parameters.
ID: 56
Title: ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation
PDF: https://arxiv.org/pdf/2305.16213
Abstract: Score distillation sampling (SDS) has shown great promise in text-to-3D generation by distilling pretrained large-scale text-to-image diffusion models, but suffers from over-saturation, over-smoothing, and low-diversity problems. In this work, we propose to model the 3D parameter as a random variable instead of a constant as in SDS and present variational score distillation (VSD), a principled particle-based variational framework to explain and address the aforementioned issues in text-to-3D generation. We show that SDS is a special case of VSD and leads to poor samples with both small and large CFG weights. In comparison, VSD works well with various CFG weights as ancestral sampling from diffusion models and simultaneously improves the diversity and sample quality with a common CFG weight (i.e.,
ID: 57
Title: Prompt-Free Diffusion: Taking "Text" out of Text-to-Image Diffusion Models
PDF: https://arxiv.org/pdf/2305.16223
Abstract: Text-to-image (T2I) research has grown explosively in the past year, owing to the large-scale pre-trained diffusion models and many emerging personalization and editing approaches. Yet, one pain point persists: the text prompt engineering, and searching high-quality text prompts for customized results is more art than science. Moreover, as commonly argued: "an image is worth a thousand words" - the attempt to describe a desired image with texts often ends up being ambiguous and cannot comprehensively cover delicate visual details, hence necessitating more additional controls from the visual domain. In this paper, we take a bold step forward: taking "Text" out of a pre-trained T2I diffusion model, to reduce the burdensome prompt engineering efforts for users. Our proposed framework, Prompt-Free Diffusion, relies on only visual inputs to generate new images: it takes a reference image as "context", an optional image structural conditioning, and an initial noise, with absolutely no text prompt. The core architecture behind the scene is Semantic Context Encoder (SeeCoder), substituting the commonly used CLIP-based or LLM-based text encoder. The reusability of SeeCoder also makes it a convenient drop-in component: one can also pre-train a SeeCoder in one T2I model and reuse it for another. Through extensive experiments, Prompt-Free Diffusion is experimentally found to (i) outperform prior exemplar-based image synthesis approaches; (ii) perform on par with state-of-the-art T2I models using prompts following the best practice; and (iii) be naturally extensible to other downstream applications such as anime figure generation and virtual try-on, with promising quality. Our code and models are open-sourced at https://github.com/SHI-Labs/Prompt-Free-Diffusion.
ID: 58
Title: ProSpect: Expanded Conditioning for the Personalization of Attribute-aware Image Generation
PDF: https://arxiv.org/pdf/2305.16225
Abstract: Personalizing generative models offers a way to guide image generation with user-provided references. Current personalization methods can invert an object or concept into the textual conditioning space and compose new natural sentences for text-to-image diffusion models. However, representing and editing specific visual attributes like material, style, layout, etc. remains a challenge, leading to a lack of disentanglement and editability. To address this, we propose a novel approach that leverages the step-by-step generation process of diffusion models, which generate images from low- to high-frequency information, providing a new perspective on representing, generating, and editing images. We develop Prompt Spectrum Space P*, an expanded textual conditioning space, and a new image representation method called ProSpect. ProSpect represents an image as a collection of inverted textual token embeddings encoded from per-stage prompts, where each prompt corresponds to a specific generation stage (i.e., a group of consecutive steps) of the diffusion model. Experimental results demonstrate that P* and ProSpect offer stronger disentanglement and controllability compared to existing methods. We apply ProSpect in various personalized attribute-aware image generation applications, such as image/text-guided material/style/layout transfer/editing, achieving previously unattainable results with a single image input without fine-tuning the diffusion models.
ID: 59
Title: Interactive Segment Anything NeRF with Feature Imitation
PDF: https://arxiv.org/pdf/2305.16233
Abstract: This paper investigates the potential of enhancing Neural Radiance Fields (NeRF) with semantics to expand their applications. Although NeRF has been proven useful in real-world applications like VR and digital creation, the lack of semantics hinders interaction with objects in complex scenes. We propose to imitate the backbone feature of off-the-shelf perception models to achieve zero-shot semantic segmentation with NeRF. Our framework reformulates the segmentation process by directly rendering semantic features and only applying the decoder from perception models. This eliminates the need for expensive backbones and benefits 3D consistency. Furthermore, we can project the learned semantics onto extracted mesh surfaces for real-time interaction. With the state-of-the-art Segment Anything Model (SAM), our framework accelerates segmentation by 16 times with comparable mask quality. The experimental results demonstrate the efficacy and computational advantages of our approach. Project page: \url{https://me.kiui.moe/san/}.
ID: 60
Title: UDPM: Upsampling Diffusion Probabilistic Models
PDF: https://arxiv.org/pdf/2305.16269
Abstract: In recent years, Denoising Diffusion Probabilistic Models (DDPM) have caught significant attention. By composing a Markovian process that starts in the data domain and then gradually adds noise until reaching pure white noise, they achieve superior performance in learning data distributions. Yet, these models require a large number of diffusion steps to produce aesthetically pleasing samples, which is inefficient. In addition, unlike common generative adversarial networks, the latent space of diffusion models is not interpretable. In this work, we propose to generalize the denoising diffusion process into an Upsampling Diffusion Probabilistic Model (UDPM), in which we reduce the latent variable dimension in addition to the traditional noise level addition. As a result, we are able to sample images of size
ID: 61
Title: CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graphs
PDF: https://arxiv.org/pdf/2305.16283
Abstract: Controllable scene synthesis aims to create interactive environments for various industrial use cases. Scene graphs provide a highly suitable interface to facilitate these applications by abstracting the scene context in a compact manner. Existing methods, reliant on retrieval from extensive databases or pre-trained shape embeddings, often overlook scene-object and object-object relationships, leading to inconsistent results due to their limited generation capacity. To address this issue, we present CommonScenes, a fully generative model that converts scene graphs into corresponding controllable 3D scenes, which are semantically realistic and conform to commonsense. Our pipeline consists of two branches, one predicting the overall scene layout via a variational auto-encoder and the other generating compatible shapes via latent diffusion, capturing global scene-object and local inter-object relationships while preserving shape diversity. The generated scenes can be manipulated by editing the input scene graph and sampling the noise in the diffusion model. Due to lacking a scene graph dataset offering high-quality object-level meshes with relations, we also construct SG-FRONT, enriching the off-the-shelf indoor dataset 3D-FRONT with additional scene graph labels. Extensive experiments are conducted on SG-FRONT where CommonScenes shows clear advantages over other methods regarding generation consistency, quality, and diversity. Codes and the dataset will be released upon acceptance.
ID: 62
Title: Diversify Your Vision Datasets with Automatic Diffusion-Based Augmentation
PDF: https://arxiv.org/pdf/2305.16289
Abstract: Many fine-grained classification tasks, like rare animal identification, have limited training data and consequently classifiers trained on these datasets often fail to generalize to variations in the domain like changes in weather or location. As such, we explore how natural language descriptions of the domains seen in training data can be used with large vision models trained on diverse pretraining datasets to generate useful variations of the training data. We introduce ALIA (Automated Language-guided Image Augmentation), a method which utilizes large vision and language models to automatically generate natural language descriptions of a dataset's domains and augment the training data via language-guided image editing. To maintain data integrity, a model trained on the original dataset filters out minimal image edits and those which corrupt class-relevant information. The resulting dataset is visually consistent with the original training data and offers significantly enhanced diversity. On fine-grained and cluttered datasets for classification and detection, ALIA surpasses traditional data augmentation and text-to-image generated data by up to 15%, often even outperforming equivalent additions of real data. Code is avilable at https://github.com/lisadunlap/ALIA.
ID: 63
Title: Voyager: An Open-Ended Embodied Agent with Large Language Models
PDF: https://arxiv.org/pdf/2305.16291
Abstract: We introduce Voyager, the first LLM-powered embodied lifelong learning agent in Minecraft that continuously explores the world, acquires diverse skills, and makes novel discoveries without human intervention. Voyager consists of three key components: 1) an automatic curriculum that maximizes exploration, 2) an ever-growing skill library of executable code for storing and retrieving complex behaviors, and 3) a new iterative prompting mechanism that incorporates environment feedback, execution errors, and self-verification for program improvement. Voyager interacts with GPT-4 via blackbox queries, which bypasses the need for model parameter fine-tuning. The skills developed by Voyager are temporally extended, interpretable, and compositional, which compounds the agent's abilities rapidly and alleviates catastrophic forgetting. Empirically, Voyager shows strong in-context lifelong learning capability and exhibits exceptional proficiency in playing Minecraft. It obtains 3.3x more unique items, travels 2.3x longer distances, and unlocks key tech tree milestones up to 15.3x faster than prior SOTA. Voyager is able to utilize the learned skill library in a new Minecraft world to solve novel tasks from scratch, while other techniques struggle to generalize. We open-source our full codebase and prompts at https://voyager.minedojo.org/.
ID: 64
Title: Landmark Attention: Random-Access Infinite Context Length for Transformers
PDF: https://arxiv.org/pdf/2305.16300
Abstract: While transformers have shown remarkable success in natural language processing, their attention mechanism's large memory requirements have limited their ability to handle longer contexts. Prior approaches, such as recurrent memory or retrieval-based augmentation, have either compromised the random-access flexibility of attention (i.e., the capability to select any token in the entire context) or relied on separate mechanisms for relevant context retrieval, which may not be compatible with the model's attention. In this paper, we present a novel approach that allows access to the complete context while retaining random-access flexibility, closely resembling running attention on the entire context. Our method uses a landmark token to represent each block of the input and trains the attention to use it for selecting relevant blocks, enabling retrieval of blocks directly through the attention mechanism instead of by relying on a separate mechanism. Our approach seamlessly integrates with specialized data structures and the system's memory hierarchy, enabling processing of arbitrarily long context lengths. We demonstrate that our method can obtain comparable performance with Transformer-XL while significantly reducing the number of retrieved tokens in each step. Finally, we show that fine-tuning LLaMA 7B with our method successfully extends its context length capacity up to 32k tokens, allowing for inference at the context lengths of GPT-4.
ID: 65
Title: Look Ma, No Hands! Agent-Environment Factorization of Egocentric Videos
PDF: https://arxiv.org/pdf/2305.16301
Abstract: The analysis and use of egocentric videos for robotic tasks is made challenging by occlusion due to the hand and the visual mismatch between the human hand and a robot end-effector. In this sense, the human hand presents a nuisance. However, often hands also provide a valuable signal, e.g. the hand pose may suggest what kind of object is being held. In this work, we propose to extract a factored representation of the scene that separates the agent (human hand) and the environment. This alleviates both occlusion and mismatch while preserving the signal, thereby easing the design of models for downstream robotics tasks. At the heart of this factorization is our proposed Video Inpainting via Diffusion Model (VIDM) that leverages both a prior on real-world images (through a large-scale pre-trained diffusion model) and the appearance of the object in earlier frames of the video (through attention). Our experiments demonstrate the effectiveness of VIDM at improving inpainting quality on egocentric videos and the power of our factored representation for numerous tasks: object detection, 3D reconstruction of manipulated objects, and learning of reward functions, policies, and affordances from videos.
ID: 66
Title: Imitating Task and Motion Planning with Visuomotor Transformers
PDF: https://arxiv.org/pdf/2305.16309
Abstract: Imitation learning is a powerful tool for training robot manipulation policies, allowing them to learn from expert demonstrations without manual programming or trial-and-error. However, common methods of data collection, such as human supervision, scale poorly, as they are time-consuming and labor-intensive. In contrast, Task and Motion Planning (TAMP) can autonomously generate large-scale datasets of diverse demonstrations. In this work, we show that the combination of large-scale datasets generated by TAMP supervisors and flexible Transformer models to fit them is a powerful paradigm for robot manipulation. To that end, we present a novel imitation learning system called OPTIMUS that trains large-scale visuomotor Transformer policies by imitating a TAMP agent. OPTIMUS introduces a pipeline for generating TAMP data that is specifically curated for imitation learning and can be used to train performant transformer-based policies. In this paper, we present a thorough study of the design decisions required to imitate TAMP and demonstrate that OPTIMUS can solve a wide variety of challenging vision-based manipulation tasks with over 70 different objects, ranging from long-horizon pick-and-place tasks, to shelf and articulated object manipulation, achieving 70 to 80% success rates. Video results at https://mihdalal.github.io/optimus/
ID: 67
Title: Break-A-Scene: Extracting Multiple Concepts from a Single Image
PDF: https://arxiv.org/pdf/2305.16311
Abstract: Text-to-image model personalization aims to introduce a user-provided concept to the model, allowing its synthesis in diverse contexts. However, current methods primarily focus on the case of learning a single concept from multiple images with variations in backgrounds and poses, and struggle when adapted to a different scenario. In this work, we introduce the task of textual scene decomposition: given a single image of a scene that may contain several concepts, we aim to extract a distinct text token for each concept, enabling fine-grained control over the generated scenes. To this end, we propose augmenting the input image with masks that indicate the presence of target concepts. These masks can be provided by the user or generated automatically by a pre-trained segmentation model. We then present a novel two-phase customization process that optimizes a set of dedicated textual embeddings (handles), as well as the model weights, striking a delicate balance between accurately capturing the concepts and avoiding overfitting. We employ a masked diffusion loss to enable handles to generate their assigned concepts, complemented by a novel loss on cross-attention maps to prevent entanglement. We also introduce union-sampling, a training strategy aimed to improve the ability of combining multiple concepts in generated images. We use several automatic metrics to quantitatively compare our method against several baselines, and further affirm the results using a user study. Finally, we showcase several applications of our method. Project page is available at: https://omriavrahami.com/break-a-scene/
ID: 68
Title: NAP: Neural 3D Articulation Prior
PDF: https://arxiv.org/pdf/2305.16315
Abstract: We propose Neural 3D Articulation Prior (NAP), the first 3D deep generative model to synthesize 3D articulated object models. Despite the extensive research on generating 3D objects, compositions, or scenes, there remains a lack of focus on capturing the distribution of articulated objects, a common object category for human and robot interaction. To generate articulated objects, we first design a novel articulation tree/graph parameterization and then apply a diffusion-denoising probabilistic model over this representation where articulated objects can be generated via denoising from random complete graphs. In order to capture both the geometry and the motion structure whose distribution will affect each other, we design a graph-attention denoising network for learning the reverse diffusion process. We propose a novel distance that adapts widely used 3D generation metrics to our novel task to evaluate generation quality, and experiments demonstrate our high performance in articulated object generation. We also demonstrate several conditioned generation applications, including Part2Motion, PartNet-Imagination, Motion2Part, and GAPart2Object.
ID: 69
Title: Parallel Sampling of Diffusion Models
PDF: https://arxiv.org/pdf/2305.16317
Abstract: Diffusion models are powerful generative models but suffer from slow sampling, often taking 1000 sequential denoising steps for one sample. As a result, considerable efforts have been directed toward reducing the number of denoising steps, but these methods hurt sample quality. Instead of reducing the number of denoising steps (trading quality for speed), in this paper we explore an orthogonal approach: can we run the denoising steps in parallel (trading compute for speed)? In spite of the sequential nature of the denoising steps, we show that surprisingly it is possible to parallelize sampling via Picard iterations, by guessing the solution of future denoising steps and iteratively refining until convergence. With this insight, we present ParaDiGMS, a novel method to accelerate the sampling of pretrained diffusion models by denoising multiple steps in parallel. ParaDiGMS is the first diffusion sampling method that enables trading compute for speed and is even compatible with existing fast sampling techniques such as DDIM and DPMSolver. Using ParaDiGMS, we improve sampling speed by 2-4x across a range of robotics and image generation models, giving state-of-the-art sampling speeds of 0.2s on 100-step DiffusionPolicy and 16s on 1000-step StableDiffusion-v2 with no measurable degradation of task reward, FID score, or CLIP score.
ID: 70
Title: Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation
PDF: https://arxiv.org/pdf/2305.16318
Abstract: Recently, video object segmentation (VOS) referred by multi-modal signals, e.g., language and audio, has evoked increasing attention in both industry and academia. It is challenging for exploring the semantic alignment within modalities and the visual correspondence across frames. However, existing methods adopt separate network architectures for different modalities, and neglect the inter-frame temporal interaction with references. In this paper, we propose MUTR, a Multi-modal Unified Temporal transformer for Referring video object segmentation. With a unified framework for the first time, MUTR adopts a DETR-style transformer and is capable of segmenting video objects designated by either text or audio reference. Specifically, we introduce two strategies to fully explore the temporal relations between videos and multi-modal signals. Firstly, for low-level temporal aggregation before the transformer, we enable the multi-modal references to capture multi-scale visual cues from consecutive video frames. This effectively endows the text or audio signals with temporal knowledge and boosts the semantic alignment between modalities. Secondly, for high-level temporal interaction after the transformer, we conduct inter-frame feature communication for different object embeddings, contributing to better object-wise correspondence for tracking along the video. On Ref-YouTube-VOS and AVSBench datasets with respective text and audio references, MUTR achieves +4.2% and +4.2% J&F improvements to state-of-the-art methods, demonstrating our significance for unified multi-modal VOS. Code is released at https://github.com/OpenGVLab/MUTR.
ID: 71
Title: Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models
PDF: https://arxiv.org/pdf/2305.16322
Abstract: Text-to-Image diffusion models have made tremendous progress over the past two years, enabling the generation of highly realistic images based on open-domain text descriptions. However, despite their success, text descriptions often struggle to adequately convey detailed controls, even when composed of long and complex texts. Moreover, recent studies have also shown that these models face challenges in understanding such complex texts and generating the corresponding images. Therefore, there is a growing need to enable more control modes beyond text description. In this paper, we introduce Uni-ControlNet, a novel approach that allows for the simultaneous utilization of different local controls (e.g., edge maps, depth map, segmentation masks) and global controls (e.g., CLIP image embeddings) in a flexible and composable manner within one model. Unlike existing methods, Uni-ControlNet only requires the fine-tuning of two additional adapters upon frozen pre-trained text-to-image diffusion models, eliminating the huge cost of training from scratch. Moreover, thanks to some dedicated adapter designs, Uni-ControlNet only necessitates a constant number (i.e., 2) of adapters, regardless of the number of local or global controls used. This not only reduces the fine-tuning costs and model size, making it more suitable for real-world deployment, but also facilitate composability of different conditions. Through both quantitative and qualitative comparisons, Uni-ControlNet demonstrates its superiority over existing methods in terms of controllability, generation quality and composability. Code is available at \url{https://github.com/ShihaoZhaoZSH/Uni-ControlNet}.
ID: 72
Title: Generative Adversarial Networks for Brain Images Synthesis: A Review
PDF: https://arxiv.org/pdf/2305.15421
Abstract: In medical imaging, image synthesis is the estimation process of one image (sequence, modality) from another image (sequence, modality). Since images with different modalities provide diverse biomarkers and capture various features, multi-modality imaging is crucial in medicine. While multi-screening is expensive, costly, and time-consuming to report by radiologists, image synthesis methods are capable of artificially generating missing modalities. Deep learning models can automatically capture and extract the high dimensional features. Especially, generative adversarial network (GAN) as one of the most popular generative-based deep learning methods, uses convolutional networks as generators, and estimated images are discriminated as true or false based on a discriminator network. This review provides brain image synthesis via GANs. We summarized the recent developments of GANs for cross-modality brain image synthesis including CT to PET, CT to MRI, MRI to PET, and vice versa.
ID: 73
Title: Differentially Private Latent Diffusion Models
PDF: https://arxiv.org/pdf/2305.15759
Abstract: Diffusion models (DMs) are widely used for generating high-quality image datasets. However, since they operate directly in the high-dimensional pixel space, optimization of DMs is computationally expensive, requiring long training times. This contributes to large amounts of noise being injected into the differentially private learning process, due to the composability property of differential privacy. To address this challenge, we propose training Latent Diffusion Models (LDMs) with differential privacy. LDMs use powerful pre-trained autoencoders to reduce the high-dimensional pixel space to a much lower-dimensional latent space, making training DMs more efficient and fast. Unlike [Ghalebikesabi et al., 2023] that pre-trains DMs with public data then fine-tunes them with private data, we fine-tune only the attention modules of LDMs at varying layers with privacy-sensitive data, reducing the number of trainable parameters by approximately 96% compared to fine-tuning the entire DM. We test our algorithm on several public-private data pairs, such as ImageNet as public data and CIFAR10 and CelebA as private data, and SVHN as public data and MNIST as private data. Our approach provides a promising direction for training more powerful, yet training-efficient differentially private DMs that can produce high-quality synthetic images.
ID: 74
Title: DDDM-VC: Decoupled Denoising Diffusion Models with Disentangled Representation and Prior Mixup for Verified Robust Voice Conversion
PDF: https://arxiv.org/pdf/2305.15816
Abstract: Diffusion-based generative models have exhibited powerful generative performance in recent years. However, as many attributes exist in the data distribution and owing to several limitations of sharing the model parameters across all levels of the generation process, it remains challenging to control specific styles for each attribute. To address the above problem, this paper presents decoupled denoising diffusion models (DDDMs) with disentangled representations, which can control the style for each attribute in generative models. We apply DDDMs to voice conversion (VC) tasks to address the challenges of disentangling and controlling each speech attribute (e.g., linguistic information, intonation, and timbre). First, we use a self-supervised representation to disentangle the speech representation. Subsequently, the DDDMs are applied to resynthesize the speech from the disentangled representations for denoising with respect to each attribute. Moreover, we also propose the prior mixup for robust voice style transfer, which uses the converted representation of the mixed style as a prior distribution for the diffusion models. The experimental results reveal that our method outperforms publicly available VC models. Furthermore, we show that our method provides robust generative performance regardless of the model size. Audio samples are available https://hayeong0.github.io/DDDM-VC-demo/.
ID: 75
Title: A Diffusion Probabilistic Prior for Low-Dose CT Image Denoising
PDF: https://arxiv.org/pdf/2305.15887
Abstract: Low-dose computed tomography (CT) image denoising is crucial in medical image computing. Recent years have been remarkable improvement in deep learning-based methods for this task. However, training deep denoising neural networks requires low-dose and normal-dose CT image pairs, which are difficult to obtain in the clinic settings. To address this challenge, we propose a novel fully unsupervised method for low-dose CT image denoising, which is based on denoising diffusion probabilistic model -- a powerful generative model. First, we train an unconditional denoising diffusion probabilistic model capable of generating high-quality normal-dose CT images from random noise. Subsequently, the probabilistic priors of the pre-trained diffusion model are incorporated into a Maximum A Posteriori (MAP) estimation framework for iteratively solving the image denoising problem. Our method ensures the diffusion model produces high-quality normal-dose CT images while keeping the image content consistent with the input low-dose CT images. We evaluate our method on a widely used low-dose CT image denoising benchmark, and it outperforms several supervised low-dose CT image denoising methods in terms of both quantitative and visual performance.
ID: 76
Title: NexToU: Efficient Topology-Aware U-Net for Medical Image Segmentation
PDF: https://arxiv.org/pdf/2305.15911
Abstract: Convolutional neural networks (CNN) and Transformer variants have emerged as the leading medical image segmentation backbones. Nonetheless, due to their limitations in either preserving global image context or efficiently processing irregular shapes in visual objects, these backbones struggle to effectively integrate information from diverse anatomical regions and reduce inter-individual variability, particularly for the vasculature. Motivated by the successful breakthroughs of graph neural networks (GNN) in capturing topological properties and non-Euclidean relationships across various fields, we propose NexToU, a novel hybrid architecture for medical image segmentation. NexToU comprises improved Pool GNN and Swin GNN modules from Vision GNN (ViG) for learning both global and local topological representations while minimizing computational costs. To address the containment and exclusion relationships among various anatomical structures, we reformulate the topological interaction (TI) module based on the nature of binary trees, rapidly encoding the topological constraints into NexToU. Extensive experiments conducted on three datasets (including distinct imaging dimensions, disease types, and imaging modalities) demonstrate that our method consistently outperforms other state-of-the-art (SOTA) architectures. All the code is publicly available at https://github.com/PengchengShi1220/NexToU.
ID: 77
Title: The Milstein scheme for singular SDEs with Hölder continuous drift
PDF: https://arxiv.org/pdf/2305.16004
Abstract: We study the
ID: 78
Title: Transfer Learning for Personality Perception via Speech Emotion Recognition
PDF: https://arxiv.org/pdf/2305.16076
Abstract: Holistic perception of affective attributes is an important human perceptual ability. However, this ability is far from being realized in current affective computing, as not all of the attributes are well studied and their interrelationships are poorly understood. In this work, we investigate the relationship between two affective attributes: personality and emotion, from a transfer learning perspective. Specifically, we transfer Transformer-based and wav2vec-based emotion recognition models to perceive personality from speech across corpora. Compared with previous studies, our results show that transferring emotion recognition is effective for personality perception. Moreoever, this allows for better use and exploration of small personality corpora. We also provide novel findings on the relationship between personality and emotion that will aid future research on holistic affect recognition.
ID: 79
Title: Trans-Dimensional Generative Modeling via Jump Diffusion Models
PDF: https://arxiv.org/pdf/2305.16261
Abstract: We propose a new class of generative models that naturally handle data of varying dimensionality by jointly modeling the state and dimension of each datapoint. The generative process is formulated as a jump diffusion process that makes jumps between different dimensional spaces. We first define a dimension destroying forward noising process, before deriving the dimension creating time-reversed generative process along with a novel evidence lower bound training objective for learning to approximate it. Simulating our learned approximation to the time-reversed generative process then provides an effective way of sampling data of varying dimensionality by jointly generating state values and dimensions. We demonstrate our approach on molecular and video datasets of varying dimensionality, reporting better compatibility with test-time diffusion guidance imputation tasks and improved interpolation capabilities versus fixed dimensional models that generate state values and dimensions separately.
ID: 80
Title: Non-adversarial training of Neural SDEs with signature kernel scores
PDF: https://arxiv.org/pdf/2305.16274
Abstract: Neural SDEs are continuous-time generative models for sequential data. State-of-the-art performance for irregular time series generation has been previously obtained by training these models adversarially as GANs. However, as typical for GAN architectures, training is notoriously unstable, often suffers from mode collapse, and requires specialised techniques such as weight clipping and gradient penalty to mitigate these issues. In this paper, we introduce a novel class of scoring rules on pathspace based on signature kernels and use them as objective for training Neural SDEs non-adversarially. By showing strict properness of such kernel scores and consistency of the corresponding estimators, we provide existence and uniqueness guarantees for the minimiser. With this formulation, evaluating the generator-discriminator pair amounts to solving a system of linear path-dependent PDEs which allows for memory-efficient adjoint-based backpropagation. Moreover, because the proposed kernel scores are well-defined for paths with values in infinite dimensional spaces of functions, our framework can be easily extended to generate spatiotemporal data. Our procedure permits conditioning on a rich variety of market conditions and significantly outperforms alternative ways of training Neural SDEs on a variety of tasks including the simulation of rough volatility models, the conditional probabilistic forecasts of real-world forex pairs where the conditioning variable is an observed past trajectory, and the mesh-free generation of limit order book dynamics.