Qi Lei

Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness ICLR 2025 Beyond Invisibility: Learning Robust Visible Watermarks for Stronger Copyright Protection UAI 2025 Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective ICCV 2025 Bridging Domains with Approximately Shared Features AISTATS 2025 Data Reconstruction Attacks and Defenses: A Systematic Evaluation AISTATS 2025 Discrepancies are Virtue: Weak-to-Strong Generalization through Lens of Intrinsic Dimension ICML 2025 Elastic Representation: Mitigating Spurious Correlations for Group Robustness AISTATS 2025 Mono3DVLT: Monocular-Video-Based 3D Visual Language Tracking CVPR 2025 Think Twice, Generate Once: Safeguarding by Progressive Self-Reflection EMNLP 2025 An Information-Theoretic Analysis of In-Context Learning ICML 2024 Controllable Prompt Tuning For Balancing Group Distributional Robustness ICML 2024 Sketchy Moment Matching: Toward Fast and Provable Data Selection for Finetuning NeurIPS 2024 Stochastic Zeroth-Order Optimization under Strongly Convexity and Lipschitz Hessian: Minimax Sample Complexity NeurIPS 2024 Breaking through Deterministic Barriers: Randomized Pruning Mask Generation and Selection EMNLP 2023 Cluster-aware Semi-supervised Learning: Relational Knowledge Distillation Provably Learns Clustering NeurIPS 2023 Optimal Sample Complexity Bounds for Non-convex Optimization under Kurdyka-Lojasiewicz Condition AISTATS 2023 Optimization for Amortized Inverse Problems ICML 2023 Provable Hierarchy-Based Meta-Reinforcement Learning AISTATS 2023 Reconstructing Training Data from Model Gradient, Provably AISTATS 2023 Sample Complexity for Quadratic Bandits: Hessian Dependent Bounds and Optimal Algorithms NeurIPS 2023 Sample Efficiency of Data Augmentation Consistency Regularization AISTATS 2023 Towards Robust Pruning: An Adaptive Knowledge-Retention Pruning Strategy for Language Models EMNLP 2023 CAT: Customized Adversarial Training for Improved Robustness IJCAI 2022 A Theory of Label Propagation for Subpopulation Shift ICML 2021 Few-Shot Learning via Learning the Representation, Provably ICLR 2021 Going Beyond Linear RL: Sample Efficient Neural Function Approximation NeurIPS 2021 How Fine-Tuning Allows for Effective Meta-Learning NeurIPS 2021 Last iterate convergence in no-regret learning: constrained min-max optimization for convex-concave landscapes AISTATS 2021 Near-Optimal Linear Regression under Distribution Shift ICML 2021 Optimal Gradient-based Algorithms for Non-concave Bandit Optimization NeurIPS 2021 Predicting What You Already Know Helps: Provable Self-Supervised Learning NeurIPS 2021 Solving Inverse Problems with a Flow-based Noise Model ICML 2021 Communication-Efficient Asynchronous Stochastic Frank-Wolfe over Nuclear-norm Balls AISTATS 2020 Fast Convergence of Langevin Dynamics on Manifold: Geodesics meet Log-Sobolev NeurIPS 2020 SGD Learns One-Layer Networks in WGANs ICML 2020 Inverting Deep Generative models, One layer at a time NeurIPS 2019 Primal-Dual Block Generalized Frank-Wolfe NeurIPS 2019 Similarity Preserving Representation Learning for Time Series Clustering IJCAI 2019 Hessian-based Analysis of Large Batch Training and Robustness to Adversaries NeurIPS 2018 Random Warping Series: A Random Features Method for Time-Series Embedding AISTATS 2018 Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization ICML 2018 A Greedy Approach for Budgeted Maximum Inner Product Search NeurIPS 2017 Doubly Greedy Primal-Dual Coordinate Descent for Sparse Empirical Risk Minimization ICML 2017 Gradient Coding: Avoiding Stragglers in Distributed Learning ICML 2017 Coordinate-wise Power Method NeurIPS 2016