Lune

Profiles2022-2026

Wenhu Chen

University of Waterloo

31Papers
21Last author
39Unique co-authors
1First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers31

  1. EditReward: A Human-Aligned Reward Model for Instruction-Guided Image EditingAuthor 6 of 6ICLR 2026 · 60 citations
  2. Emergent Hierarchical Reasoning in LLMs through Reinforcement LearningAuthor 6 of 6ICLR 2026 · 44 citations
  3. Context Forcing: Consistent Autoregressive Video Generation with Long ContextAuthor 8 of 8ICML 2026 · 35 citations
  4. Critique-Coder: Enhancing Coder Models by Critique Reinforcement LearningAuthor 4 of 4ICLR 2026 · 7 citations
  5. VisCoder2: Building Multi-Language Visualization Coding AgentsAuthor 11 of 11ICLR 2026 · 3 citations
  6. VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement LearningAuthor 6 of 7NeurIPS 2025 · 356 citations
  7. General-Reasoner: Advancing LLM Reasoning Across All DomainsAuthor 6 of 6NeurIPS 2025 · 153 citations
  8. ACECODER: Acing Coder RL via Automated Test-Case SynthesisAuthor 6 of 9ACL 2025 · 72 citations
  9. VisualWebInstruct: Scaling up Multimodal Instruction Data through Web SearchAuthor 7 of 7EMNLP 2025 · 29 citations
  10. Pixel Reasoner: Incentivizing Pixel Space Reasoning via Curiosity-Driven Reinforcement LearningAuthor 5 of 5NeurIPS 2025 · 6 citations
  11. VisCoder: Fine-Tuning LLMs for Executable Python Visualization Code GenerationAuthor 5 of 5EMNLP Findings 2025 · 3 citations
  12. VAMBA: Understanding Hour-Long Videos with Hybrid Mamba-TransformersAuthor 6 of 6ICCV 2025 · 2 citations
  13. MEGA-Bench: Scaling Multimodal Evaluation to over 500 Real-World TasksAuthor 16 of 16ICLR 2025
  14. OmniEdit: Building Image Editing Generalist Models Through Specialist SupervisionAuthor 6 of 6ICLR 2025
  15. T2V-Turbo-v2: Enhancing Video Model Post-Training through Data, Reward, and Conditional Guidance DesignAuthor 6 of 11ICLR 2025
  16. VISTA: Enhancing Long-Duration and High-Resolution Video Understanding by Video Spatiotemporal AugmentationAuthor 5 of 5CVPR 2025
  17. VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding TasksAuthor 6 of 6ICLR 2025
  18. MAmmoTH: Building Math Generalist Models through Hybrid Instruction TuningAuthor 8 of 8ICLR 2024 · 558 citations
  19. MMMU: A Massive Multi-Discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIAuthor 22 of 22CVPR 2024 · 213 citations
  20. MAmmoTH2: Scaling Instructions from the WebAuthor 4 of 4NeurIPS 2024 · 176 citations
  21. T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward FeedbackAuthor 6 of 9NeurIPS 2024 · 97 citations
  22. ImagenHub: Standardizing the evaluation of conditional image generation modelsAuthor 7 of 7ICLR 2024 · 71 citations
  23. Augmenting Black-box LLMs with Medical Textbooks for Biomedical Question AnsweringAuthor 3 of 3EMNLP Findings 2024 · 42 citations
  24. VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video GenerationAuthor 19 of 19EMNLP 2024 · 20 citations
  25. Unifying Multimodal Retrieval via Document Screenshot EmbeddingAuthor 4 of 5EMNLP 2024 · 13 citations
  26. On the Risk of Misinformation Pollution with Large Language ModelsAuthor 3 of 6EMNLP Findings 2023 · 85 citations
  27. Few-shot In-context Learning on Knowledge Base Question AnsweringAuthor 5 of 5ACL 2023 · 55 citations
  28. TheoremQA: A Theorem-driven Question Answering DatasetAuthor 1 of 8EMNLP 2023 · 30 citations
  29. EDIS: Entity-Driven Image Search over Multimodal Web ContentAuthor 4 of 5EMNLP 2023 · 6 citations
  30. Controllable Dialogue Simulation with In-context LearningAuthor 2 of 6EMNLP Findings 2022 · 24 citations

Showing the 30 most recent indexed papers.

Dusk over the sea between two cliffs drawn in fine vertical lines