collaborators

8 papers

cs.AI2026

MemPrism: Task-Conditioned Relational Memory Views for Long-Horizon Agents

Zhisheng Chen, Bingfan Zeng, Bangde Cao +8

Long-horizon agents rely on memory to reuse experiences, yet existing memory systems often assume that evidence can be directly consumed through a fixed representation. This leads…

cs.CV2026

ProtoAda: Prototype-Guided Adaptive Adapter Expansion and Geometric Consolidation for Multimodal Continual Instruction Tuning

Yu-Cheng Shi, Zhen-Hao Xie, Jun-Tao Tang +1

Multimodal Large Language Models (MLLMs) achieve strong performance through instruction tuning, but real-world deployment requires them to continually acquire new vision-language c…

cs.CL2026

CRAM: Centroid-Routing and Adaptive MoE for Multimodal Continual Instruction Tuning

Jun-Tao Tang, Zhen-Hao Xie, Yu-Cheng Shi +1

Multimodal Large Language Models (MLLMs) unify heterogeneous vision-language tasks under a shared generative framework via instruction tuning, yet real-world deployment demands con…

cs.AI2026

PolarMem: A Training-Free Polarized Latent Graph Memory for Verifiable Vision-Language Models

Zhisheng Chen, Tingyu Wu, Zijie Zhou +7

Memory is not merely a storage mechanism for intelligent systems, but a structure for organizing evidence and constraining belief. This is especially important for multimodal reaso…

cs.LG2026

SAME: Stabilized Mixture-of-Experts for Multimodal Continual Instruction Tuning

Zhen-Hao Xie, Jun-Tao Tang, Yu-Cheng Shi +3

Multimodal Large Language Models (MLLMs) achieve strong performance through instruction tuning, but real-world deployment requires them to continually expand their capabilities, ma…

cs.AI2026

MineEvolve: Self-Evolution with Accumulated Knowledge for Long-Horizon Embodied Minecraft Agents

Zhengwei Xie, Zhisheng Chen, Ziyan Weng +7

Long-horizon embodied intelligence requires agents to improve through interaction, not merely to execute plans generated from static goals. A central challenge is therefore to tran…