Daily Papers of 2025-02-05

  1. VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models 50 upvotes, #1 of 2025-02-05
  2. Inverse Bridge Matching Distillation 25 upvotes, #2 of 2025-02-05
  3. ACECODER: Acing Coder RL via Automated Test-Case Synthesis 23 upvotes, #3 of 2025-02-05
  4. Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search 18 upvotes, #4 of 2025-02-05
  5. QLASS: Boosting Language Agent Inference via Q-Guided Stepwise Search 14 upvotes, #5 of 2025-02-05
  6. Can LLMs Maintain Fundamental Abilities under KV Cache Compression? 11 upvotes, #6 of 2025-02-05
  7. Concept Steerers: Leveraging K-Sparse Autoencoders for Controllable Generations 10 upvotes, #7 of 2025-02-05
  8. Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial? 9 upvotes, #8 of 2025-02-05
  9. COCONut-PanCap: Joint Panoptic Segmentation and Grounded Captions for Fine-Grained Understanding and Generation 8 upvotes, #9 of 2025-02-05
  10. Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Models 7 upvotes, #10 of 2025-02-05
  11. Generating Multi-Image Synthetic Data for Text-to-Image Customization 5 upvotes, #11 of 2025-02-05
  12. Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification 4 upvotes, #12 of 2025-02-05
  13. Federated Sketching LoRA: On-Device Collaborative Fine-Tuning of Large Language Models 2 upvotes, #13 of 2025-02-05
  14. Activation Approximations Can Incur Safety Vulnerabilities Even in Aligned LLMs: Comprehensive Analysis and Defense 0 upvotes, #14 of 2025-02-05

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.