publications

* denotes equal contribution. see also my Google Scholar profile.

2026

  1. EMNLP
    Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets
    Duc Duong*, Hoang Anh Duy Le*, Jianwen Xie, Anshumali Shrivastava, and Zhaozhuo Xu
    In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2026
  2. ICML
    Scout Before You Attend: Sketch-and-Walk Sparse Attention for Efficient LLM Inference
    Hoang Anh Duy Le, Sahil Joshi, Zeyu Yang, Zhaozhuo Xu, and Anshumali Shrivastava
    In Proceedings of the 43rd International Conference on Machine Learning (ICML), 2026
  3. ICML
    FAFO: Lossy KV Cache Compression for Lossless Inference Acceleration via Draftless Fumble Decoding
    Hoang Anh Duy Le*, Shaochen Zhong*, Yifan Lu, Yingtong Dou, Jiayi Yuan, Yu-Neng Chuang, Xiran Fan, Guanchu Wang, Yuzhong Chen, and Xia Hu
    In Proceedings of the 43rd International Conference on Machine Learning (ICML), 2026
  4. ACL
    AutoL2S: Auto Long-Short Reasoning for Efficient Large Language Models
    Feng Luo, Yu-Neng Chuang, Guanchun Wang, Hoang Anh Duy Le, Shaochen Zhong, Hongyi Liu, Jiayi Yuan, Yang Sui, Vladimir Braverman, Vipin Chaudhary, and Xia Hu
    In Findings of the Association for Computational Linguistics: ACL 2026, 2026
  5. arXiv
    When Implausible Tokens Get Reinforced: Tail-Aware Credit Calibration for LLM Reinforcement Learning
    Xiuyi Lou, Zicheng Xu, Yu-Neng Chuang, Hoang Anh Duy Le, Zhaozhuo Xu, Guanchun Wang, and Vladimir Braverman
    arXiv preprint arXiv:2607.07976, 2026
  6. arXiv
    Learning at the Right Pace: Adaptive Data Scheduling Improves LLM Reinforcement Learning
    Zicheng Xu, Ruixuan Zhang, Yu-Neng Chuang, Xiuyi Lou, Hoang Anh Duy Le, Oren Gal, Alexander S. Szalay, Zhaozhuo Xu, Guanchun Wang, and Vladimir Braverman
    arXiv preprint arXiv:2606.22305, 2026
  7. arXiv
    SOCKET: SOft Collision Kernel EsTimator for Sparse Attention
    Sahil Joshi, Agniva Chowdhury, Wyatt Bellinger, Amar Kanakamedala, Ekam Singh, Hoang Anh Duy Le, Aditya Desai, and Anshumali Shrivastava
    arXiv preprint arXiv:2602.06283, 2026
  8. TMLR
    The LLM Data Auditor: A Metric-Oriented Survey on Quality and Trustworthiness in Evaluating Synthetic Data
    Kaituo Zhang, Mingzhi Hu, Hoang Anh Duy Le, Fariha Kabir Torsha, Zhimeng Jiang, Minh Khai Bui, Chia-Yuan Chang, Yu-Neng Chuang, Zhen Xiong, Ying Lin, Guanchun Wang, and Na Zou
    Transactions on Machine Learning Research (TMLR), 2026
  9. Preprint
    Sweeping Promptable Spoofs under the DirtyRAG: A Practical, Query-Blind RAG Attack Done Right
    Shaochen Zhong, Jiamu Zhang, Hoang Anh Duy Le, Wenya Xie, Yifan Lu, Xintong Sun, Mohsen Hariri, Hongyi Liu, Guanchun Wang, Zhaozhuo Xu, and others
    Preprint, 2026

2025

  1. EMNLP
    Word Salad Chopper: Reasoning Models Waste A Ton Of Decoding Budget On Useless Repetitions, Self-Knowingly
    Wenya Xie, Shaochen Zhong, Hoang Anh Duy Le, Zhaozhuo Xu, Jianwen Xie, and Zirui Liu
    In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025
    DOI
  2. ACL
    ReasonerRank: Redefining Language Model Evaluation with Ground-Truth-Free Ranking Frameworks
    Jiamu Zhang, Jiayi Yuan, Andrew Wen, Hoang Anh Duy Le, Yu-Neng Chuang, Soo-Hyun Choi, Rui Chen, and Xia Hu
    In Findings of the Association for Computational Linguistics: ACL 2025, 2025
    DOI
  3. Preprint
    Graph Transformers Get the GIST: Graph Invariant Structural Trait for Refined Graph Encoding
    Hoang Anh Duy Le, Shaochen Zhong, Jerry Xiao, Jiamu Zhang, Yu-Neng Chuang, Li Li, Rui Chen, Shuai Xu, Zirui Liu, Kaixiong Zhou, and others
    Preprint, 2025

2024

  1. EMNLP
    KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches
    Jiayi Yuan, Hongyi Liu, Shaochen Zhong, Yu-Neng Chuang, Songchen Li, Guanchu Wang, Hoang Anh Duy Le, Hongye Jin, Vipin Chaudhary, Zhaozhuo Xu, Zirui Liu, and Xia Hu
    In Findings of the Association for Computational Linguistics: EMNLP 2024, 2024
  2. ICML
    Knowledge Graphs Can be Learned with Just Intersection Features
    Hoang Anh Duy Le, Shaochen Zhong, Zirui Liu, Shuai Xu, Vipin Chaudhary, Kaixiong Zhou, and Zhaozhuo Xu
    In Proceedings of the 41st International Conference on Machine Learning (ICML), 2024
  3. ICML
    GNNs Also Deserve Editing, and They Need It More Than Once
    Shaochen Zhong*, Hoang Anh Duy Le*, Zirui Liu, Zhimeng Jiang, Andrew Ye, Jiamu Zhang, Jiayi Yuan, Kaixiong Zhou, Zhaozhuo Xu, Jing Ma, Shuai Xu, Vipin Chaudhary, and Xia Hu
    In Proceedings of the 41st International Conference on Machine Learning (ICML), 2024
  4. ICDE
    GraphLingo: Domain Knowledge Exploration by Synchronizing Knowledge Graphs and Large Language Models
    Hoang Anh Duy Le, Kris Zhao, Mengying Wang, and Yinghui Wu
    In 2024 IEEE 40th International Conference on Data Engineering (ICDE), 2024
    DOI