PPaperPicks

Zhihao Zhang

11 papers at tracked venues · 8 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments
  2. AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progress
  3. LLMEval-Fair: A Large-Scale Longitudinal Study on Robust and Fair Evaluation of Large Language Models
  4. Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
  5. Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination
  6. What Makes a Good Speech Tokenizer for LLM-Centric Speech Generation? A Systematic Study
  7. LoRACoE: Improving Large Language Model via Composition-based LoRA Expert
  8. PFDial: A Structured Dialogue Instruction Fine-tuning Method Based on UML Flowcharts
  9. Improving Discriminative Capability of Reward Models in RLHF Using Contrastive Learning
  10. PDF-to-Tree: Parsing PDF Text Blocks into a Tree
  11. Unveiling Linguistic Regions in Large Language Models
    ACL 2024 · Zhihao Zhang