collaborators

9 papers

cs.AI2026

ComMem: Complementary Memory Systems for Test-Time Adaptation of Vision-Language Models

Guanglong Sun, Shuang Cui, Bo Lei +6

Test-time adaptation (TTA) of vision-language models (VLMs) is essential for their robust deployment in dynamic, real-world environments. However, existing TTA methods often adapt…

cs.LG2026

Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection

Guanglong Sun, Siyuan Zhang, Liyuan Wang +3

Safety post-training can improve the harmfulness and policy compliance of Large Language Models (LLMs), but it may also reduce general utility, a phenomenon often described as the…

cs.AI2026

MePo: Meta Post-Refinement for Rehearsal-Free General Continual Learning

Guanglong Sun, Hongwei Yan, Liyuan Wang +5

To cope with uncertain changes of the external world, intelligent systems must continually learn from complex, evolving environments and respond in real time. This ability, collect…

cs.LG2026

FlyPrompt: Brain-Inspired Random-Expanded Routing with Temporal-Ensemble Experts for General Continual Learning

Hongwei Yan, Guanglong Sun, Kanglei Zhou +3

General continual learning (GCL) challenges intelligent systems to learn from single-pass, non-stationary data streams without clear task boundaries. While recent advances in conti…

cs.CV2026

TP-Blend: Textual-Prompt Attention Pairing for Precise Object-Style Blending in Diffusion Models

Xin Jin, Yichuan Zhong, Yapeng Tian

Current text-conditioned diffusion editors handle single object replacement well but struggle when a new object and a new style must be introduced simultaneously. We present Twin-P…

cs.CV2026

Sparse Video Generation Propels Real-World Beyond-the-View Vision-Language Navigation

Hai Zhang, Siqi Liang, Li Chen +5

Why must vision-language navigation be bound to detailed and verbose language instructions? While such details ease decision-making, they fundamentally contradict the goal for navi…