Xiyao Wang

Xiyao Wang on Hugging Face Daily Papers: 13 papers, 1 in the top 3 of their day, 592 upvotes.

  1. Agentic Critical Training 13 upvotes, #16 of 2026-03-10
  2. Multi-Crit: Benchmarking Multimodal Judges on Pluralistic Criteria-Following 10 upvotes, #4 of 2025-11-28
  3. ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation 31 upvotes, #8 of 2025-11-04
  4. Agent Learning via Early Experience 223 upvotes, #1 of 2025-10-10
  5. LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training 38 upvotes, #8 of 2025-09-29
  6. LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model 76 upvotes, #4 of 2025-09-03
  7. ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs 20 upvotes, #5 of 2025-06-16
  8. MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning 32 upvotes, #5 of 2025-06-09
  9. SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement 14 upvotes, #10 of 2025-04-11
  10. Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension 6 upvotes, #26 of 2024-12-06
  11. Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning 9 upvotes, #15 of 2024-10-11
  12. LLaVA-Critic: Learning to Evaluate Multimodal Models 31 upvotes, #6 of 2024-10-04
  13. Premier-TACO: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss 10 upvotes, #6 of 2024-02-12

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.