Yiwen Guo - Homepage

Short Biography

Yiwen Guo is an independent research scientist. He used to work at ByteDance AI Lab and Intel Labs. He receieved his PhD degree from the Department of Electronic Engineering, Tsinghua University in 2016, and the Bachelor's degree from Wuhan University. He was a visiting scholar at the Department of Statistics, University College London (UCL).

Research Interests

His current research interests center on machine learning, computer vision, natural language processing, and cybersecurity. In particular, he has years of experience in studying trustworthy AI, code intelligence, vision-language models, and DNN compression. He is always open for research collaborations and discussions. Contact him if you are interested in the internship or full-time research and engineering positions.

Conference Publications

The Program Testing Ability of Large Language Models for Code
Weimin Xiong, Yiwen Guo^‡, Hao Chen
To appear in EMNLP (industry track), 2024
Code Representation Pre-training with Complements from Program Executions
Jiabo Huang, Jianyu Zhao, Yuyang Rong, Yiwen Guo^‡, Yifeng He, Hao Chen
To appear in EMNLP (industry track), 2024
Unveiling and Consulting Core Experts in Retrieval-Augmented MoE-based LLMs
Xin Zhou^*, Ping Nie^*, Yiwen Guo^‡, Haojie Wei, Zhanqiu Zhang, Pasquale Minervini, Ruotian Ma, Tao Gui^‡, Qi Zhang^‡, Xuanjing Huang
To appear in EMNLP, 2024
Improved Generation of Adversarial Examples Against Safety-aligned LLMs
Qizhang Li, Yiwen Guo^‡, Wangmeng Zuo, and Hao Chen
To appear in NeurIPS, 2024 [Paper] [Code]
UniTSyn: A Large-Scale Dataset Capable of Enhancing the Prowess of Large Language Models for Program Testing
Yifeng He, Jiabo Huang, Yuyang Rong, Yiwen Guo^‡, Ethan Wang, and Hao Chen
In ISSTA, 2024 [Paper] [Code]
Learned ISTA with Error-based Thresholding for Adaptive Sparse Coding
Ziang Li, Kailun Wu, Yiwen Guo^‡, and Changshui Zhang^‡
In ICASSP, 2024 [Paper] [Code]
Intrusion Detection at Scale with the Assistance of a Command-line Language Model
Jiongliang Lin, Yiwen Guo^‡, and Hao Chen
In DSN (industry track), 2024 [Paper]
Black-Box Tuning of Vision-Language Models with Effective Gradient Approximation
Zixian Guo, Yuxiang Wei, Ming Liu, Zhilong Ji, Jinfeng Bai, Yiwen Guo, and Wangmeng Zuo
In EMNLP (findings), 2023 [Paper] [Code]
Adversarial Examples Are Not Real Features
Ang Li, Yifei Wang, Yiwen Guo, and Yisen Wang^‡
In NeurIPS, 2023 [Paper] [Code]
Towards Evaluating Transfer-based Attacks Systematically, Practically, and Fairly
Qizhang Li, Yiwen Guo^‡, Wangmeng Zuo, and Hao Chen
In NeurIPS, 2023 [Paper] [Code]
Improving Adversarial Transferability via Intermediate-level Perturbation Decay
Qizhang Li, Yiwen Guo^‡, Wangmeng Zuo^‡, and Hao Chen
In NeurIPS, 2023 [Paper] [Code]
MHCN: A Hyperbolic Neural Network Model for Multi-view Hierarchical Clustering
Fangfei Lin, Bing Bai^‡, Yiwen Guo^‡, Hao Chen, Yazhou Ren, and Zenglin Xu^‡
In ICCV, 2023 [Paper]
Understanding Programs by Exploiting (Fuzzing) Test Cases
Jianyu Zhao^*, Yuyang Rong^*, Yiwen Guo^‡, Yifeng He, and Hao Chen
In ACL (findings), 2023 [Paper] [Code]
CFA: Class-wise Calibrated Fair Adversarial Training
Zeming Wei, Yifei Wang, Yiwen Guo, and Yisen Wang^‡
In CVPR, 2023 [Paper] [Code]
Texts as Images in Prompt Tuning for Multi-Label Recognition
Zixian Guo, Bowen Dong, Zhilong Ji, Jinfeng Bai, Yiwen Guo, and Wangmeng Zuo
In CVPR, 2023 [Paper] [Code]
Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examples
Qizhang Li, Yiwen Guo^‡, Wangmeng Zuo, and Hao Chen
In ICLR, 2023 [Paper] [Code]
Squeeze Training for Adversarial Robustness
Qizhang Li, Yiwen Guo^‡, Wangmeng Zuo^‡, and Hao Chen
In ICLR, 2023 [Paper] [Code]
When Adversarial Training Meets Vision Transformers: Recipes from Training to Architecture
Yichuan Mo, Dongxian Wu, Yifei Wang, Yiwen Guo, and Yisen Wang^‡
In NeurIPS (spotlight), 2022 [Paper] [Code]
Task-Optimized User Clustering based on Mobile App Usage for Cold-Start Recommendations
Bulou Liu, Bing Bai, Weibang Xie, Yiwen Guo, and Hao Chen
In KDD (ADS track), 2022 [Paper]
Robust and Fully-Dynamic Coreset for Continuous-and-Bounded Learning (With Outliers) Problems
Zixiu Wang, Yiwen Guo, and Hu Ding
In NeurIPS (spotlight), 2021 [Paper]
Protect Privacy of Deep Classification Networks by Exploiting Their Generative Power
Jiyu Chen, Yiwen Guo, Qianjun Zheng, and Hao Chen
In ECML-PKDD (journal track) 2021 [Paper] [Code]
Policy-Driven Attack: Learning to Query for Hard-label Black-box Adversarial Examples
Ziang Yan^*, Yiwen Guo^*, Jian Liang, and Changshui Zhang
In ICLR 2021 [Paper] [Code]
Practical No-box Adversarial Attacks against DNNs
Qizhang Li, Yiwen Guo^‡, and Hao Chen
In NeurIPS 2020 [Paper] [Code]
Backpropagating Linearly Improves Transferability of Adversarial Examples
Yiwen Guo^*, Qizhang Li^*, and Hao Chen
In NeurIPS 2020 [Paper] [Code]
Yet Another Intermediate-Level Attack
Qizhang Li, Yiwen Guo^‡, and Hao Chen
In ECCV 2020 [Paper] [Code]
Metric Learning for Categorical and Ambiguous Features: An Adversarial Approach
Xiaochen Yang, Mingzhi Dong, Yiwen Guo, and Jing-Hao Xue
In ECML-PKDD 2020 [Paper] [Code]
Sparse Coding with Gated Learned ISTA
Kailun Wu^*, Yiwen Guo^*, Ziang Li, and Changshui Zhang
In ICLR (spotlight) 2020 [Paper] [Code]
Subspace Attack: Exploiting Promising Subspaces for Query-Efficient Black-box Attacks
Ziang Yan^*, Yiwen Guo^*, and Changshui Zhang
In NeurIPS 2019 [Paper] [Code]
DATA: Differentiable ArchiTecture Approximation
Jianlong Chang, Xinbang Zhang, Yiwen Guo, Gaofeng Meng, Shiming Xiang, and Chunhong Pan
In NeurIPS 2019 [Paper] [Code]
Sparse DNNs with Improved Adversarial Robustness
Yiwen Guo^*, Chao Zhang^*, Changshui Zhang, and Yurong Chen
In NeurIPS 2018 [Paper]
Deep Defense: Training DNNs with Improved Adversarial Robustness
Ziang Yan^*, Yiwen Guo^*, and Changshui Zhang
In NeurIPS 2018 [Paper] [Code]
Physics Inspired Optimization on Semantic Transfer Features: An Alternative Method for Room Layout Estimation
Hao Zhao, Ming Lu, Anbang Yao, Yiwen Guo, Yurong Chen, and Li Zhang
In CVPR 2017 [Paper] [Project]
Network Sketching: Exploiting Binary Structure in Deep CNNs
Yiwen Guo, Anbang Yao, Hao Zhao, and Yurong Chen
In CVPR 2017 [Paper]
Incremental Network Quantization: Towards Lossless CNNs with Low-precision Weights
Aojun Zhou^*, Anbang Yao^*, Yiwen Guo^*, Lin Xu, and Yurong Chen
In ICLR 2017 [Paper] [Code]
Dynamic Network Surgery for Efficient DNNs
Yiwen Guo, Anbang Yao, and Yurong Chen
In NeurIPS 2016 [Paper] [Code]

Journal Publications

Learning with Noisy Labels Using Collaborative Sample Selection and Contrastive Semi-Supervised Learning
Qing Miao, Xiaohe Wu, Chao Xu^‡, Yanli Ji, Wangmeng Zuo, Yiwen Guo, and Zhaopeng Meng
In Knowledge-Based Systems, 2024 [Paper]
A Theoretical View of Linear Backpropagation and its Convergence
Ziang Li^*, Yiwen Guo^*^‡, Haodi Liu, and Changshui Zhang^‡
In IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024 [Paper] [Code]
Towards Certified Robustness of Distance Metric Learning
Xiaochen Yang^*, Yiwen Guo^*, Mingzhi Dong, and Jing-Hao Xue
In IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2024 [Paper] [Code]
An Intermediate-Level Attack Framework on The Basis of Linear Regression
Yiwen Guo^*, Qizhang Li^*, Wangmeng Zuo, and Hao Chen
In IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022 [Paper] [Code]
Deepfake Forensics via An Adversarial Game
Zhi Wang, Yiwen Guo^‡, and Wangmeng Zuo
In IEEE Transactions on Image Processing (TIP), 2022 [Paper] [Code]
Recent Advances in Large Margin Learning
Yiwen Guo and Changshui Zhang
In IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021 [Paper]
Protect Privacy of Deep Classification Networks by Exploiting Their Generative Power
Jiyu Chen, Yiwen Guo, Qianjun Zheng, and Hao Chen
In Machine Learning, 2021 [Paper] [Code]
Deep Likelihood Network for Image Restoration with Multiple Degradation Levels
Yiwen Guo, Ming Lu, Wangmeng Zuo, Changshui Zhang, and Yurong Chen
In IEEE Transactions on Image Processing (TIP), 2021 [Paper] [Code]
DATA: Differentiable ArchiTecture Approximation with Distribution Guided Sampling
Xinbang Zhang, Jianlong Chang, Yiwen Guo, Gaofeng Meng, Shiming Xiang, Zhouchen Lin, and Chunhong Pan
In IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020 [Paper] [Code]
Pointly-Supervised Scene Parsing with Uncertainty Mixture
Hao Zhao, Ming Lu, Anbang Yao, Yiwen Guo, Yurong Chen, and Li Zhang
In Computer Vision and Image Understanding (CVIU), 2020 [Paper]
On Connections between Regularizations for Improving DNN Robustness
Yiwen Guo^*, Long Chen^*, Yurong Chen, and Changshui Zhang
In IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020 [Paper]
Adjusting The Imbalance Ratio by The Dimensionality of Imbalanced Data
Rui Zhu, Yiwen Guo, and Jing-Hao Xue
In Pattern Recognition Letters, 2020 [Paper]
Adversarial Margin Maximization Networks
Ziang Yan, Yiwen Guo, and Changshui Zhang
In IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2019 [Paper] [Code]
Compressing Deep Neural Networks with Sparse Matrix Factorization
Kailun Wu, Yiwen Guo, and Changshui Zhang
In IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2019 [Paper]
Sufficient Canonical Correlation Analysis
Yiwen Guo, Xiaoqing Ding, Changsong Liu, and Jing-Hao Xue
In IEEE Transactions on Image Processing (TIP), 2016 [Paper]
MiLDA: A Graph Embedding Approach to Multi-view Face Recognition
Yiwen Guo, Xiaoqing Ding, and Jing-Hao Xue
In Neurocomputing, 2015 [Paper]
Fisher's Linear Discriminant Embedded Metric Learning
Yiwen Guo, Xiaoqing Ding, Chi Fang, and Jing-Hao Xue
In Neurocomputing, 2014 [Paper]

Professional Activities

Conference PC member or reviewer: ICML, NeurIPS, CVPR, ICCV, AAAI, IJCAI, etc.
Journal reviewer: Nature Communications, Nature Machine Intelligence, Journal of Selected Topics in Signal Processing, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), IEEE Transactions on Neural Networks and Learning Systems (TNNLS), IEEE Transactions on Image Processing (TIP), etc.