Weixin Liang

60 papers A* 11A 2B 2Journal 42Unranked 3
YearRankTypeTitle / Venue / Authors
2025 A* conf
Adaptive Self-improvement LLM Agentic System for ML Library Development.
ICML
Genghan Zhang, Weixin Liang, Olivia Hsu, Kunle Olukotun
2025 J jnl
Adaptive Self-improvement LLM Agentic System for ML Library Development.
CoRR
Genghan Zhang, Weixin Liang, Olivia Hsu, Kunle Olukotun
2025 J jnl
Closing the Modality Gap for Mixed Modality Search.
CoRR
Binxu Li, Yuhui Zhang, Xiaohan Wang, Weixin Liang, Ludwig Schmidt, Serena Yeung-Levy
2025 J jnl
Computational Approaches to Understanding Large Language Model Impact on Writing and Information Ecosystems.
CoRR
Weixin Liang
2025 J jnl
From Replication to Redesign: Exploring Pairwise Comparisons for LLM-Based Peer Review.
CoRR
Yaohui Zhang, Haijing Zhang, Wenlong Ji, Tianyu Hua, Nick Haber, Hancheng Cao, Weixin Liang
2025 J jnl
Mixture-of-Mamba: Enhancing Multi-Modal State-Space Models with Modality-Aware Sparsity.
CoRR
Weixin Liang, Junhong Shen, Genghan Zhang, Ning Dong, Luke Zettlemoyer, Lili Yu
2025 J jnl
Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models.
Trans. Mach. Learn. Res.
Weixin Liang, Lili Yu, Liang Luo, Srini Iyer, Ning Dong, Chunting Zhou, Gargi Ghosh, Mike Lewis, Wen-tau Yih, Luke Zettlemoyer, Xi Victoria Lin
2025 A conf
Reinforcement Learning-Based Scheduling for Dual-Arm Cluster Tool with Multifunctional Process Modules.
IROS
Lang Jin Liu, Qinghua Zhu, Weixin Liang, Yan Hou
2025 J jnl
ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code.
CoRR
Tianyu Hua, Harper Hua, Violet Xiang, Benjamin Klieger, Sang T. Truong, Weixin Liang, Fan-Yun Sun, Nick Haber
2025 J jnl
The Widespread Adoption of Large Language Model-Assisted Writing Across Society.
CoRR
Weixin Liang, Yaohui Zhang, Mihai Codreanu, Jiayu Wang, Hancheng Cao, James Zou
2025 J jnl
The widespread adoption of large language model-assisted writing across society.
Patterns
Weixin Liang, Yaohui Zhang, Mihai Codreanu, Jiayu Wang, Hancheng Cao, James Zou
2025 J jnl
Weak-for-Strong: Training Weak Meta-Agent to Harness Strong Executors.
CoRR
Fan Nie, Lan Feng, Haotian Ye, Weixin Liang, Pan Lu, Huaxiu Yao, Alexandre Alahi, James Zou
2024 B conf
A Deep Reinforcement Learning Approach to Optimize Closing Down a Single-Arm Cluster Tool.
SMC
Weixin Liang, Qinghua Zhu, Zongru Li, Jiantie Zhou, Yan Hou
2024 J jnl
LMFusion: Adapting Pretrained Language Models for Multimodal Generation.
CoRR
Weijia Shi, Xiaochuang Han, Chunting Zhou, Weixin Liang, Xi Victoria Lin, Luke Zettlemoyer, Lili Yu
2024 J jnl
Mapping the Increasing Use of LLMs in Scientific Papers.
CoRR
Weixin Liang, Yaohui Zhang, Zhengxuan Wu, Haley Lepp, Wenlong Ji, Xuandong Zhao, Hancheng Cao, Sheng Liu, Siyu He, Zhi Huang, Diyi Yang, Christopher Potts, Christopher D. Manning, James Y. Zou
2024 J jnl
Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models.
CoRR
Weixin Liang, Lili Yu, Liang Luo, Srinivasan Iyer, Ning Dong, Chunting Zhou, Gargi Ghosh, Mike Lewis, Wen-tau Yih, Luke Zettlemoyer, Xi Victoria Lin
2024 A* conf
Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews.
ICML
Weixin Liang, Zachary Izzo, Yaohui Zhang, Haley Lepp, Hancheng Cao, Xuandong Zhao, Lingjiao Chen, Haotian Ye, Sheng Liu, Zhi Huang, Daniel A. McFarland, James Y. Zou
2024 J jnl
Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews.
CoRR
Weixin Liang, Zachary Izzo, Yaohui Zhang, Haley Lepp, Hancheng Cao, Xuandong Zhao, Lingjiao Chen, Haotian Ye, Sheng Liu, Zhi Huang, Daniel A. McFarland, James Y. Zou
2024 J jnl
Navigating Dataset Documentations in AI: A Large-Scale Analysis of Dataset Cards on Hugging Face.
CoRR
Xinyu Yang, Weixin Liang, James Zou
2024 A* conf
Navigating Dataset Documentations in AI: A Large-Scale Analysis of Dataset Cards on HuggingFace.
ICLR
Xinyu Yang, Weixin Liang, James Zou
2024 J jnl
Systematic analysis of 32,111 AI model cards characterizes documentation practice in AI.
Nat. Mac. Intell.
Weixin Liang, Nazneen Rajani, Xinyu Yang, Ezinwanne Ozoani, Eric Wu, Yiqun Chen, Daniel Scott Smith, James Zou
2024 J jnl
What's documented in AI? Systematic Analysis of 32K AI Model Cards.
CoRR
Weixin Liang, Nazneen Rajani, Xinyu Yang, Ezinwanne Ozoani, Eric Wu, Yiqun Chen, Daniel Scott Smith, James Zou
2023 A* conf
Accuracy on the Curve: On the Nonlinear Correlation of ML Performance Between Data Subpopulations.
ICML
Weixin Liang, Yining Mao, Yongchan Kwon, Xinyu Yang, James Zou
2023 J jnl
Accuracy on the Curve: On the Nonlinear Correlation of ML Performance Between Data Subpopulations.
CoRR
Weixin Liang, Yining Mao, Yongchan Kwon, Xinyu Yang, James Zou
2023 J jnl
Can large language models provide useful feedback on research papers? A large-scale empirical analysis.
CoRR
Weixin Liang, Yuhui Zhang, Hancheng Cao, Binglu Wang, Daisy Ding, Xinyu Yang, Kailas Vodrahalli, Siyu He, Daniel Scott Smith, Yian Yin, Daniel A. McFarland, James Zou
2023 J jnl
GPT detectors are biased against non-native English writers.
CoRR
Weixin Liang, Mert Yüksekgönül, Yining Mao, Eric Wu, James Zou
2023 J jnl
GPT detectors are biased against non-native English writers.
Patterns
Weixin Liang, Mert Yüksekgönül, Yining Mao, Eric Wu, James Zou
2023 A* conf
OpenDataVal: a Unified Benchmark for Data Valuation.
NeurIPS
Kevin Fu Jiang, Weixin Liang, James Y. Zou, Yongchan Kwon
2023 J jnl
OpenDataVal: a Unified Benchmark for Data Valuation.
CoRR
Kevin Fu Jiang, Weixin Liang, James Zou, Yongchan Kwon
2022 J jnl
Advances, challenges and opportunities in creating data for trustworthy AI.
Nat. Mach. Intell.
Weixin Liang, Girmaw Abebe Tadesse, Daniel E. Ho, Li Fei-Fei, Matei Zaharia, Ce Zhang, James Zou
2022 J jnl
Author Correction: Advances, challenges and opportunities in creating data for trustworthy AI.
Nat. Mac. Intell.
Weixin Liang, Girmaw Abebe Tadesse, Daniel E. Ho, Li Fei-Fei, Matei Zaharia, Ce Zhang, James Zou
2022 J jnl
Data Budgeting for Machine Learning.
CoRR
Xinyi Zhao, Weixin Liang, James Zou
2022 J jnl
Disparities in Dermatology AI Performance on a Diverse, Curated Clinical Image Set.
CoRR
Roxana Daneshjou, Kailas Vodrahalli, Roberto A. Novoa, Melissa Jenkins, Weixin Liang, Veronica Rotemberg, Justin Ko, Susan M. Swetter, Elizabeth E. Bailey, Olivier Gevaert, Pritam Mukherjee, Michelle Phung, Kiana Yekrang, Bradley Fong, Rachna Sahasrabudhe, Johan A. C. Allerup, Utako Okata-Karigane, James Zou, Albert Chiou
2022 J jnl
GSCLIP : A Framework for Explaining Distribution Shifts in Natural Language.
CoRR
Zhiying Zhu, Weixin Liang, James Zou
2022 A* conf
Improving Out-of-Distribution Robustness via Selective Augmentation.
ICML
Huaxiu Yao, Yu Wang, Sai Li, Linjun Zhang, Weixin Liang, James Zou, Chelsea Finn
2022 J jnl
Improving Out-of-Distribution Robustness via Selective Augmentation.
CoRR
Huaxiu Yao, Yu Wang, Sai Li, Linjun Zhang, Weixin Liang, James Zou, Chelsea Finn
2022 A* conf
MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts and Training Conflicts.
ICLR
Weixin Liang, James Zou
2022 J jnl
MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts and Training Conflicts.
CoRR
Weixin Liang, James Zou
2022 A* conf
Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning.
NeurIPS
Weixin Liang, Yuhui Zhang, Yongchan Kwon, Serena Yeung, James Y. Zou
2022 J jnl
Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning.
CoRR
Weixin Liang, Yuhui Zhang, Yongchan Kwon, Serena Yeung, James Zou
2022 J jnl
SEAL : Interactive Tool for Systematic Error Analysis and Labeling.
CoRR
Nazneen Rajani, Weixin Liang, Lingjiao Chen, Meg Mitchell, James Zou
2022 — conf
SEAL: Interactive Tool for Systematic Error Analysis and Labeling.
EMNLP (Demos)
Nazneen Rajani, Weixin Liang, Lingjiao Chen, Margaret Mitchell, James Zou
2022 J jnl
Systematic analysis of 50 years of Stanford University technology transfer and commercialization.
Patterns
Weixin Liang, Scott Elrod, Daniel A. McFarland, James Zou
2021 J jnl
Disparities in Dermatology AI: Assessments Using Diverse Clinical Images.
CoRR
Roxana Daneshjou, Kailas Vodrahalli, Weixin Liang, Roberto A. Novoa, Melissa Jenkins, Veronica Rotemberg, Justin Ko, Susan M. Swetter, Elizabeth E. Bailey, Olivier Gevaert, Pritam Mukherjee, Michelle Phung, Kiana Yekrang, Bradley Fong, Rachna Sahasrabudhe, James Zou, Albert Chiou
2021 J jnl
GraghVQA: Language-Guided Graph Neural Networks for Graph-based Visual Question Answering.
CoRR
Weixin Liang, Yanhao Jiang, Zixuan Liu
2021 — conf
HERALD: An Annotation Efficient Method to Detect User Disengagement in Social Conversations.
ACL/IJCNLP (1)
Weixin Liang, Kaihui Liang, Zhou Yu
2021 J jnl
HERALD: An Annotation Efficient Method to Detect User Disengagement in Social Conversations.
CoRR
Weixin Liang, Kaihui Liang, Zhou Yu
2021 B conf
Neural Group Testing to Accelerate Deep Learning.
ISIT
Weixin Liang, James Zou
2020 — conf
ALICE: Active Learning with Contrastive Natural Language Explanations.
EMNLP (1)
Weixin Liang, James Zou, Zhou Yu
2020 J jnl
ALICE: Active Learning with Contrastive Natural Language Explanations.
CoRR
Weixin Liang, James Zou, Zhou Yu
2020 A* conf
Beyond User Self-Reported Likert Scale Ratings: A Comparison Model for Automatic Dialog Evaluation.
ACL
Weixin Liang, James Zou, Zhou Yu
2020 J jnl
Beyond User Self-Reported Likert Scale Ratings: A Comparison Model for Automatic Dialog Evaluation.
CoRR
Weixin Liang, James Zou, Zhou Yu
2020 J jnl
DAWSON: A Domain Adaptive Few Shot Generation Framework.
CoRR
Weixin Liang, Zixuan Liu, Can Liu
2020 J jnl
LRTA: A Transparent Neural-Symbolic Reasoning Framework with Modular Supervision for Visual Question Answering.
CoRR
Weixin Liang, Feiyang Niu, Aishwarya N. Reganti, Govind Thattai, Gökhan Tür
2020 A* conf
MOSS: End-to-End Dialog System Framework with Modular Supervision.
AAAI
Weixin Liang, Youzhi Tian, Chengcai Chen, Zhou Yu
2020 J jnl
Neural Group Testing to Accelerate Deep Learning.
CoRR
Weixin Liang, James Zou
2019 J jnl
CU-Net: Component Unmixing Network for Textile Fiber Identification.
Int. J. Comput. Vis.
Zunlei Feng, Weixin Liang, Daocheng Tao, Li Sun, Anxiang Zeng, Mingli Song
2019 A* conf
DeepStore: In-Storage Acceleration for Intelligent Queries.
MICRO
Vikram Sharma Mailthody, Zaid Qureshi, Weixin Liang, Ziyan Feng, Simon Garcia De Gonzalo, Youjie Li, Hubertus Franke, Jinjun Xiong, Jian Huang, Wen-Mei Hwu
2019 J jnl
MOSS: End-to-End Dialog System Framework with Modular Supervision.
CoRR
Weixin Liang, Youzhi Tian, Chengcai Chen, Zhou Yu
2018 A conf
MemCloak: Practical Access Obfuscation for Untrusted Memory.
ACSAC
Weixin Liang, Kai Bu, Ke Li, Jinhong Li, Arya Tavakoli