Daily Papers of 2024-06-25

  1. DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation 53 upvotes, #1 of 2024-06-25
  2. Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs 48 upvotes, #2 of 2024-06-25
  3. Evaluating D-MERIT of Partial-annotation on Information Retrieval 34 upvotes, #3 of 2024-06-25
  4. Long Context Transfer from Language to Vision 30 upvotes, #4 of 2024-06-25
  5. Video-Infinity: Distributed Long Video Generation 25 upvotes, #5 of 2024-06-25
  6. VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Models 22 upvotes, #6 of 2024-06-25
  7. Scaling Laws for Linear Complexity Language Models 21 upvotes, #7 of 2024-06-25
  8. WARP: On the Benefits of Weight Averaged Rewarded Policies 19 upvotes, #8 of 2024-06-25
  9. Efficient Continual Pre-training by Mitigating the Stability Gap 18 upvotes, #9 of 2024-06-25
  10. Sparser is Faster and Less is More: Efficient Sparse Attention for Long-Range Transformers 16 upvotes, #10 of 2024-06-25
  11. Towards Fast Multilingual LLM Inference: Speculative Decoding and Specialized Drafters 16 upvotes, #10 of 2024-06-25
  12. Beyond the Turn-Based Game: Enabling Real-Time Conversations with Duplex Models 14 upvotes, #12 of 2024-06-25
  13. Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs 13 upvotes, #13 of 2024-06-25
  14. Preference Tuning For Toxicity Mitigation Generalizes Across Languages 12 upvotes, #14 of 2024-06-25
  15. Confidence Regulation Neurons in Language Models 10 upvotes, #15 of 2024-06-25
  16. AutoDetect: Towards a Unified Framework for Automated Weakness Detection in Large Language Models 10 upvotes, #15 of 2024-06-25
  17. How Many Parameters Does it Take to Change a Light Bulb? Evaluating Performance in Self-Play of Conversational Games as a Function of Model Characteristics 9 upvotes, #17 of 2024-06-25
  18. ClotheDreamer: Text-Guided Garment Generation with 3D Gaussians 7 upvotes, #18 of 2024-06-25
  19. IRASim: Learning Interactive Real-Robot Action Simulators 6 upvotes, #19 of 2024-06-25
  20. Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization 6 upvotes, #19 of 2024-06-25
  21. Can Few-shot Work in Long-Context? Recycling the Context to Generate Demonstrations 5 upvotes, #21 of 2024-06-25
  22. video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models 5 upvotes, #21 of 2024-06-25
  23. Repulsive Score Distillation for Diverse Sampling of Diffusion Models 4 upvotes, #23 of 2024-06-25
  24. OlympicArena Medal Ranks: Who Is the Most Intelligent AI So Far? 3 upvotes, #24 of 2024-06-25

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.