Daily Papers of 2024-10-08

  1. Differential Transformer 148 upvotes, #1 of 2024-10-08
  2. LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations 44 upvotes, #2 of 2024-10-08
  3. VideoGuide: Improving Video Diffusion Models without Training Through a Teacher's Guide 26 upvotes, #3 of 2024-10-08
  4. FAN: Fourier Analysis Networks 24 upvotes, #4 of 2024-10-08
  5. ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery 18 upvotes, #5 of 2024-10-08
  6. Named Clinical Entity Recognition Benchmark 17 upvotes, #6 of 2024-10-08
  7. UniMuMo: Unified Text, Music and Motion Generation 16 upvotes, #7 of 2024-10-08
  8. Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents 16 upvotes, #7 of 2024-10-08
  9. MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion 15 upvotes, #9 of 2024-10-08
  10. TLDR: Token-Level Detective Reward Model for Large Vision Language Models 15 upvotes, #9 of 2024-10-08
  11. Presto! Distilling Steps and Layers for Accelerating Music Generation 15 upvotes, #9 of 2024-10-08
  12. GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models 14 upvotes, #12 of 2024-10-08
  13. MathHay: An Automated Benchmark for Long-Context Mathematical Reasoning in LLMs 13 upvotes, #13 of 2024-10-08
  14. LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning 11 upvotes, #14 of 2024-10-08
  15. OmniBooth: Learning Latent Control for Image Synthesis with Multi-modal Instruction 8 upvotes, #15 of 2024-10-08
  16. TurtleBench: Evaluating Top Language Models via Real-World Yes/No Puzzles 8 upvotes, #15 of 2024-10-08
  17. What Matters for Model Merging at Scale? 7 upvotes, #17 of 2024-10-08
  18. SELECT: A Large-Scale Benchmark of Data Curation Strategies for Image Classification 7 upvotes, #17 of 2024-10-08
  19. Autonomous Character-Scene Interaction Synthesis from Text Instruction 6 upvotes, #19 of 2024-10-08
  20. Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach 4 upvotes, #20 of 2024-10-08
  21. SePPO: Semi-Policy Preference Optimization for Diffusion Alignment 4 upvotes, #20 of 2024-10-08
  22. Grounding Language in Multi-Perspective Referential Communication 3 upvotes, #22 of 2024-10-08
  23. SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model Transformation 1 upvotes, #23 of 2024-10-08

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.