collaborators

11 papers

cs.AI2026

Breaking the Reversal Curse in Autoregressive Language Models via Identity Bridge

Xutao Ma, Yixiao Huang, Hanlin Zhu +1

Autoregressive large language models (LLMs) have achieved remarkable success in many complex tasks, yet they can still fail in very simple logical reasoning such as the "reversal c…

cs.LG2026

Transformers Provably Learn to Internalize Chain-of-Thought

Yixiao Huang, Hanlin Zhu, Zixuan Wang +4

Chain-of-Thought (CoT) prompting substantially improves the sample efficiency of transformers, reducing the complexity of tasks like parity learning from exponential to polynomial…

cs.LG2026

Multi-Objective Learning for Diffusion Models: A Statistical Theory under Semi-Supervised Learning

Ziheng Cheng, Yixiao Huang, Hanlin Zhu +5

Diffusion models are increasingly used as powerful conditional generators, yet real deployments often involve multiple target distributions arising from different tasks, e.g., dive…

cs.LG2026

Do Sparse Autoencoders Identify Reasoning Features in Language Models?

George Ma, Zhongyuan Liang, Irene Y. Chen +1

We study how reliably sparse autoencoders (SAEs) support claims about reasoning-related internal features in large language models. We first give a stylized analysis showing that s…

cs.CV2026

ScribbleEdit: Synthetic Data for Image Editing with Scribbles and Text

Anya Ji, George Ma, Téa Wright +4

Recent progress in generative models has significantly advanced image editing capabilities, yet precise and intuitive user control remains difficult. Specifically, users often stru…

cs.LG2026

Reinforcement Learning via Value Gradient Flow

Haoran Xu, Kaiwen Hu, Somayeh Sojoudi +1

We study behavior-regularized reinforcement learning (RL), where regularization toward a reference distribution (the dataset in offline RL or the base model in LLM RL finetuning) i…