Daily Papers of 2025-03-06

  1. Babel: Open Multilingual Large Language Models Serving Over 90% of Global Speakers 58 upvotes, #1 of 2025-03-06
  2. HoT: Highlighted Chain of Thought for Referencing Supporting Facts from Inputs 42 upvotes, #2 of 2025-03-06
  3. Process-based Self-Rewarding Language Models 35 upvotes, #3 of 2025-03-06
  4. KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding 26 upvotes, #4 of 2025-03-06
  5. GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control 19 upvotes, #5 of 2025-03-06
  6. ABC: Achieving Better Control of Multimodal Embeddings using VLMs 18 upvotes, #6 of 2025-03-06
  7. Enhancing Abnormality Grounding for Vision Language Models with Knowledge Descriptions 12 upvotes, #7 of 2025-03-06
  8. Fine-Tuning Small Language Models for Domain-Specific AI: An Edge AI Perspective 11 upvotes, #8 of 2025-03-06
  9. CrowdSelect: Synthetic Instruction Data Selection with Multi-LLM Wisdom 10 upvotes, #9 of 2025-03-06
  10. Remasking Discrete Diffusion Models with Inference-Time Scaling 9 upvotes, #10 of 2025-03-06
  11. Mixture of Structural-and-Textual Retrieval over Text-rich Graph Knowledge Bases 6 upvotes, #11 of 2025-03-06
  12. QE4PE: Word-level Quality Estimation for Human Post-Editing 6 upvotes, #11 of 2025-03-06
  13. Exploring Rewriting Approaches for Different Conversational Tasks 5 upvotes, #13 of 2025-03-06
  14. Benchmarking Large Language Models for Multi-Language Software Vulnerability Detection 4 upvotes, #14 of 2025-03-06
  15. FLAME: A Federated Learning Benchmark for Robotic Manipulation 4 upvotes, #14 of 2025-03-06
  16. Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models 4 upvotes, #14 of 2025-03-06
  17. SwiLTra-Bench: The Swiss Legal Translation Benchmark 3 upvotes, #17 of 2025-03-06
  18. CognitiveDrone: A VLA Model and Evaluation Benchmark for Real-Time Cognitive Task Solving and Reasoning in UAVs 3 upvotes, #17 of 2025-03-06
  19. Diverse Controllable Diffusion Policy with Signal Temporal Logic 3 upvotes, #17 of 2025-03-06
  20. Reliable and Efficient Multi-Agent Coordination via Graph Neural Network Variational Autoencoders 3 upvotes, #17 of 2025-03-06
  21. Interact, Instruct to Improve: A LLM-Driven Parallel Actor-Reasoner Framework for Enhancing Autonomous Vehicle Interactions 2 upvotes, #21 of 2025-03-06

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.