Yuejie Chi

Full Professor@Yale University·美国·OpenReview

研究方向

reinforcement learning · statistical learning · nonconvex optimization · signal processing · inverse problems · data science · generative AI · distributed optimization

Yuejie Chi

Achieving Logarithmic Regret in KL-Regularized Zero-Sum Markov Games

Generalized Parallel Scaling with Interdependent Generations

Polynomial Convergence of Riemannian Diffusion Models

Scalable LLM Math Reasoning Acceleration with Low-rank Distillation

Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RL

Transformers Provably Learn Chain-of-Thought Reasoning with Length Generalization

Multi-head Transformers Provably Learn Symbolic Multi-step Reasoning via Gradient Descent

ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference

ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference

LoRe: Personalizing LLMs via Low-Rank Reward Modeling

Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning

A Theoretical Analysis of Self-Supervised Learning for Vision Transformers

Breaking the Curse of Multiagency in Robust Multi-Agent Reinforcement Learning

Vertical Federated Learning with Missing Features During Training and Inference

Incentivize without Bonus: Provably Efficient Model-based Online Multi-agent RL for Markov Games

Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF

Breaking the Curse of Multiagency in Robust Multi-Agent Reinforcement Learning

Feynman: Knowledge-Infused Diagramming Agent for Scaling Visual Reasoning Data