Quanshi Zhang

Challenging the Explanation Based on Preceding Tokens: Discovering Transferable Non-Literal Biasing ACL 2026 Towards Attributions of Input Variables in a Coalition ICML 2025 Monitoring Primitive Interactions During the Training of DNNs AAAI 2025 Layerwise Change of Knowledge in Neural Networks ICML 2024 Defining and extracting generalizable interaction primitives from DNNs ICLR 2024 Where We Have Arrived in Proving the Emergence of Sparse Interaction Primitives in DNNs ICLR 2024 Clarifying the Behavior and the Difficulty of Adversarial Training AAAI 2024 Explaining Generalization Power of a DNN Using Interactive Concepts AAAI 2024 Batch Normalization Is Blind to the First and Second Derivatives of the Loss AAAI 2024 Identifying Semantic Induction Heads to Understand In-Context Learning ACL 2024 Towards the Dynamics of a DNN Learning Symbolic Interactions NIPS 2024 Defects of Convolutional Decoder Networks in Frequency Representation ICML 2023 Does a Neural Network Really Encode Symbolic Concepts? ICML 2023 HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagation ICML 2023 Towards the Difficulty for a Deep Neural Network to Learn Concepts of Different Complexities NIPS 2023 Defining and Quantifying the Emergence of Sparse Concepts in DNNs CVPR 2023 Can We Faithfully Represent Absence States to Compute Shapley Values on a DNN? ICLR 2023 Bayesian Neural Networks Avoid Encoding Complex and Perturbation-Sensitive Concepts ICML 2023 Towards Theoretical Analysis of Transformation Complexity of ReLU DNNs ICML 2022 Quantification and Analysis of Layer-wise and Pixel-wise Information Discarding ICML 2022 DISCOVERING AND EXPLAINING THE REPRESENTATION BOTTLENECK OF DNNS ICLR 2022 Interpretable Generative Adversarial Networks AAAI 2022 Exploring Image Regions Not Well Encoded by an INN AISTATS 2022 RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL EMNLP 2022 Building Interpretable Interaction Trees for Deep NLP Models AAAI 2021 Visualizing the Emergence of Intermediate Visual Patterns in DNNs NIPS 2021 Interpreting Representation Quality of DNNs for 3D Point Cloud Processing NIPS 2021 Interpreting Multivariate Shapley Interactions in DNNs AAAI 2021 Towards a Unified Game-Theoretic View of Adversarial Perturbations and Robustness NIPS 2021 Verifiability and Predictability: Interpreting Utilities of Network Architectures for Point Cloud Processing CVPR 2021 Interpreting Attributions and Interactions of Adversarial Attacks ICCV 2021 Interpreting and Boosting Dropout from a Game-Theoretic View ICLR 2021 A Unified Approach to Interpreting and Boosting Adversarial Transferability ICLR 2021 Interpreting and Disentangling Feature Components of Various Complexity from DNNs ICML 2021 Interpretable Compositional Convolutional Neural Networks IJCAI 2021 Explaining Knowledge Distillation by Quantifying the Knowledge CVPR 2020 3D-Rotation-Equivariant Quaternion Neural Networks ECCV 2020 Interpretable Complex-Valued Neural Networks for Privacy Protection ICLR 2020 Knowledge Consistency between Neural Networks and Beyond ICLR 2020 Interpreting CNNs via Decision Trees CVPR 2019 Towards a Deep and Unified Understanding of Deep Neural Models in NLP ICML 2019 Explaining Neural Networks Semantically and Quantitatively ICCV 2019 Interpretable Convolutional Neural Networks CVPR 2018 Mining Object Parts From CNNs via Active Question-Answering CVPR 2017 Mining And-Or Graphs for Graph Matching and Object Discovery ICCV 2015 Attributed Graph Mining and Matching: An Attempt to Define and Extract Soft Attributed Patterns CVPR 2014 When 3D Reconstruction Meets Ubiquitous RGB-D Images CVPR 2014 Category Modeling from Just a Single Labeling: Use Depth Information to Guide the Learning of 2D Models CVPR 2013 Learning Graph Matching: Oriented to Category Modeling from Cluttered Scenes ICCV 2013