PPaperPicks

Zhiyuan Hu

15 papers at tracked venues · 10 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models
    ACL 2026 · Zhiyuan Hu
  2. Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation
  3. Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs
    ACL 2026 · Zhiyuan Hu
  4. BehaviorSFT: Behavioral Token Conditioning for Health Agents Across the Proactivity Spectrum
  5. CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases
  6. LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models
    ACL 2025 · Zhiyuan Hu
  7. MMVU: Measuring Expert-Level Multi-Discipline Video Understanding
  8. Multi-Scale Contrastive Learning for Video Temporal Grounding
  9. Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs
  10. Encoding and Controlling Global Semantics for Long-form Video Question Answering
  11. MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration
  12. Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning
  13. PoetryDiffusion: Towards Joint Semantic and Metrical Manipulation in Poetry Generation
    AAAI 2024 · Zhiyuan Hu
  14. READ-PVLA: Recurrent Adapter with Partial Video-Language Alignment for Parameter-Efficient Transfer Learning in Low-Resource Video-Language Modeling
  15. Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in LLMs
    NeurIPS 2024 · Zhiyuan Hu