collaborators

6 papers

cs.LG2026

Sharper Analysis of Single-Loop Methods for Bilevel Optimization

Yubo Zhou, Jun Shu, Luo Luo +4

Bilevel optimization underpins many machine learning applications, including hyperparameter optimization, meta-learning, neural architecture search, and reinforcement learning. Whi…

cs.LG2026

A Limit Theory of Foundation Models: A Mathematical Approach to Understanding Emergent Intelligence and Scaling Laws

Jun Shu, Junxiong Jia, Deyu Meng +1

Emergent intelligence have played a major role in the modern AI development. While existing studies primarily rely on empirical observations to characterize this phenomenon, a rigo…

cs.LG2026

Understanding the Generalization of Bilevel Programming in Hyperparameter Optimization: A Tale of Bias-Variance Decomposition

Yubo Zhou, Jun Shu, Junmin Liu +1

Gradient-based hyperparameter optimization (HPO) have emerged recently, leveraging bilevel programming techniques to optimize hyperparameter by estimating hypergradient w.r.t. vali…

cs.LG2026

KoopGen: Koopman Generator Networks for Representing and Predicting Dynamical Systems with Continuous Spectra

Liangyu Su, Jun Shu, Rui Liu +2

Representing and predicting high-dimensional and spatiotemporally chaotic dynamical systems remains a fundamental challenge in dynamical systems and machine learning. Although data…

cs.CV2026

Are Dense Labels Always Necessary for 3D Object Detection from Point Cloud?

Chenqiang Gao, Chuandong Liu, Jun Shu +5

Current state-of-the-art (SOTA) 3D object detection methods often require a large amount of 3D bounding box annotations for training. However, collecting such large-scale densely-s…

cs.LG2026

Rollout-Training Co-Design for Efficient LLM-Based Multi-Agent Reinforcement Learning

Zhida Jiang, Zhaolong Xing, Jiawei Lu +13

Despite algorithm-level innovations for multi-agent reinforcement learning (MARL), the underlying networked infrastructure for large-scale MARL training remains underexplored. Exis…