I am Heming Xia, a Ph.D. student at The Hong Kong Polytechnic University, supervised by Prof. Wenjie Li. I obtained my master degree from the MOE Key Laboratory of Computational Linguistics, Peking University, advised by Prof. Zhifang Sui. Before that, I received my bachelor degree from the School of Physics, Peking University in 2020. I have also spent time at NLC Group @ Microsoft Research Asia as a Research Intern, where I was fortunate to work with Dr. Tao Ge. Please check my CV for further information.
Research
I am broadly interested in natural language processing and machine learning. My current research focuses on 1) efficient and effective NLP 2) tool learning, and 3) cross vision and language understanding.
News
[2024.01] 🔥Released Spec-Bench: a comprehensive benchmark for Speculative Decoding, check it out!
[2024.01] Released our new survey 📖 on Speculative Decoding.
[2024.01] Started my Ph.D. study at the Natural Language Processing Group @PolyU, The Hong Kong Polytechnic University, supervised by Prof. Wenjie Li.
[2023.10] Got three papers accepted by EMNLP 2023.
[2023.5] Got one short paper accepted by ACL 2023.
[2022.5] Got one paper accepted by ACL 2022.
[2021.10] Started my research internship at NLC Group @ Microsoft Research Asia, advised by Dr. Tao Ge.
[2020.9] Started my Master study at the MOE Key Laboratory of Computational Linguistics, Peking University, advised by Prof. Zhifang Sui.
Publications
Most recent publications on Google Scholar.
* indicates equal contribution
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, Zhifang Sui
Arxiv 2024. [link] [code]
ImageNetVC: Zero- and Few-Shot Visual Commonsense Evaluation on 1000 ImageNet Categories
Heming Xia*, Qingxiu Dong*, Lei Li, Jingjing Xu, Tianyu Liu, Ziwei Qin, Zhifang Sui
Findings of EMNLP 2023. [link] [code]
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
Findings of EMNLP 2023. [link]
Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation
Heming Xia*, Tao Ge*, Peiyi Wang, Si-Qing Chen, Furu wei, and Zhifang Sui
Findings of EMNLP 2023. [link] [code]
Enhancing Continual Relation Extraction via Classifier Decomposition
Heming Xia, Peiyi Wang, Tianyu Liu, Binghuai Lin, Yunbo Cao, and Zhifang Sui
Findings of ACL 2023. [link] [code]
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
ACL 2022. [link] [code]
Improved deep learning techniques in gravitational-wave data analysis
Heming Xia, Lijing Shao, Junjie Zhao and Zhoujian Cao
Phys. Rev. D 103 2021. [link] [code]
Service
Reviewer: NeurIPS 2022, AACL 2022, AACL 2023, ARR (Feb, Apr-2024)
Awards
Model Student of Social Work, Peking University (2022)
Merit Student, Peking University (2021)
Scholarship of National Astronomical Observatory, Chinese Academy of Sciences (2019)
Outstanding Volunteer Award of Volunteer and Cultural Program in Thailand, The Green Lion (2017)
Merit Student, Henan Province, China (2016)