papers

Publications (234)

cs.LG2026

Breaking AR's Sampling Bottleneck: Provable Acceleration via Diffusion Language Models

Gen Li, Changxiao Cai

Diffusion models have emerged as a powerful paradigm for modern generative modeling, demonstrating strong potential for large language models (LLMs). Unlike conventional autoregres…

cs.LG2025

Transformers Meet In-Context Learning: A Universal Approximation Theory

Gen Li, Yuchen Jiao, Yu Huang +2

Large language models are capable of in-context learning, the ability to perform new tasks at test time using a handful of input-output examples, without parameter updates. We deve…

cs.RO2026

RoboForge: Physically Optimized Text-guided Whole-Body Locomotion for Humanoids

Xichen Yuan, Zhe Li, Bofan Lyu +4

While generative models have become effective at producing human-like motions from text, transferring these motions to humanoid robots for physical execution remains challenging. E…

cs.LG2024

Minimax-Optimal Reward-Agnostic Exploration in Reinforcement Learning

Gen Li, Yuling Yan, Yuxin Chen +1

This paper studies reward-agnostic exploration in reinforcement learning (RL) -- a scenario where the learner is unware of the reward functions during the exploration stage -- and…

cs.LG2020

The Efficacy of Regularization in Two-Layer Neural Networks

Gen Li, Yuantao Gu, Jie Ding

A crucial problem in neural networks is to select the most appropriate number of hidden neurons and obtain tight statistical risk bounds. In this work, we present a new perspective…

cs.RO2024

F3T: A soft tactile unit with 3D force and temperature mathematical decoupling ability for robots

Xiong Yang, Hao Ren, Dong Guo +9

The human skin exhibits remarkable capability to perceive contact forces and environmental temperatures, providing intricate information essential for nuanced manipulation. Despite…