Baoxiang Wang

Offline Multi-Agent Reinforcement Learning via Sequential Score Decomposition

Talk, Judge, Cooperate: Gossip-Driven Indirect Reciprocity in Self-Interested LLM Agents

Provable Strategic In-Context Learning of Transformers

On the Decomposition of Differentiable Games

When Human Data Runs Out: Self-Supervised Reasoning via Negotiation Self-Play

Information Bargaining: Bilateral Commitment in Bayesian Persuasion

Pointwise Convergence in Games with Conflicting Interests

Verbalized Bayesian Persuasion

Improved Approximation Algorithms for $k$-Submodular Maximization via Multilinear Extension

Scalable Exploration via Ensemble++

Uncoupled and Convergent Learning in Monotone Games under Bandit Feedback

The adaptive complexity of parallelized log-concave sampling

A Comprehensive Framework for Analyzing the Convergence of Adam: Bridging the Gap with SGD

Tackling Data Corruption in Offline Reinforcement Learning via Sequence Modeling

ADG: Ambient Diffusion-Guided Dataset Recovery for Corruption-Robust Offline Reinforcement Learning

Learning to Communicate Through Implicit Communication Channels

Reward Translation via Reward Machine in Semi-Alignable MDPs

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

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

Scalable Exploration via Ensemble++

No-Regret and Incentive-Compatible Combinatorial Online Prediction

The Implicit Bias of Stochastic AdaGrad-Norm on Separable Data

Uncoupled and Convergent Learning in Monotone Games under Bandit Feedback

Verbalized Bayesian Persuasion

Bayesian Persuasion Is a Bargaining Game

No MCMC Teaching For me: Learning Energy-Based Models via Diffusion Synergy

Offline Multi-agent Reinforcement Learning with Sequential Score Decomposition

A Comprehensive Framework for Analyzing the Convergence of Adam: Bridging the Gap with Stochastic Gradient Descent