Guanchu (Gary) Wang

Ph.D. Candidate
Department of Computer Science
Rice University
Address: Duncan Hall 3014, 6100 Main St, Houston, TX 77005
Email: Guanchu.Wang@rice.edu
[CV] [Linkedin] [Google Scholar] [DBLP] [ResearchGate] [Paper with code]

left 

Selected Publications and Preprints

Full list [Google Scholar]. * indicates equal contributions

 

Preprint   Assessing and Enhancing Large Language Models in Rare Disease Question-answering

Guanchu Wang*, M.S., Junhao Ran∗, B.Eng., Ruixiang Tang, Ph.D., Chia-Yuan Chang, M.S., Yu-Neng Chuang, M.S., Zirui Liu, Ph.D., Vladimir Braverman, Ph.D., Zhandong Liu, Ph.D., Xia Hu, Ph.D.
[Summary] [Paper] [Code]

 

Preprint   Benchmarking Large Language Models for the Genetic Diagnosis of Rare Mendelian Diseases

Matthew B. Neeley*, B.S., Guantong Qi*, B.S., Guanchu Wang*, M.S., Ruixiang Tang, Ph.D., Dongxue Mao, Ph.D., Chaozhong Liu, Ph.D., Sasidhar Pasupuleti, M.S., Bo Yuan, Ph.D., Fan Xia, Ph.D., Hugo Bellen, D.V.M, Ph.D., Pengfei Liu, Ph.D., Zhandong Liu, Ph.D., Xia Hu, Ph.D.
[Summary] [Paper] [Code]

 

Preprint   Understanding Different Design Choices in Training Large Time Series Models.

Yu-Neng Chuang*, Songchen Li*, Jiayi Yuan*, Guanchu Wang*, Kwei-Herng Lai, Leisheng Yu, Sirui Ding, Chia-Yuan Chang, Qiaoyu Tan, Daochen Zha, Xia Hu
[Summary] [Paper] [Code]

 

Preprint   FaithLM: Towards Faithful Explanations for Large Language Models.

Yu-Neng Chuang, Guanchu Wang, Chia-Yuan Chang, Ruixiang Tang, Shaochen Zhong, Fan Yang, Mengnan Du, Xuanting Cai, and Xia Hu
[Summary] [Paper] [Code]

 

Preprint   LEMO: Learning Shapley Manifold for Faithful Explanation.

Guanchu Wang, Yu-Neng Chuang, Huiyuan Chen, Yuzhong Chen, Zhimeng Jiang, Mangesh Bendre, Mahashweta Das, Zirui Liu, Jiayi Yuan, and Xia Hu
[Summary] [Paper] [Code]

 

EMNLP 2024   Secured Weight Release for Large Language Models via Taylor Expansion.

Guanchu Wang*, Yu-Neng Chuang*, Ruixiang Tang, Shaochen Zhong, Jiayi Yuan, Hongye Jin, Zirui Liu, Vipin Chaudhary, Shuai Xu, James Caverlee, Xia Hu
Empirical Methods in Natural Language Processing, EMNLP 2024.
[Summary] [Paper] [Code]

 

EMNLP 2024 Findings   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, Duy Le, Hongye Jin, Vipin Chaudhary, Zhaozhuo Xu, Zirui Liu, Xia Hu
Empirical Methods in Natural Language Processing, EMNLP 2024.
[Summary] [Paper] [Code]

 

TKDD 2024   Efficient GNN Explanation via Learning Removal-based Attribution.

Yao Rong, Guanchu Wang, Qizhang Feng, Ninghao Liu, Zirui Liu, Enkelejda Kasneci and Xia Hu
Transactions on Knowledge Discovery from Data.
[Summary] [Paper] [Code]

 

ICML 2024   TVE: Learning Meta-attribution for Transferable Vision Explainer.

Guanchu Wang, Yu-Neng Chuang, Fan Yang, Mengnan Du, Chia-Yuan Chang, Shaochen Zhong, Zirui Liu, Zhaozhuo Xu, Kaixiong Zhou, Xuanting Cai, and Xia Hu
International Conference on Machine Learning, ICML 2024.
[Summary] [Paper] [Code]

 

NeurIPS 2023   Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model.

Guanchu Wang*, Zirui Liu*, Shaochen Zhong, Zhaozhuo Xu, Daochen Zha, Ruixiang Tang, Zhimeng Jiang, Kaixiong Zhou, Vipin Chaudhary, Shuai Xu and Xia Hu
Neural Information Processing Systems, NeurIPS 2023.
[Summary] [Paper] [Code]

 

CIKM 2023   DiscoverPath: A Knowledge Refinement and Retrieval System for Interdisciplinarity on Biomedical Research.

Yu-neng Chuang, Guanchu Wang, Chia-Yuan Zhang, Kwei-Herng Lai, Ruixiang Tang, Fan Yang, Alfredo Costilla-Reyes, Kaixiong Zhou, Xiaoqian Jiang and Xia Hu
International Conference on Information and Knowledge Management, CIKM 2023, Demo Track, Best Paper Honorable Mention.
[Summary] [Paper] [Code] [Demo] [FrontEnd]

 

ECML-PKDD 2023   Mitigating Algorithmic Bias with Limited Annotations.

Guanchu Wang, Mengnan Du, Ninghao Liu, Na Zou and Xia Hu
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases
ECML-PKDD 2023
[Summary] [Paper] [Code]

 

ICML 2023   DIVISION: Memory Efficient Training via Dual Activation Precision.

Guanchu Wang, Zirui Liu, Zhimeng Jiang, Ninghao Liu, Na Zou and Xia Hu
International Conference on Machine Learning, ICML 2023.
[Summary] [Paper] [Code]

 

ICLR 2023   CoRTX: Contrastive Learning for Real-time Explanations.

Guanchu Wang*, Yu-Neng Chuang*, Fan Yang, Quan Zhou, Pushkar Tripathi, Xuanting Cai and Xia Hu
(* Equal contribution) International Conference on Learning Representations, ICLR 2023.
[Summary] [Paper] [Code] Applied to Meta Ads Transparency [News]

 

CIKM 2022   BED: A Real-Time Object Detection System for Edge Devices.

Guanchu Wang*, Zaid Pervaiz Bhat∗, Zhimeng Jiang∗, Yi-Wei Chen∗, Daochen Zha∗, Alfredo Costilla Reyes∗, Afshin Niktash, Gorkem Ulkar, Erman Okman, Xuanting Cai, Xia Hu
(* Equal contribution) International Conference on Information and Knowledge Management, Demo Track, Best Paper Award.
[Summary] [Video] [Talk] [Paper] [Slide] [Code]

 

ICML 2022   Accelerating Shapley Explanation via Contributive Cooperator Selection.

Guanchu Wang*, Yu-Neng Chuang*, Mengnan Du, Fan Yang, Quan Zhou, Pushkar Tripathi, Xuanting Cai and Xia Hu
(* Equal contribution) International Conference on Machine Learning, Spotlight of ICML 2022.
[Summary] [Paper] [Code] [Slide] Applied to Meta Ads Transparency [Link]

 

NeurIPS 2021   Fairness via Representation Neutralization.

Mengnan Du, Subhabrata Mukherjee, Guanchu Wang, Ruixiang Tang, Ahmed Hassan Awadallah, and Xia Hu
Neural Information Processing Systems, NeurIPS 2021.
[Summary] [Paper] [Code] [Poster]

 

NeurIPS 2021   Revisiting Time Series Outlier Detection: Definitions and Benchmarks.

Kwei-Herng Lai, Daochen Zha, Junjie Xu, Yue Zhao, Guanchu Wang, and Xia Hu
Neural Information Processing Systems, NeurIPS 2021.
[Summary] [Paper] [Code] [Poster]

 

AAAI 2021   TODS: An Automated Time Series Outlier Detection System.

Kwei-Herng Lai*, Daochen Zha*, Guanchu Wang, Junjie Xu, Yue Zhao, Devesh Kumar, Yile Chen, Purav Zumkhawaka, Minyang Wan, Diego Martinez, and Xia Hu
AAAI Conference on Artificial Intelligence, AAAI 2021, Demo Track.
[Summary] [Video][Paper] [Code]

 

IJCAI 2020   Independent Skill Transfer for Deep Reinforcement Learning.

Qiangxing Tian, Guanchu Wang, Jinxin Liu, and Donglin Wang
International Joint Conference on Artificial Intelligence, IJCAI 2020 (Accepted rate 12.6%).
[Summary] [Paper] [Code] [Poster]

 

JOCN 2023   Graph-based Conflict-free MAC Protocol and Conflict Analysis for Two-layer Ultraviolet Communication Network.

Yuchen Pan, Guanchu Wang, Yubo Zhang, Jingyin Tang, Chen Gong, and Zhengyuan Xu
IEEE Journal of Optical Communications and Networking, JOCN 2023.
[Summary] [Paper] [Code] [Poster]

 

PJ 2019   Multi-layer Superimposed Transmission for Optical Wireless Scattering Communication.

Guanchu Wang, Chen Gong, Zhimeng Jiang, and Zhengyuan Xu
IEEE Photonics Journal, PJ 2019.
[Summary] [Paper] [Code] [Abstract]

 

TCOM 2018   Signal Characterization for Multiple Access Non-line of Sight Scattering Communication.

Guanchu Wang, Chen Gong, and Zhengyuan Xu
IEEE Transaction on Communication, TCOM 2018.
[Summary] [Paper] [Code] [Abstract]

 

PJ 2018   A 1Mbps Real-time NLOS UV Scattering Communication System with Receiver Diversity over 1km.

Guanchu Wang, Kun Wang, Chen Gong, Difan Zou, Zhimeng Jiang, and Zhengyuan Xu
IEEE Photonics Journal, PJ 2018.
[Summary] [Paper] [Code] [Abstract]

 

Globecom 2017   Signal detection and achievable rates for multiple access optical wireless scattering communication.

Guanchu Wang, Chen Gong, Zhengyuan Xu
IEEE Global Communication Conference, Globecom 2017.
[Summary] [Paper] [Code] [Poster]