Daily Papers of 2025-06-24

  1. Light of Normals: Unified Feature Representation for Universal Photometric Stereo 80 upvotes, #1 of 2025-06-24
  2. OmniGen2: Exploration to Advanced Multimodal Generation 68 upvotes, #2 of 2025-06-24
  3. LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning 51 upvotes, #3 of 2025-06-24
  4. OAgents: An Empirical Study of Building Effective Agents 34 upvotes, #4 of 2025-06-24
  5. RLPR: Extrapolating RLVR to General Domains without Verifiers 31 upvotes, #5 of 2025-06-24
  6. Phantom-Data : Towards a General Subject-Consistent Video Generation Dataset 28 upvotes, #6 of 2025-06-24
  7. ViDAR: Video Diffusion-Aware 4D Reconstruction From Monocular Inputs 27 upvotes, #7 of 2025-06-24
  8. ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs 27 upvotes, #7 of 2025-06-24
  9. Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations 25 upvotes, #9 of 2025-06-24
  10. DIP: Unsupervised Dense In-Context Post-training of Visual Representations 18 upvotes, #10 of 2025-06-24
  11. VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory 18 upvotes, #10 of 2025-06-24
  12. 3D Arena: An Open Platform for Generative 3D Evaluation 11 upvotes, #12 of 2025-06-24
  13. LettinGo: Explore User Profile Generation for Recommendation System 10 upvotes, #13 of 2025-06-24
  14. SlimMoE: Structured Compression of Large MoE Models via Expert Slimming and Distillation 10 upvotes, #13 of 2025-06-24
  15. From Virtual Games to Real-World Play 10 upvotes, #13 of 2025-06-24
  16. Enhancing Step-by-Step and Verifiable Medical Reasoning in MLLMs 9 upvotes, #16 of 2025-06-24
  17. 4Real-Video-V2: Fused View-Time Attention and Feedforward Reconstruction for 4D Scene Generation 9 upvotes, #16 of 2025-06-24
  18. FinCoT: Grounding Chain-of-Thought in Expert Financial Reasoning 8 upvotes, #18 of 2025-06-24
  19. Robust Reward Modeling via Causal Rubrics 7 upvotes, #19 of 2025-06-24
  20. How Alignment Shrinks the Generative Horizon 7 upvotes, #19 of 2025-06-24
  21. Auto-Regressively Generating Multi-View Consistent Images 7 upvotes, #19 of 2025-06-24
  22. ReDit: Reward Dithering for Improved LLM Policy Optimization 7 upvotes, #19 of 2025-06-24
  23. TC-Light: Temporally Consistent Relighting for Dynamic Long Videos 7 upvotes, #19 of 2025-06-24
  24. ConsumerBench: Benchmarking Generative AI Applications on End-User Devices 6 upvotes, #24 of 2025-06-24
  25. FaithfulSAE: Towards Capturing Faithful Features with Sparse Autoencoders without External Dataset Dependencies 6 upvotes, #24 of 2025-06-24
  26. Steering Conceptual Bias via Transformer Latent-Subspace Activation 6 upvotes, #24 of 2025-06-24
  27. I Know Which LLM Wrote Your Code Last Summer: LLM generated Code Stylometry for Authorship Attribution 5 upvotes, #27 of 2025-06-24
  28. CommVQ: Commutative Vector Quantization for KV Cache Compression 5 upvotes, #27 of 2025-06-24
  29. 4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time 5 upvotes, #27 of 2025-06-24
  30. Demystifying the Visual Quality Paradox in Multimodal Large Language Models 4 upvotes, #30 of 2025-06-24
  31. SoK: Evaluating Jailbreak Guardrails for Large Language Models 3 upvotes, #31 of 2025-06-24
  32. CultureMERT: Continual Pre-Training for Cross-Cultural Music Representation Learning 3 upvotes, #31 of 2025-06-24
  33. GEMeX-ThinkVG: Towards Thinking with Visual Grounding in Medical VQA via Reinforcement Learning 3 upvotes, #31 of 2025-06-24
  34. Audit & Repair: An Agentic Framework for Consistent Story Visualization in Text-to-Image Diffusion Models 3 upvotes, #31 of 2025-06-24
  35. Spec2RTL-Agent: Automated Hardware Code Generation from Complex Specifications Using LLM Agent Systems 2 upvotes, #35 of 2025-06-24
  36. A deep learning and machine learning approach to predict neonatal death in the context of São Paulo 2 upvotes, #35 of 2025-06-24
  37. TPTT: Transforming Pretrained Transformer into Titans 2 upvotes, #35 of 2025-06-24
  38. RePIC: Reinforced Post-Training for Personalizing Multi-Modal Language Models 2 upvotes, #35 of 2025-06-24
  39. Quantifying Fairness in LLMs Beyond Tokens: A Semantic and Statistical Perspective 1 upvotes, #39 of 2025-06-24

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.