Simon Shaolei Du

Policy-Based Trajectory Clustering in Offline Reinforcement Learning UAI 2026 Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination ICML 2025 Exploring How Generative MLLMs Perceive More Than CLIP with the Same Vision Encoder ACL 2025 Is Your World Simulator a Good Story Presenter? A Consecutive Events-Based Benchmark for Future Long Video Generation CVPR 2025 Minimax Optimal Regret Bound for Reinforcement Learning with Trajectory Feedback ICML 2025 Offline Multi-task Transfer RL with Representational Penalization AISTATS 2025 The Crucial Role of Samplers in Online Direct Preference Optimization ICLR 2025 A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning ICLR 2024 CLIPLoss and Norm-Based Data Selection Methods for Multimodal Contrastive Learning NeurIPS 2024 Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking ICLR 2024 Distributional Successor Features Enable Zero-Shot Policy Optimization NeurIPS 2024 Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning ICLR 2024 Horizon-Free Regret for Linear Markov Decision Processes ICLR 2024 How Over-Parameterization Slows Down Gradient Descent in Matrix Sensing: The Curses of Symmetry and Initialization ICLR 2024 JoMA: Demystifying Multilayer Transformers via Joint Dynamics of MLP and Attention ICLR 2024 Rethinking Transformers in Solving POMDPs ICML 2024 Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning ICLR 2024 Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov Games ICLR 2023 Horizon-Free and Variance-Dependent Reinforcement Learning for Latent Markov Decision Processes ICML 2023 Improved Active Multi-Task Representation Learning via Lasso ICML 2023 Linear Convergence of Natural Policy Gradient Methods with Log-Linear Policies ICLR 2023 Offline Congestion Games: How Feedback Type Affects Data Coverage Requirement ICLR 2023 On the Power of Pre-training for Generalization in RL: Provable Benefits and Hardness ICML 2023 Sharp Variance-Dependent Bounds in Reinforcement Learning: Best of Both Worlds in Stochastic and Deterministic Environments ICML 2023 Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing ICML 2023 Variance-Aware Sparse Linear Bandits ICLR 2023 AdaLoss: A Computationally-Efficient and Provably Convergent Adaptive Gradient Method AAAI 2022 A Reduction-Based Framework for Conservative Bandits and Reinforcement Learning ICLR 2022 Provable Adaptation across Multiway Domains via Representation Learning ICLR 2022 Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization ICLR 2021 Few-Shot Learning via Learning the Representation, Provably ICLR 2021 How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks ICLR 2021 Impact of Representation Learning in Linear Bandits ICLR 2021 Optimism in Reinforcement Learning with Generalized Linear Function Approximation ICLR 2021 An Improved Gap-Dependency Analysis of the Noisy Power Method COLT 2016