Soujanya Poria's repositories
multimodal-sentiment-analysis
Attention-based multimodal fusion for sentiment analysis
contextual-multimodal-fusion
Contextual inter modal attention for multimodal sentiment analysis
Multimodal-Infomax
This repository contains the official implementation code of the paper Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis, accepted at EMNLP 2021.
Open-Assistant
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
sentence-ordering
This repository contains the PyTorch implementation of the paper STaCK: Sentence Ordering with Temporal Commonsense Knowledge appearing at EMNLP 2021.
CICERO
This repository contains the dataset and codes used in our ACL 2022 paper CICERO: A Dataset for Contextualized Commonsense Inference in Dialogues
della
DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling
Emma-X
Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning
ferret
Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique
flan-alpaca
This repository contains code for extending the Stanford Alpaca synthetic instruction tuning to existing instruction-tuned models such as Flan-T5.
flan-eval
This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.
HyperRED
This repository implements our EMNLP 2022 research paper A Dataset for Hyper-Relational Extraction and a Cube-Filling Approach.
minimal-mistakes
:triangular_ruler: Jekyll theme for building a personal site, blog, project documentation, or portfolio.
MSA-Robustness
NAACL 2022 paper on Analyzing Modality Robustness in Multimodal Sentiment Analysis
multimodal-deep-learning
This repository contains various models targetting multimodal representation learning, multimodal fusion for downstream tasks such as multimodal sentiment analysis.
mustango
Mustango: Toward Controllable Text-to-Music Generation
puzzle-reasoning
This repository is maintained to release dataset and models for multimodal puzzle reasoning.
red-instruct
Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment
resta
Restore safety in fine-tuned language models through task arithmetic
speech-adapters
Codes and datasets for our ICASSP2023 paper, Evaluating parameter-efficient transfer learning approaches on SURE benchmark for speech understanding
tango
Codes and Model of the paper "Text-to-Audio Generation using Instruction Tuned LLM and Latent Diffusion Model"
TangoFlux
TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching
trust-align
Codes and datasets for the paper Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse
unifiedqa
UnifiedQA: Crossing Format Boundaries With a Single QA System
walledeval
Test LLMs against jailbreaks and unprecedented harms