Daily Papers of 2025-02-17

  1. Large Language Diffusion Models 77 upvotes, #1 of 2025-02-17
  2. The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks 53 upvotes, #2 of 2025-02-17
  3. Region-Adaptive Sampling for Diffusion Transformers 52 upvotes, #3 of 2025-02-17
  4. Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model 49 upvotes, #4 of 2025-02-17
  5. ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models 38 upvotes, #5 of 2025-02-17
  6. MM-RLHF: The Next Step Forward in Multimodal LLM Alignment 30 upvotes, #6 of 2025-02-17
  7. DarwinLM: Evolutionary Structured Pruning of Large Language Models 17 upvotes, #7 of 2025-02-17
  8. ImageRAG: Dynamic Image Retrieval for Reference-Guided Image Generation 16 upvotes, #8 of 2025-02-17
  9. Diverse Inference and Verification for Advanced Reasoning 16 upvotes, #8 of 2025-02-17
  10. FoNE: Precise Single-Token Number Embeddings via Fourier Features 11 upvotes, #10 of 2025-02-17
  11. Precise Parameter Localization for Textual Generation in Diffusion Models 11 upvotes, #10 of 2025-02-17
  12. Selective Self-to-Supervised Fine-Tuning for Generalization in Large Language Models 9 upvotes, #12 of 2025-02-17
  13. Small Models, Big Impact: Efficient Corpus and Graph-Based Adaptation of Small Multilingual Language Models for Low-Resource Languages 9 upvotes, #12 of 2025-02-17
  14. We Can't Understand AI Using our Existing Vocabulary 8 upvotes, #14 of 2025-02-17
  15. AdaPTS: Adapting Univariate Foundation Models to Probabilistic Multivariate Time Series Forecasting 8 upvotes, #14 of 2025-02-17
  16. Text-guided Sparse Voxel Pruning for Efficient 3D Visual Grounding 6 upvotes, #16 of 2025-02-17
  17. STMA: A Spatio-Temporal Memory Agent for Long-Horizon Embodied Task Planning 5 upvotes, #17 of 2025-02-17
  18. V2V-LLM: Vehicle-to-Vehicle Cooperative Autonomous Driving with Multi-Modal Large Language Models 4 upvotes, #18 of 2025-02-17
  19. MRS: A Fast Sampler for Mean Reverting Diffusion based on ODE and SDE Solvers 3 upvotes, #19 of 2025-02-17
  20. Jailbreaking to Jailbreak 3 upvotes, #19 of 2025-02-17
  21. Agentic End-to-End De Novo Protein Design for Tailored Dynamics Using a Language Diffusion Model 3 upvotes, #19 of 2025-02-17
  22. CLaMP 3: Universal Music Information Retrieval Across Unaligned Modalities and Unseen Languages 3 upvotes, #19 of 2025-02-17
  23. Cluster and Predict Latents Patches for Improved Masked Image Modeling 2 upvotes, #23 of 2025-02-17

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.