Yisen Wang

Monet: Reasoning in Latent Visual Space Beyond Image and Language CVPR 2026 An Augmentation-Aware Theory for Self-Supervised Contrastive Learning ICML 2025 An Augmentation Overlap Theory of Contrastive Learning JMLR 2025 Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness ICLR 2025 Can In-context Learning Really Generalize to Out-of-distribution Tasks? ICLR 2025 Identifying and Understanding Cross-Class Features in Adversarial Training ICML 2025 Incorporating Arbitrary Matrix Group Equivariance into KANs ICML 2025 Leveraging Flatness to Improve Information-Theoretic Generalization Bounds for SGD ICLR 2025 Long-Short Alignment for Effective Long-Context Modeling in LLMs ICML 2025 Projection Head is Secretly an Information Bottleneck ICLR 2025 Rethinking Invariance in In-context Learning ICLR 2025 SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation ICLR 2025 TC-MoE: Augmenting Mixture of Experts with Ternary Expert Choice ICLR 2025 What is Wrong with Perplexity for Long-context Language Modeling? ICLR 2025 A Canonicalization Perspective on Invariant and Equivariant Learning NeurIPS 2024 A Theoretical Understanding of Self-Correction through In-context Alignment NeurIPS 2024 Dissecting the Failure of Invariant Learning on Graphs NeurIPS 2024 Do Generated Data Always Help Contrastive Learning? ICLR 2024 Fight Back Against Jailbreaking via Prompt Adversarial Tuning NeurIPS 2024 Graph Neural Networks (with Proper Weights) Can Escape Oversmoothing ACML 2024 Look Ahead or Look Around? A Theoretical Comparison Between Autoregressive and Masked Pretraining ICML 2024 Non-negative Contrastive Learning ICLR 2024 On the Role of Discrete Tokenization in Visual Representation Learning ICLR 2024 PID: Prompt-Independent Data Protection Against Latent Diffusion Models ICML 2024 TERD: A Unified Framework for Safeguarding Diffusion Models Against Backdoors ICML 2024 Understanding the Role of Equivariance in Self-supervised Learning NeurIPS 2024 Adversarial Examples Are Not Real Features NeurIPS 2023 A Message Passing Perspective on Learning Dynamics of Contrastive Learning ICLR 2023 Architecture Matters: Uncovering Implicit Mechanisms in Graph Contrastive Learning NeurIPS 2023 ArCL: Enhancing Contrastive Learning with Augmentation-Robust Representations ICLR 2023 Balance, Imbalance, and Rebalance: Understanding Robust Overfitting from a Minimax Game Perspective NeurIPS 2023 CFA: Class-Wise Calibrated Fair Adversarial Training CVPR 2023 ContraNorm: A Contrastive Learning Perspective on Oversmoothing and Beyond ICLR 2023 Generalist: Decoupling Natural and Robust Generalization CVPR 2023 GEQ: Gaussian Kernel Inspired Equilibrium Models NeurIPS 2023 Identifiable Contrastive Learning with Automatic Feature Importance Discovery NeurIPS 2023 Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral Embedding NeurIPS 2023 On the Connection between Invariant Learning and Adversarial Training for Out-of-Distribution Generalization AAAI 2023 On the Generalization of Multi-modal Contrastive Learning ICML 2023 Rethinking the Effect of Data Augmentation in Adversarial Contrastive Learning ICLR 2023 Rethinking Weak Supervision in Helping Contrastive Learning ICML 2023 Towards a Unified Theoretical Understanding of Non-contrastive Learning via Rank Differential Mechanism ICLR 2023 Towards Memory- and Time-Efficient Backpropagation for Training Spiking Neural Networks ICCV 2023 Unbiased Stochastic Proximal Solver for Graph Neural Networks with Equilibrium States ICLR 2023 A Unified Contrastive Energy-based Model for Understanding the Generative Ability of Adversarial Training ICLR 2022 CerDEQ: Certifiable Deep Equilibrium Model ICML 2022 Certified Adversarial Robustness Under the Bounded Support Set ICML 2022 Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlap ICLR 2022 G$^2$CN: Graph Gaussian Convolution Networks with Concentrated Graph Filters ICML 2022 How Mask Matters: Towards Theoretical Understandings of Masked Autoencoders NeurIPS 2022 Improving Out-of-Distribution Generalization by Adversarial Training with Structured Priors NeurIPS 2022 Optimization-Induced Graph Implicit Nonlinear Diffusion ICML 2022 Optimization inspired Multi-Branch Equilibrium Models ICLR 2022 Self-ensemble Adversarial Training for Improved Robustness ICLR 2022 Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation CVPR 2022 When Adversarial Training Meets Vision Transformers: Recipes from Training to Architecture NeurIPS 2022 Adversarial Neuron Pruning Purifies Backdoored Deep Models NeurIPS 2021 A Unified Approach to Interpreting and Boosting Adversarial Transferability ICLR 2021 Can Subnetwork Structure Be the Key to Out-of-Distribution Generalization? ICML 2021 Clustering Effect of Adversarial Robust Models NeurIPS 2021 Dissecting the Diffusion Process in Linear Graph Convolutional Networks NeurIPS 2021 Efficient Equivariant Network NeurIPS 2021 Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks NeurIPS 2021 Finding Optimal Tangent Points for Reducing Distortions of Hard-label Attacks NeurIPS 2021 Gauge Equivariant Transformer NeurIPS 2021 GBHT: Gradient Boosting Histogram Transform for Density Estimation ICML 2021 Improving Adversarial Robustness via Channel-wise Activation Suppressing ICLR 2021 Leveraged Weighted Loss for Partial Label Learning ICML 2021 Morié Attack (MA): A New Potential Risk of Screen Photos NeurIPS 2021 On Training Implicit Models NeurIPS 2021 Residual Relaxation for Multi-view Representation Learning NeurIPS 2021 Towards a Unified Game-Theoretic View of Adversarial Perturbations and Robustness NeurIPS 2021 Training Feedback Spiking Neural Networks by Implicit Differentiation on the Equilibrium State NeurIPS 2021 Unlearnable Examples: Making Personal Data Unexploitable ICLR 2021 Adversarial Camouflage: Hiding Physical-World Attacks With Natural Styles CVPR 2020 Adversarial Weight Perturbation Helps Robust Generalization NeurIPS 2020 Improving Adversarial Robustness Requires Revisiting Misclassified Examples ICLR 2020 Improving Query Efficiency of Black-box Adversarial Attack ECCV 2020 Normalized Loss Functions for Deep Learning with Noisy Labels ICML 2020 Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets ICLR 2020 Dirichlet Latent Variable Hierarchical Recurrent Encoder-Decoder in Dialogue Generation EMNLP 2019 Hilbert-Based Generative Defense for Adversarial Examples ICCV 2019 On the Convergence and Robustness of Adversarial Training ICML 2019 Symmetric Cross Entropy for Robust Learning With Noisy Labels ICCV 2019 Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality ICLR 2018 Decoupled Networks CVPR 2018 Dimensionality-Driven Learning with Noisy Labels ICML 2018 Iterative Learning With Open-Set Noisy Labels CVPR 2018 Robust Survey Aggregation with Student-t Distribution and Sparse Representation IJCAI 2017 Student-t Process Regression with Student-t Likelihood IJCAI 2017 Bernoulli Random Forests: Closing the Gap between Theoretical Consistency and Empirical Soundness IJCAI 2016