PPaperPicks

Weihong Zhong

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

Venues

Frequent coauthors

Papers

  1. Causal Tracing of Object Representations in Large Vision Language Models: Mechanistic Interpretability and Hallucination Mitigation
  2. MPR-GUI: Benchmarking and Enhancing Multilingual Perception and Reasoning in GUI Agents
  3. Question Tells You Where the Answer Is: Intention-aware Long-Context KV Cache Compression
  4. Alleviating Hallucinations from Knowledge Misalignment in Large Language Models via Selective Abstention Learning
  5. Cross-Lingual Text-Rich Visual Comprehension: An Information Theory Perspective
  6. Improving Contextual Faithfulness of Large Language Models via Retrieval Heads-Induced Optimization
  7. Length Controlled Generation for Black-box LLMs
  8. A visualization method for data domain changes in CNN networks and the optimization method for selecting thresholds in classification tasks
  9. Advancing Large Language Model Attribution through Self-Improving
  10. Discrete Modeling via Boundary Conditional Diffusion Processes
  11. Extending Context Window of Large Language Models from a Distributional Perspective
  12. Investigating and Mitigating the Multimodal Hallucination Snowballing in Large Vision-Language Models
    ACL 2024 · Weihong Zhong
  13. Learning Fine-Grained Grounded Citations for Attributed Large Language Models
  14. Length Extrapolation of Transformers: A Survey from the Perspective of Positional Encoding