collaborators

6 papers

cs.CV2026

MuRA: Multi-Rank Adaptation for Efficient and Effective Test-Time Vision-Language Generalization

Gengyuan Liu, Nanzhou Wang, Chang Liu +5

Vision-language models exhibit remarkable zero-shot capabilities but suffer significant performance degradation under distribution shifts. While test-time adaptation (TTA) via Low-…

cs.RO2026

UniLab: A Heterogeneous Architecture for Robot RL Beyond GPU-Dominant Paradigms

Yufei Jia, Zhanxiang Cao, Mingrui Yu +48

Simulation-based RL for contemporary robot control is increasingly organized around GPU-resident simulation: physics, rollout collection, and learning are placed on a single GPU-ce…

cs.AI2025

ChordPrompt: Orchestrating Cross-Modal Prompt Synergy for Multi-Domain Incremental Learning in CLIP

Zhiyuan Wang, Bokui Chen

Continual learning (CL) empowers pre-trained vision-language models to adapt effectively to novel or previously underrepresented data distributions without comprehensive retraining…

cs.AI2025

ORMind: A Cognitive-Inspired End-to-End Reasoning Framework for Operations Research

Zhiyuan Wang, Bokui Chen, Yinya Huang +4

Operations research (OR) is widely deployed to solve critical decision-making problems with complex objectives and constraints, impacting manufacturing, logistics, finance, and hea…

cs.LG2025

INCPrompt: Task-Aware incremental Prompting for Rehearsal-Free Class-incremental Learning

Zhiyuan Wang, Xiaoyang Qu, Jing Xiao +2

This paper introduces INCPrompt, an innovative continual learning solution that effectively addresses catastrophic forgetting. INCPrompt's key innovation lies in its use of adaptiv…

cs.LG2025

P2DT: Mitigating Forgetting in task-incremental Learning with progressive prompt Decision Transformer

Zhiyuan Wang, Xiaoyang Qu, Jing Xiao +2

Catastrophic forgetting poses a substantial challenge for managing intelligent agents controlled by a large model, causing performance degradation when these agents face new tasks.…