Daily Papers of 2025-02-07

  1. Analyze Feature Flow to Enhance Interpretation and Steering in Language Models 53 upvotes, #1 of 2025-02-07
  2. Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2 39 upvotes, #2 of 2025-02-07
  3. ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features 31 upvotes, #3 of 2025-02-07
  4. DynVFX: Augmenting Real Videos with Dynamic Content 27 upvotes, #4 of 2025-02-07
  5. Great Models Think Alike and this Undermines AI Oversight 25 upvotes, #5 of 2025-02-07
  6. Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis 22 upvotes, #6 of 2025-02-07
  7. BOLT: Bootstrap Long Chain-of-Thought in Language Models without Distillation 21 upvotes, #7 of 2025-02-07
  8. Ola: Pushing the Frontiers of Omni-Modal Language Model with Progressive Modality Alignment 21 upvotes, #7 of 2025-02-07
  9. Weak-to-Strong Diffusion with Reflection 20 upvotes, #9 of 2025-02-07
  10. UltraIF: Advancing Instruction Following from the Wild 20 upvotes, #9 of 2025-02-07
  11. MAGA: MAssive Genre-Audience Reformulation to Pretraining Corpus Expansion 17 upvotes, #11 of 2025-02-07
  12. ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization 17 upvotes, #11 of 2025-02-07
  13. MotionLab: Unified Human Motion Generation and Editing via the Motion-Condition-Motion Paradigm 15 upvotes, #13 of 2025-02-07
  14. MotionCanvas: Cinematic Shot Design with Controllable Image-to-Video Generation 14 upvotes, #14 of 2025-02-07
  15. PILAF: Optimal Human Preference Sampling for Reward Modeling 10 upvotes, #15 of 2025-02-07
  16. Beyond Prompt Content: Enhancing LLM Performance via Content-Format Integrated Prompt Optimization 10 upvotes, #15 of 2025-02-07
  17. Towards Physical Understanding in Video Generation: A 3D Point Regularization Approach 8 upvotes, #17 of 2025-02-07
  18. ChartCitor: Multi-Agent Framework for Fine-Grained Chart Visual Attribution 7 upvotes, #18 of 2025-02-07
  19. Learning Real-World Action-Video Dynamics with Heterogeneous Masked Autoregression 6 upvotes, #19 of 2025-02-07
  20. PlotGen: Multi-Agent LLM-based Scientific Data Visualization via Multimodal Feedback 5 upvotes, #20 of 2025-02-07
  21. Enhancing Code Generation for Low-Resource Languages: No Silver Bullet 4 upvotes, #21 of 2025-02-07
  22. Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions 3 upvotes, #22 of 2025-02-07

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.