PPaperPicks

Xiang Liu

Hong Kong University of Science and Technology, Guang Zhou, China

16 papers at tracked venues · 13 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Probing the Plasticity and Correlation of LLM Value Systems: LLM Value Rankings are Not Stable
  2. Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression
  3. ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference
    NeurIPS 2025 · Xiang Liu
  4. City-VLM: Towards Multidomain Perception Scene Understanding via Multimodal Incomplete Learning
  5. EssayJudge: A Multi-Granular Benchmark for Assessing Automated Essay Scoring Capabilities of Multimodal Large Language Models
  6. ParZC: Parametric Zero-Cost Proxies for Efficient NAS
  7. Perovskite-LLM: Knowledge-Enhanced Large Language Models for Perovskite Solar Cell Research
    EMNLP 2025 · Xiang Liu
  8. 3D Question Answering for City Scene Understanding
  9. Active Prompting with Chain-of-Thought for Large Language Models
  10. Discovering Sparsity Allocation for Layer-wise Pruning of Large Language Models
  11. LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning
  12. LPZero: Language Model Zero-cost Proxy Search from Zero
  13. LongGenBench: Long-context Generation Benchmark
    EMNLP 2024 · Xiang Liu
  14. Plum: Prompt Learning using Metaheuristics
  15. Pruner-Zero: Evolving Symbolic Pruning Metric From Scratch for Large Language Models
  16. Should We Really Edit Language Models? On the Evaluation of Edited Language Models