PPaperPicks

Yue Dong

University of California, Riverside, CA, USA

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

Venues

Frequent coauthors

Papers

  1. A Real-Time System to Populate FRA Form 57 from News
  2. Anchoring the Cache: Mitigating Contextual Hallucination in KV-Compressed Long-Context Summarization
  3. Harnessing the Unseen: The Hidden Influence of Intrinsic Knowledge in Long-Context Language Models
  4. Attention Eclipse: Manipulating Attention to Bypass LLM Safety-Alignment
  5. ExpertGenQA: Open-ended QA generation in Specialized Domains
  6. HEAL: An Empirical Study on Hallucinations in Embodied Agents Driven by Large Language Models
  7. LaMMA-P: Generalizable Multi-Agent Long-Horizon Task Allocation and Planning with LM-Driven PDDL Planner
  8. Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models
  9. Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning
  10. Adversarial Attacks on Parts of Speech: An Empirical Study in Text-to-Image Generation
  11. Asymmetric Bias in Text-to-Image Generation with Adversarial Attacks
  12. Biasly: An Expert-Annotated Dataset for Subtle Misogyny Detection and Mitigation
  13. Can Textual Unlearning Solve Cross-Modality Safety Alignment?
  14. EcoRank: Budget-Constrained Text Re-ranking Using Large Language Models
  15. How to Leverage Personal Textual Knowledge for Personalized Conversational Information Retrieval
  16. Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models
  17. Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinations
  18. PAT-Questions: A Self-Updating Benchmark for Present-Anchored Temporal Question-Answering
  19. Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack
  20. Vulnerabilities of Large Language Models to Adversarial Attacks
  21. Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedy