We're a research lab advancing the frontiers of both theoretical and empirical machine learning. Our directions include LLM reasoning, reinforcement learning, AI agents, alignment, optimization, and generative models.

Faculty

Prof. Tong Zhang

Ph.D.

Ordered by year

Wei Xiong

LLM Reasoning

Theoretical & Empirical RL

Chenlu Ye

LLM Reinforcement Learning

Reasoning

Multi-turn Agent

Yifan Hao

Post-training

Reasoning

Deep Learning

Rui Pan

Optimization

Acceleration

LLM Training

Rui Yang

Reinforcement Learning

LLM Alignment

VLM-based Agents

Shivanshu Shekhar

RLHF for Continuous Generative Models

Yuxing Liu

Optimization Theory & Practice

LLM Training

Nishant Jain

Theoretical Analysis for Generative Models

Jiarui Yao

RL for LLMs

Agents

Multimodal

Jack (Hao) Bai

LLM Reasoning

Empirical RL

Agents

Ruida Wang

Neuron-symbolic LLM

Formal Math Reasoning

Lean4

M.S.

Alphabetical order

Hanyang Chen

Embodied AI

Reinforcement Learning

Jerry Huang

LLM Agents

Alignment

Reasoning

Planning

Pengcheng Wang

LLM Agents

Diffusion Language Model

Hanning Zhang

LLM Reasoning

LLM Alignment

Empirical Reinforcement Learning