Daily Papers of 2024-10-16

  1. Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free 45 upvotes, #1 of 2024-10-16
  2. LLMtimesMapReduce: Simplified Long-Sequence Processing using Large Language Models 36 upvotes, #2 of 2024-10-16
  3. Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family Experts 36 upvotes, #2 of 2024-10-16
  4. What Matters in Transformers? Not All Attention is Needed 27 upvotes, #4 of 2024-10-16
  5. MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation 24 upvotes, #5 of 2024-10-16
  6. LVD-2M: A Long-take Video Dataset with Temporally Dense Captions 18 upvotes, #6 of 2024-10-16
  7. MTU-Bench: A Multi-granularity Tool-Use Benchmark for Large Language Models 17 upvotes, #7 of 2024-10-16
  8. Efficient Diffusion Models: A Comprehensive Survey from Principles to Practices 14 upvotes, #8 of 2024-10-16
  9. SecCodePLT: A Unified Platform for Evaluating the Security of Code GenAI 12 upvotes, #9 of 2024-10-16
  10. EchoPrime: A Multi-Video View-Informed Vision-Language Model for Comprehensive Echocardiography Interpretation 11 upvotes, #10 of 2024-10-16
  11. NesTools: A Dataset for Evaluating Nested Tool Learning Abilities of Large Language Models 11 upvotes, #10 of 2024-10-16
  12. Agent-as-a-Judge: Evaluate Agents with Agents 9 upvotes, #12 of 2024-10-16
  13. GS^3: Efficient Relighting with Triple Gaussian Splatting 9 upvotes, #12 of 2024-10-16
  14. SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning 7 upvotes, #14 of 2024-10-16
  15. Towards Synergistic, Generalized, and Efficient Dual-System for Robotic Manipulation 4 upvotes, #15 of 2024-10-16
  16. Towards Natural Image Matting in the Wild via Real-Scenario Prior 2 upvotes, #16 of 2024-10-16
  17. Empirical Study of Mutual Reinforcement Effect and Application in Few-shot Text Classification Tasks via Prompt 2 upvotes, #16 of 2024-10-16
  18. MultiVENT 2.0: A Massive Multilingual Benchmark for Event-Centric Video Retrieval 1 upvotes, #18 of 2024-10-16

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.