Daily Papers of 2025-12-02

  1. From Code Foundation Models to Agents and Applications: A Practical Guide to Code Intelligence 248 upvotes, #1 of 2025-12-02
  2. LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling 150 upvotes, #2 of 2025-12-02
  3. Envision: Benchmarking Unified Understanding & Generation for Causal World Process Insights 88 upvotes, #3 of 2025-12-02
  4. Stabilizing Reinforcement Learning with LLMs: Formulation and Practices 83 upvotes, #4 of 2025-12-02
  5. TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models 60 upvotes, #5 of 2025-12-02
  6. How Far Are We from Genuinely Useful Deep Research Agents? 51 upvotes, #6 of 2025-12-02
  7. What about gravity in video generation? Post-Training Newton's Laws with Verifiable Rewards 47 upvotes, #7 of 2025-12-02
  8. Infinity-RoPE: Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rollout 44 upvotes, #8 of 2025-12-02
  9. The Consistency Critic: Correcting Inconsistencies in Generated Images via Reference-Guided Attentive Alignment 38 upvotes, #9 of 2025-12-02
  10. Wikontic: Constructing Wikidata-Aligned, Ontology-Aware Knowledge Graphs with Large Language Models 38 upvotes, #9 of 2025-12-02
  11. LFM2 Technical Report 34 upvotes, #11 of 2025-12-02
  12. Flash-DMD: Towards High-Fidelity Few-Step Image Generation with Efficient Distillation and Joint Reinforcement Learning 24 upvotes, #12 of 2025-12-02
  13. VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference 23 upvotes, #13 of 2025-12-02
  14. GR-RL: Going Dexterous and Precise for Long-Horizon Robotic Manipulation 23 upvotes, #13 of 2025-12-02
  15. Rectifying LLM Thought from Lens of Optimization 23 upvotes, #13 of 2025-12-02
  16. Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model 17 upvotes, #16 of 2025-12-02
  17. MultiBanana: A Challenging Benchmark for Multi-Reference Text-to-Image Generation 15 upvotes, #17 of 2025-12-02
  18. Where Culture Fades: Revealing the Cultural Gap in Text-to-Image Generation 14 upvotes, #18 of 2025-12-02
  19. Flow Straighter and Faster: Efficient One-Step Generative Modeling via MeanFlow on Rectified Trajectories 14 upvotes, #18 of 2025-12-02
  20. SpeContext: Enabling Efficient Long-context Reasoning with Speculative Context Sparsity in LLMs 14 upvotes, #18 of 2025-12-02
  21. Accelerating Streaming Video Large Language Models via Hierarchical Token Compression 14 upvotes, #18 of 2025-12-02
  22. InternVideo-Next: Towards General Video Foundation Models without Video-Text Supervision 14 upvotes, #18 of 2025-12-02
  23. SCALE: Selective Resource Allocation for Overcoming Performance Bottlenecks in Mathematical Test-time Scaling 8 upvotes, #23 of 2025-12-02
  24. PromptBridge: Cross-Model Prompt Transfer for Large Language Models 8 upvotes, #23 of 2025-12-02
  25. Script: Graph-Structured and Query-Conditioned Semantic Token Pruning for Multimodal Large Language Models 8 upvotes, #23 of 2025-12-02
  26. ORION: Teaching Language Models to Reason Efficiently in the Language of Thought 7 upvotes, #26 of 2025-12-02
  27. StreamGaze: Gaze-Guided Temporal Reasoning and Proactive Understanding in Streaming Videos 7 upvotes, #26 of 2025-12-02
  28. HiconAgent: History Context-aware Policy Optimization for GUI Agents 5 upvotes, #28 of 2025-12-02
  29. CauSight: Learning to Supersense for Visual Causal Discovery 5 upvotes, #28 of 2025-12-02
  30. Asking like Socrates: Socrates helps VLMs understand remote sensing images 4 upvotes, #30 of 2025-12-02
  31. POLARIS: Projection-Orthogonal Least Squares for Robust and Adaptive Inversion in Diffusion Models 4 upvotes, #30 of 2025-12-02
  32. Seeing the Wind from a Falling Leaf 4 upvotes, #30 of 2025-12-02
  33. Learning Eigenstructures of Unstructured Data Manifolds 4 upvotes, #30 of 2025-12-02
  34. OpenREAD: Reinforced Open-Ended Reasoing for End-to-End Autonomous Driving with LLM-as-Critic 3 upvotes, #34 of 2025-12-02
  35. Agentic Policy Optimization via Instruction-Policy Co-Evolution 3 upvotes, #34 of 2025-12-02
  36. IndicParam: Benchmark to evaluate LLMs on low-resource Indic Languages 2 upvotes, #36 of 2025-12-02
  37. WiseEdit: Benchmarking Cognition- and Creativity-Informed Image Editing 2 upvotes, #36 of 2025-12-02
  38. Generalist Large Language Models Outperform Clinical Tools on Medical Benchmarks 2 upvotes, #36 of 2025-12-02
  39. ChronosObserver: Taming 4D World with Hyperspace Diffusion Sampling 2 upvotes, #36 of 2025-12-02
  40. The Art of Scaling Test-Time Compute for Large Language Models 2 upvotes, #36 of 2025-12-02
  41. Structured Extraction from Business Process Diagrams Using Vision-Language Models 1 upvotes, #41 of 2025-12-02
  42. A Hierarchical Framework for Humanoid Locomotion with Supernumerary Limbs 1 upvotes, #41 of 2025-12-02
  43. DreamingComics: A Story Visualization Pipeline via Subject and Layout Customized Generation using Video Models 1 upvotes, #41 of 2025-12-02
  44. OmniFusion: Simultaneous Multilingual Multimodal Translations via Modular Fusion 1 upvotes, #44 of 2025-12-02
  45. Doppler-Enhanced Deep Learning: Improving Thyroid Nodule Segmentation with YOLOv5 Instance Segmentation 1 upvotes, #44 of 2025-12-02
  46. MEGConformer: Conformer-Based MEG Decoder for Robust Speech and Phoneme Classification 1 upvotes, #44 of 2025-12-02
  47. Generative Video Motion Editing with 3D Point Tracks 4 upvotes, #44 of 2025-12-02

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.