Shuai Li

Bandit Learning for Online Scheduling with Immediate Decision

Multi-Subspace Multi-Modal Modeling for Diffusion Models: Estimation, Convergence and Mixture of Experts

Player-optimal Stable Regret for Bandit Learning in Many-to-one Matching Markets with Substitutability

Elucidating Guidance in Variance Exploding Diffusion Models: Fast Convergence and Better Diversity

AdaReP: Plug-and-Play Acceleration for World Model Predictive Control using Adaptive Re-Planning

On the Effect of Positional Encoding for In-context Learning in Transformers

The Accumulation of Score Estimation Error in Diffusion Models

Evaluating the Role of Great Pre-trained Diffusion Models in Few-shot Phase: Warm-up and Acceleration

Quantifying QiGan: What Shape Patterns Does a DNN Exploit in Go?

Overcoming Redundant Context in Auto-Regressive LLMs with Dynamic Draft Refinement

In-Context Stochastic Gradient Descent with Hybrid Mamba-2 and Linear Self-Attention Model

One-Shot Style Personalization for RL Agents via Latent Discriminator

Efficient Thinking via Meta Chain-of-Thought Evaluation

Beyond Static Retrieval Policies: Task-Aware Adaptive RAG With METAR

Optimal Algorithm for Max-Min Fair Bandit

Learning Preferences without Interaction for Cooperative AI: A Hybrid Offline-Online Approach

Bandit Learning in Matching Markets with Indifference

Learning Imperfect Information Extensive-form Games with Last-iterate Convergence under Bandit Feedback

Optimal Algorithm for Max-Min Fair Bandit

Online-to-Offline RL for Agent Alignment

Learning Imperfect Information Extensive-form Games with Last-iterate Convergence under Bandit Feedback

Multi-player Multi-armed Bandits with Delayed Feedback

Improved Discretization Complexity Analysis of Consistency Models: Variance Exploding Forward Process and Decay Discretization Scheme

Offline-to-Online Reinforcement Learning with Classifier-Free Diffusion Generation

Contrastive guidance and feedback: A Suitable way to improve 3D Consistency of Multi-view Diffusion Model

The Convergence of Second-Order Sampling Methods for Diffusion Models

The Implicit Bias of Stochastic AdaGrad-Norm on Separable Data

Adversarial Attacks on Cooperative Multi-agent Bandits

The Discretization Complexity Analysis of Consistency Models under Variance Exploding Forward Process

Offline-to-Online Reinforcement Learning with Classifier-Free Diffusion Generation