Daily Papers of 2024-12-02

  1. GRAPE: Generalizing Robot Policy via Preference Alignment 38 upvotes, #1 of 2024-12-02
  2. Beyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTS 30 upvotes, #2 of 2024-12-02
  3. Video Depth without Video Models 28 upvotes, #3 of 2024-12-02
  4. On Domain-Specific Post-Training for Multimodal Large Language Models 24 upvotes, #4 of 2024-12-02
  5. Spatiotemporal Skip Guidance for Enhanced Video Diffusion Sampling 22 upvotes, #5 of 2024-12-02
  6. Yi-Lightning Technical Report 21 upvotes, #6 of 2024-12-02
  7. FAM Diffusion: Frequency and Attention Modulation for High-Resolution Image Generation with Stable Diffusion 17 upvotes, #7 of 2024-12-02
  8. Reverse Thinking Makes LLMs Stronger Reasoners 17 upvotes, #7 of 2024-12-02
  9. Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model 15 upvotes, #9 of 2024-12-02
  10. Puzzle: Distillation-Based NAS for Inference-Optimized LLMs 13 upvotes, #10 of 2024-12-02
  11. Trajectory Attention for Fine-grained Video Motion Control 12 upvotes, #11 of 2024-12-02
  12. Look Every Frame All at Once: Video-Ma^2mba for Efficient Long-form Video Understanding with Multi-Axis Gradient Checkpointing 10 upvotes, #12 of 2024-12-02
  13. Scaling Transformers for Low-Bitrate High-Quality Speech Coding 10 upvotes, #12 of 2024-12-02
  14. MATATA: a weak-supervised MAthematical Tool-Assisted reasoning for Tabular Applications 8 upvotes, #14 of 2024-12-02
  15. DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding 8 upvotes, #14 of 2024-12-02
  16. AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers 7 upvotes, #16 of 2024-12-02
  17. LLM Teacher-Student Framework for Text Classification With No Manually Annotated Data: A Case Study in IPTC News Topic Classification 6 upvotes, #17 of 2024-12-02
  18. AlphaTablets: A Generic Plane Representation for 3D Planar Reconstruction from Monocular Videos 5 upvotes, #18 of 2024-12-02
  19. DeMo: Decoupled Momentum Optimization 3 upvotes, #19 of 2024-12-02
  20. Training Noise Token Pruning 1 upvotes, #20 of 2024-12-02
  21. SpotLight: Shadow-Guided Object Relighting via Diffusion 1 upvotes, #20 of 2024-12-02

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.