Daily Papers of 2025-02-14

  1. The Stochastic Parrot on LLM's Shoulder: A Summative Assessment of Physical Concept Understanding 180 upvotes, #1 of 2025-02-14
  2. InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU 139 upvotes, #2 of 2025-02-14
  3. Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generation 39 upvotes, #3 of 2025-02-14
  4. TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models 32 upvotes, #4 of 2025-02-14
  5. EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents 32 upvotes, #4 of 2025-02-14
  6. Can this Model Also Recognize Dogs? Zero-Shot Model Search from Weights 31 upvotes, #6 of 2025-02-14
  7. An Open Recipe: Adapting Language-Specific LLMs to a Reasoning Model in One Day via Model Merging 30 upvotes, #7 of 2025-02-14
  8. SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models 30 upvotes, #7 of 2025-02-14
  9. CoSER: Coordinating LLM-Based Persona Simulation of Established Roles 27 upvotes, #9 of 2025-02-14
  10. MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency 27 upvotes, #9 of 2025-02-14
  11. Exploring the Potential of Encoder-free Architectures in 3D LMMs 26 upvotes, #11 of 2025-02-14
  12. Logical Reasoning in Large Language Models: A Survey 21 upvotes, #12 of 2025-02-14
  13. Typhoon T1: An Open Thai Reasoning Model 16 upvotes, #13 of 2025-02-14
  14. SQuARE: Sequential Question Answering Reasoning Engine for Enhanced Chain-of-Thought in Large Language Models 16 upvotes, #13 of 2025-02-14
  15. mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data 13 upvotes, #15 of 2025-02-14
  16. CoT-Valve: Length-Compressible Chain-of-Thought Tuning 12 upvotes, #16 of 2025-02-14
  17. DexTrack: Towards Generalizable Neural Tracking Control for Dexterous Manipulation from Human References 12 upvotes, #16 of 2025-02-14
  18. Mathematical Reasoning in Large Language Models: Assessing Logical and Arithmetic Errors across Wide Numerical Ranges 11 upvotes, #18 of 2025-02-14
  19. VFX Creator: Animated Visual Effect Generation with Controllable Diffusion Transformer 7 upvotes, #19 of 2025-02-14
  20. 3CAD: A Large-Scale Real-World 3C Product Dataset for Unsupervised Anomaly 6 upvotes, #20 of 2025-02-14
  21. Latent Radiance Fields with 3D-aware 2D Representations 6 upvotes, #20 of 2025-02-14

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.