Fudan University

Fudan University on Hugging Face Daily Papers: 34 papers, 4 in the top 3 of their day, 1 paper of the day.

  1. Decompose Radicals, Then Reward: Fine-Grained Inspection for Accurate Chinese Text Rendering 5 upvotes, #53 of 2026-10-01
  2. Chinese-Jev: Bringing System One Model to Chinese-Language Tasks 25 upvotes, #38 of 2026-09-30
  3. VideoPhysEdit: Physical Counterfactual Video Editing via Rigid-Body Physical Scene Reconstruction 19 upvotes, #38 of 2026-09-29
  4. All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts 55 upvotes, #6 of 2026-09-23
  5. Agentic Visual Generation: From Generative Models to Agentic Control 36 upvotes, #14 of 2026-09-09
  6. Agents in the Large: Perception-Centered Architecture for Persistent Agents 11 upvotes, #17 of 2026-09-02
  7. Aphanta: Diagnosing Task-Aligned Image-Edited Intermediates for Multimodal Reasoning 3 upvotes, #22 of 2026-08-28
  8. PolicyShiftGuard: Benchmarking and Improving Policy-Adaptive Image Guardrails 38 upvotes, #7 of 2026-07-16
  9. Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods 6 upvotes, #17 of 2026-06-25
  10. FreeStyle: Free Control of Style-Content Dual-Reference Generation from Community LoRA Mining 28 upvotes, #8 of 2026-06-19
  11. RepWAM: World Action Modeling with Representation Visual-Action Tokenizers 6 upvotes, #25 of 2026-06-11
  12. Learning A Unified Risk Map for Autonomous Driving in Partially Observable Environments 8 upvotes, #44 of 2026-05-29
  13. LoMo: Local Modality Substitution for Deeper Vision-Language Fusion 23 upvotes, #17 of 2026-05-29
  14. ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation 87 upvotes, #2 of 2026-05-28
  15. DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes 46 upvotes, #7 of 2026-05-28
  16. SEIF: Self-Evolving Reinforcement Learning for Instruction Following 29 upvotes, #10 of 2026-05-12
  17. Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges 29 upvotes, #4 of 2026-04-23
  18. GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization (V1.0) 12 upvotes, #15 of 2026-04-21
  19. Hierarchical Codec Diffusion for Video-to-Speech Generation 2 upvotes, #27 of 2026-04-20
  20. DARE: Diffusion Large Language Models Alignment and Reinforcement Executor 21 upvotes, #16 of 2026-04-08
  21. PixelSmile: Toward Fine-Grained Facial Expression Editing 116 upvotes, #2 of 2026-03-27
  22. DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use 5 upvotes, #29 of 2026-03-13
  23. OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens 137 upvotes, #1 of 2026-03-03
  24. ArcFlow: Unleashing 2-Step Text-to-Image Generation via High-Precision Non-Linear Flow Distillation 3 upvotes, #37 of 2026-02-12
  25. Unified Personalized Reward Model for Vision Generation 19 upvotes, #14 of 2026-02-04
  26. AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning 47 upvotes, #2 of 2026-01-28
  27. Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment 8 upvotes, #19 of 2026-01-21
  28. The Agent's First Day: Benchmarking Learning, Exploration, and Scheduling in the Workplace Scenarios 7 upvotes, #16 of 2026-01-14
  29. VideoLoom: A Video Large Language Model for Joint Spatial-Temporal Understanding 6 upvotes, #20 of 2026-01-14
  30. FlashPortrait: 6x Faster Infinite Portrait Animation with Adaptive Latent Prediction 10 upvotes, #18 of 2025-12-19
  31. UniREditBench: A Unified Reasoning-based Image Editing Benchmark 36 upvotes, #5 of 2025-11-04
  32. Sparser Block-Sparse Attention via Token Permutation 23 upvotes, #8 of 2025-10-27
  33. LLMs Learn to Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions 22 upvotes, #18 of 2025-10-10
  34. Taming Masked Diffusion Language Models via Consistency Trajectory Reinforcement Learning with Fewer Decoding Step 7 upvotes, #45 of 2025-09-30

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.