主要是记录一些这几年读的 paper，持续搬运中，欢迎指正
主要领域 LLM, Video, Low-level Vision, Reinfercement Learning
扩展阅读： 走出新手村」十次 CV 论文会议投稿的经验总结.pdf
Organize some of my insights and paper reading records. Total Count：54
- 2024 - MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models
- 2024 - Solving olympiad geometry without human demonstrations
- 2024 - RealChat-1M: A Large-Scale Real-World LLM Conversation Dataset
- 2024 - ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search
- 2024 - xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval
- 2023 - Offline RL for Natural Language Generation with Implicit Language Q Learning
- 2023 - MarioGPT: Open-Ended Text2Level Generation through Large Language Models
- 2023 - A Comparative Study between Full-Parameter and LoRA-based Fine-Tuning on Chinese Instruction Data for Instruction Following Large Language Model
- 2023 - OctoPack: Instruction Tuning Code Large Language Models
- 2022 - SCIENCEWORLD: Is your Agent Smarter than a 5th Grader?
- 2022 - OPT: Open Pre-trained Transformer Language Models
- 2022 - Constitutional AI: Harmlessness from AI Feedback
- 2022 - Training Compute-Optimal Large Language Models
- 2021 - Aligning AI With Shared Human Values
- 2023 - Learning About Progress From Experts
- 2023 - Mastering Diverse Domains through World Models
- 2023 - Become a Proficient Player with Limited Data through Watching Pure Videos
- 2022 - NeoRL: A Near Real-World Benchmark for Offline Reinforcement Learning
- 2022 - Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos
- 2021 - What Matters for On-Policy Deep Actor-Critic Methods? A Large-Scale Study
- 2019 - Learning to Paint with Model-based Deep Reinforcement Learning
- 2018 - Playing text-adventure games with graph-based deep reinforcement learning
- 2022 - Zero-Shot Text-Guided Object Generation with Dream Fields
- 2022 - Simple Baselines for Image Restoration
- 2022 - RepSR: Training Efficient VGG-style Super-Resolution Networks with Structural Re-Parameterization and Batch Normalization
- 2020 - Reference-Based Sketch Image Colorization using Augmented-Self Reference and Dense Semantic Correspondence
- 2019 - Single Image Reflection Removal Exploiting Misaligned Training Data and Network Enhancements
- 2019 - Towards Optimal Structured CNN Pruning via Generative Adversarial Learning
- 2023 - A Dynamic Multi-Scale Voxel Flow Network for Video Prediction
- 2022 - Disentangling Architecture and Training for Optical Flow
- 2022 - Unifying Flow, Stereo and Depth Estimation
- 2022 - Real-Time Intermediate Flow Estimation for Video Frame Interpolation
- 2022 - VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution
- 2022 - SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image
- 2020 - UPFlow: Upsampling Pyramid for Unsupervised Optical Flow Learning
- 2020 - Softmax Splatting for Video Frame Interpolation
- 2020 - MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask
- 2020 - ScopeFlow: Dynamic Scene Scoping for Optical Flow
- 2020 - What Matters in Unsupervised Optical Flow
- 2020 - RAFT: Recurrent All-Pairs Field Transforms for Optical Flow
- 2019 - Depth-Aware Video Frame Interpolation
- 2016 - FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
- 2022 - One-Shot Adaptation of GAN in Just One CLIP
- 2022 - Splicing ViT Features for Semantic Appearance Transfer
- 2022 - Online convolutional re-parameterization
- 2021 - Diverse Branch Block: Building a Convolution as an Inception-like Unit
- 2021 - RepVGG: Making VGG-Style ConvNets Great Again
- 2020 - Designing network design spaces
- 2019 - ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks
- 2016 - Aggregated Residual Transformations for Deep Neural Networks