PPaperPicks

Chao Zhang

Georgia Institute of Technology, College of Computing, Atlanta, GA, USA

32 papers at tracked venues · 20 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Do LLMs Catch Their Own Mistakes? A Comprehensive Benchmark for Reflective Tool Use LLMs
  2. OpenDecoder: Open Large Language Model Decoding to Incorporate Document Quality in RAG
  3. Calibrating Pre-trained Language Classifiers on LLM-generated Noisy Labels via Iterative Refinement
  4. DF2: Distribution-Free Decision-Focused Learning
  5. DORM: Preference Data Weights Optimization for Reward Modeling in LLM Alignment
  6. Diffusion Models as Constrained Samplers for Optimization with Unknown Constraints
  7. Efficient Evolutionary Search Over Chemical Space with Large Language Models
  8. Ensembles of Low-Rank Expert Adapters
  9. Hephaestus: Improving Fundamental Agent Capabilities of Large Language Models through Continual Pre-Training
  10. LLM-Augmented Chemical Synthesis and Design Decision Programs
  11. MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering
  12. Matryoshka Pilot: Learning to Drive Black-Box LLMs with LLMs
  13. RenderBender: A Survey on Adversarial Attacks Using Differentiable Rendering
  14. Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models
  15. WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning
  16. A Simple but Effective Approach to Improve Structured Language Model Output for Information Extraction
  17. Aligning Large Language Models with Representation Editing: A Control Perspective
  18. Assessing Logical Puzzle Solving in Large Language Models: Insights from a Minesweeper Case Study
  19. BBox-Adapter: Lightweight Adapting for Black-Box Large Language Models
  20. BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrievers
  21. Data Diversity Matters for Robust Instruction Tuning
  22. Explanation-aware Soft Ensemble Empowers Large Language Model In-context Learning
  23. HYDRA: Model Factorization Framework for Black-Box LLM Personalization
  24. Knowledge Distillation with Perturbed Loss: From a Vanilla Teacher to a Proxy Teacher
  25. PLaD: Preference-based Large Language Model Distillation with Pseudo-Preference Pairs
  26. POLYIE: A Dataset of Information Extraction from Polymer Material Scientific Literature
  27. ProgGen: Generating Named Entity Recognition Datasets Step-by-step with Self-Reflexive Large Language Models
  28. Time-MMD: Multi-Domain Multimodal Dataset for Time Series Analysis
  29. Time-Series Forecasting for Out-of-Distribution Generalization Using Invariant Learning
  30. ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search
  31. Towards Modeling Uncertainties of Self-Explaining Neural Networks via Conformal Prediction
  32. Two Birds with One Stone: Enhancing Uncertainty Quantification and Interpretability with Graph Functional Neural Process