Hongyuan Zha

Error Analysis of Discrete Flow with Generator Matching

Negotiated Reasoning: On Provably Addressing Relative Over-Generalization

Finetuning-free Alignment of Diffusion Model for Text-to-Image Generation

Offline Multi-Agent Reinforcement Learning via Sequential Score Decomposition

Discrete Guidance Matching: Exact Guidance for Discrete Flow Matching

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

LLM as an Algorithmist: Enhancing Anomaly Detectors via Programmatic Synthesis

CALM Before the STORM: Unlocking Native Reasoning for Optimization Modeling

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

Information Bargaining: Bilateral Commitment in Bayesian Persuasion

Verbalized Bayesian Persuasion

A Distributional Approach to Uncertainty-Aware Preference Alignment Using Offline Demonstrations

LOPT: Learning Optimal Pigovian Tax in Sequential Social Dilemmas

Reward Translation via Reward Machine in Semi-Alignable MDPs

Generative Modeling Reinvents Supervised Learning: Label Repurposing with Predictive Consistency Learning

Your Consistency Model is Secretly a More Powerful Supervised Learning Paradigm for Learning Tasks with Complex Labels

Verbalized Bayesian Persuasion

Bayesian Persuasion Is a Bargaining Game

Offline Multi-agent Reinforcement Learning with Sequential Score Decomposition

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