Zichen Wen

Zichen Wen on Hugging Face Daily Papers: 16 papers, 6 in the top 3 of their day, 917 upvotes.

  1. Kimi K2.5: Visual Agentic Intelligence 219 upvotes, #2 of 2026-02-03
  2. Innovator-VL: A Multimodal Large Language Model for Scientific Discovery 76 upvotes, #3 of 2026-01-29
  3. TRivia: Self-supervised Fine-tuning of Vision-Language Models for Table Recognition 9 upvotes, #23 of 2025-12-03
  4. OmniLayout: Enabling Coarse-to-Fine Learning with LLMs for Universal Document Layout Generation 9 upvotes, #14 of 2025-10-31
  5. AI for Service: Proactive Assistance with AI Glasses 71 upvotes, #4 of 2025-10-17
  6. ViCO: A Training Strategy towards Semantic Aware Dynamic High-Resolution 2 upvotes, #36 of 2025-10-15
  7. Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods 11 upvotes, #20 of 2025-10-09
  8. Efficient Multi-modal Large Language Models via Progressive Consistency Distillation 38 upvotes, #3 of 2025-10-06
  9. Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning 65 upvotes, #4 of 2025-10-01
  10. The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs 56 upvotes, #1 of 2025-07-21
  11. EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models 10 upvotes, #16 of 2025-06-18
  12. Shifting AI Efficiency From Model-Centric to Data-Centric Compression 141 upvotes, #2 of 2025-05-27
  13. Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation 19 upvotes, #7 of 2025-03-26
  14. LEGION: Learning to Ground and Explain for Synthetic Image Detection 19 upvotes, #8 of 2025-03-20
  15. OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation 18 upvotes, #7 of 2024-12-04
  16. MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation? 49 upvotes, #1 of 2024-07-09

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.