PPaperPicks

Haozhe Wang

14 papers at tracked venues · 12 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. AURORA: Automated Training Framework of Universal Process Reward Models via Ensemble Prompting and Reverse Verification
  2. Benchmarking Multimodal Knowledge Conflict for Large Multimodal Models
  3. RelaCtrl: Relevance-Guided Efficient Control for Diffusion Transformers
  4. SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding
  5. TR-DQ: Time-Rotation Diffusion Quantization
  6. ACECODER: Acing Coder RL via Automated Test-Case Synthesis
  7. Argus: Benchmarking and Enhancing Vision-Language Models for 3D Radiology Report Generation
  8. Can Medical Vision-Language Pre-training Succeed with Purely Synthetic Data?
  9. Knowledge-enhanced Multimodal ECG Representation Learning with Arbitrary-Lead Inputs
  10. Pixel Reasoner: Incentivizing Pixel Space Reasoning via Curiosity-Driven Reinforcement Learning
  11. Renderworld: World Model with Self-Supervised 3D Label
  12. To Code or not to Code? Adaptive Tool Integration for Math Language Models via Expectation-Maximization
    ACL 2025 · Haozhe Wang
  13. VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning
    NeurIPS 2025 · Haozhe Wang
  14. V-PETL Bench: A Unified Visual Parameter-Efficient Transfer Learning Benchmark