Publications

(*) Equal Contribution. (†) Corresponding Author.

2025

  1. ArXiv
    hauntattack.png
    HauntAttack: When Attack Follows Reasoning as a Shadow
    Jingyuan Ma*, Rui Li*, Zheng Li, Junfeng Liu, Heming Xia, Lei Sha, and Zhifang Sui
    In ArXiv, 2025
    arXiv
  2. ArXiv
    llmreval.png
    LLM-REVal: Can We Trust LLM Reviewers Yet?
    Rui Li, Jia-Chen Gu, Po-Nien Kung, Heming Xia, Junfeng liu, Xiangwen Kong, Zhifang Sui, and Nanyun Peng
    In ArXiv, 2025
    arXiv Code Website
  3. ArXiv
    advprompt.png
    Merlin’s Whisper: Enabling Efficient Reasoning in LLMs via Black-box Adversarial Prompting
    Heming Xia, Cunxiao Du†, Rui Li, Chak Tou Leong, Yongqi Li†, and Wenjie Li
    In ArXiv, 2025
    arXiv Code
  4. ArXiv
    latentcot.jpg
    Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning
    Xinghao Chen*, Anhao Zhao*, Heming Xia, Xuan Lu, Hanlin Wang, Yanjun Chen, Wei Zhang, Jian Wang†, Wenjie Li, and Xiaoyu Shen†
    In ArXiv, 2025
    arXiv Paper List
  5. ArXiv
    knnssd.jpg
    KNN-SSD: Enabling Dynamic Self-Speculative Decoding via Nearest Neighbor Layer Set Optimization
    Mingbo Song, Heming Xia, Jun Zhang, Chak Tou Leong, Qiancheng Xu, Wenjie Li, and Sujian Li
    In ArXiv, 2025
    arXiv
  6. ArXiv
    oracle.jpg
    From Query to Logic: Ontology-Driven Multi-Hop Reasoning in LLMs
    Haonan Bian, Yutao Qi†, Rui Yang, Yuanxi Che, Jiaqian Wang, Heming Xia, and Ranran Zhen
    In ArXiv, 2025
    arXiv
  7. EMNLP
    tokenskip.jpg
    TokenSkip: Controllable Chain-of-Thought Compression in LLMs
    Heming Xia, Chak Tou Leong, Wenjie Wang, Yongqi Li†, and Wenjie Li
    In EMNLP, 2025
    HTML Code
  8. EMNLP
    specvlm.jpg
    SpecVLM: Enhancing Speculative Decoding of Video LLMs via Verifier-Guided Token Pruning
    Yicheng Ji*, Jun Zhang*, Heming Xia, Jinpeng Chen, Lidan Shou, Gang Chen, and Huan Li†
    In EMNLP, 2025
    HTML
  9. EMNLP
    stripcipher.jpg
    Beyond Single Frames: Can LMMs Comprehend Temporal and Contextual Narratives in Image Sequences?
    Xiaochen Wang*, Heming Xia*, Jialin Song, Longyu Guan, Yixin Yang, Qingxiu Dong, Weiyao Luo, Yifan Pu, Yiru Wang, Xiangdi Meng, Wenjie Li, and Zhifang Sui†
    In Findings of EMNLP, 2025
    HTML
  10. ACL
    cue.jpg
    Towards Harmonized Uncertainty Estimation for Large Language Models
    Rui Li, Jing Long, Muge Qi, Heming Xia, Lei Sha, Peiyi Wang, and Zhifang Sui†
    In ACL (Oral), 2025
    HTML
  11. ACL
    digitaltwin.jpg
    How Far are LLMs from Being Our Digital Twins? A Benchmark for Persona-Based Behavior Chain Simulation
    Rui Li, Heming Xia, Xinfeng Yuan, Qingxiu Dong, Lei Sha, Wenjie Li, and Zhifang Sui†
    In Findings of ACL, 2025
    HTML Code
  12. ACL
    petoolllm.jpg
    PEToolLLM: Towards Personalized Tool Learning in Large Language Models
    Qiancheng Xu, Yongqi Li†, Heming Xia, Fan Liu, Min Yang, and Wenjie Li
    In Findings of ACL, 2025
    HTML Code
  13. Tutorial
    tutorial.jpg
    Speculative Decoding for Efficient LLM Inference
    Heming Xia, Yongqi Li, Cunxiao Du, Qian Liu, and Wenjie Li
    In COLING, 2025
    Video Slides Website
  14. ICLR
    swift.jpg
    SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration
    Heming Xia, Yongqi Li†, Jun Zhang, Cunxiao Du, and Wenjie Li
    In ICLR, 2025
    HTML Code

2024

  1. EMNLP
    appbench.jpg
    AppBench: Planning of Multiple APIs from Various APPs for Complex User Instruction
    Hongru Wang*, Rui Wang*, Boyang Xue, Heming Xia, Jingtao Cao, Zeming Liu, Jeff Z. Pan†, and Kam-Fai Wong†
    In EMNLP, 2024
    HTML Code
  2. EMNLP
    icl.jpg
    A Survey on In-context Learning
    Qingxiu Dong, Lei Li, Damai Dai, Ce Zheng, Jingyuan Ma, Rui Li, Heming Xia, Jingjing Xu, Zhiyong Wu, Baobao Chang, Xu Sun, Lei Li, and Zhifang Sui
    In EMNLP, 2024
    HTML Paper List 机器之心
  3. EMNLP
    toolfeedback.jpg
    Enhancing Tool Retrieval with Iterative Feedback from Large Language Models
    Qiancheng Xu, Yongqi Li†, Heming Xia, and Wenjie Li
    In Findings of EMNLP, 2024
    HTML
  4. EMNLP
    sentinel.png
    Taking a Deep Breath: Enhancing Language Modeling of Large Language Models with Sentinel Tokens
    Weiyao Luo, Suncong Zheng, Heming Xia, Weikang Wang, Yan Lei, Tianyu Liu, Shuang Chen, and Zhifang Sui†
    In Findings of EMNLP, 2024
    HTML
  5. ACL
    specsurvey.jpg
    Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding
    Heming Xia, Zhe Yang, Qingxiu Dong, Peiyi Wang, Yongqi Li, Tao Ge, Tianyu Liu, Wenjie Li, and Zhifang Sui
    In Findings of ACL, 2024
    HTML Code Paper List 机器之心
  6. ACL
    semantic.jpg
    Can Large Multimodal Models Uncover Deep Semantics Behind Images?
    Yixin Yang, Zheng Li, Qingxiu Dong, Heming Xia, and Zhifang Sui
    In Findings of ACL, 2024
    HTML Code

2023

  1. EMNLP
    specdec.jpg
    Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation
    Heming Xia*, Tao Ge*†, Peiyi Wang, Si-Qing Chen, Furu Wei, and Zhifang Sui
    In Findings of EMNLP, 2023
    HTML Code
  2. EMNLP
    imagenetvc.jpg
    ImageNetVC: Zero- and Few-Shot Visual Commonsense Evaluation on 1000 ImageNet Categories
    Heming Xia*, Qingxiu Dong*, Lei Li, Jingjing Xu, Tianyu Liu, Ziwei Qin, and Zhifang Sui
    In Findings of EMNLP, 2023
    HTML Code
  3. EMNLP
    bidrop.jpg
    Bi-Drop: Enhancing Fine-tuning Generalization via Synchronous sub-net Estimation and Optimization
    Shoujie Tong*, Heming Xia*, Damai Dai, Runxin Xu, Tianyu Liu, Binghuai Lin, Yunbo Cao, and Zhifang Sui
    In Findings of EMNLP, 2023
    HTML
  4. ACL
    cdec.jpg
    Enhancing Continual Relation Extraction via Classifier Decomposition
    Heming Xia, Peiyi Wang, Tianyu Liu, Binghuai Lin, Yunbo Cao, and Zhifang Sui
    In Findings of ACL, 2023
    HTML Code

2022

  1. ACL
    pmr.jpg
    Premise-based Multimodal Reasoning: Conditional Inference on Joint Textual and Visual Clues
    Qingxiu Dong*, Ziwei Qin*, Heming Xia, Tian Feng, Shoujie Tong, Haoran Meng, Lin Xu, Zhongyu Wei, Weidong Zhan, Baobao Chang, Sujian Li, Tianyu Liu, and Zhifang Sui
    In ACL, 2022
    HTML Code

2021

  1. Phys. Rev. D
    gw.jpg
    Improved deep learning techniques in gravitational-wave data analysis
    Heming Xia, Lijing Shao†, Junjie Zhao, and Zhoujian Cao
    In Phys. Rev. D 103, 2021
    HTML Code