Daily Papers of 2024-10-25

  1. Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss 82 upvotes, #1 of 2024-10-25
  2. Can Knowledge Editing Really Correct Hallucinations? 50 upvotes, #2 of 2024-10-25
  3. LOGO -- Long cOntext aliGnment via efficient preference Optimization 42 upvotes, #3 of 2024-10-25
  4. Unleashing Reasoning Capability of LLMs via Scalable Question Synthesis from Scratch 37 upvotes, #4 of 2024-10-25
  5. Framer: Interactive Frame Interpolation 34 upvotes, #5 of 2024-10-25
  6. Unbounded: A Generative Infinite Game of Character Life Simulation 32 upvotes, #6 of 2024-10-25
  7. Distill Visual Chart Reasoning Ability from LLMs to MLLMs 18 upvotes, #7 of 2024-10-25
  8. Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering 17 upvotes, #8 of 2024-10-25
  9. Why Does the Effective Context Length of LLMs Fall Short? 15 upvotes, #9 of 2024-10-25
  10. Taipan: Efficient and Expressive State Space Language Models with Selective Attention 14 upvotes, #10 of 2024-10-25
  11. SMITE: Segment Me In TimE 13 upvotes, #11 of 2024-10-25
  12. MotionCLR: Motion Generation and Training-free Editing via Understanding Attention Mechanisms 13 upvotes, #11 of 2024-10-25
  13. Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs 12 upvotes, #13 of 2024-10-25
  14. WAFFLE: Multi-Modal Model for Automated Front-End Development 11 upvotes, #14 of 2024-10-25
  15. Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances 9 upvotes, #15 of 2024-10-25
  16. Stable Consistency Tuning: Understanding and Improving Consistency Models 9 upvotes, #15 of 2024-10-25
  17. CCI3.0-HQ: a large-scale Chinese dataset of high quality designed for pre-training large language models 8 upvotes, #17 of 2024-10-25
  18. CAMEL-Bench: A Comprehensive Arabic LMM Benchmark 8 upvotes, #17 of 2024-10-25
  19. ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning 7 upvotes, #19 of 2024-10-25
  20. DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations 7 upvotes, #19 of 2024-10-25
  21. Language Models are Symbolic Learners in Arithmetic 6 upvotes, #21 of 2024-10-25
  22. Value Residual Learning For Alleviating Attention Concentration In Transformers 6 upvotes, #21 of 2024-10-25
  23. Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models 5 upvotes, #23 of 2024-10-25
  24. The Nature of Mathematical Modeling and Probabilistic Optimization Engineering in Generative AI 5 upvotes, #23 of 2024-10-25
  25. Should We Really Edit Language Models? On the Evaluation of Edited Language Models 5 upvotes, #23 of 2024-10-25
  26. ZIP-FIT: Embedding-Free Data Selection via Compression-Based Alignment 4 upvotes, #26 of 2024-10-25
  27. Data Scaling Laws in Imitation Learning for Robotic Manipulation 4 upvotes, #26 of 2024-10-25
  28. Pantograph: A Machine-to-Machine Interaction Interface for Advanced Theorem Proving, High Level Reasoning, and Data Extraction in Lean 4 3 upvotes, #28 of 2024-10-25
  29. Multi-Draft Speculative Sampling: Canonical Architectures and Theoretical Limits 3 upvotes, #28 of 2024-10-25

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.