activity
20242026
collaborators

12 papers

math.OC2026

On Second-Order Methods for Bilevel Optimization

Jiawen Bi, Jiaxiang Li, Mingyi Hong +1

Bilevel optimization is an indispensable modeling tool for modern machine learning and engineering design. However, the theory and practice for finding second order stationary poin…

cs.RO2026

Action-Effect Memory Pretraining for Robot Manipulation

Yijing Zhou, Qiwei Liang, Sitong Zhuang +5

We present AEM, an Action-Effect Memory pretraining framework for robot manipulation that learns compact temporal representations from vision-action history. Unlike prior robot rep…

cs.LG2026

Memory-Efficient LLM Pretraining via Minimalist Optimizer Design

Athanasios Glentis, Jiaxiang Li, Andi Han +1

Training large language models (LLMs) relies on adaptive optimizers such as Adam, which introduce extra operations and require significantly more memory to maintain first- and seco…

math.OC2026

A Correspondence-Driven Approach for Bilevel Decision-making with Nonconvex Lower-Level Problems

Xiaotian Jiang, Jiaxiang Li, Jiawen Bi +2

We consider bilevel optimization problems with general nonconvex lower-level objectives and show that the classical hyperfunction-based formulation is unsettled, since the global m…

cs.AI2025

A Framework for Quantifying How Pre-Training and Context Benefit In-Context Learning

Bingqing Song, Jiaxiang Li, Rong Wang +2

Pre-trained large language models have demonstrated a strong ability to learn from context, known as in-context learning (ICL). Despite a surge of recent applications that leverage…

cs.LG2025

ADARL: Adaptive Low-Rank Structures for Robust Policy Learning under Uncertainty

Chenliang Li, Junyu Leng, Jiaxiang Li +4

Robust reinforcement learning (Robust RL) seeks to handle epistemic uncertainty in environment dynamics, but existing approaches often rely on nested min--max optimization, which i…