activity
20242026
collaborators

12 papers

cs.CV2026

Breaking the Synthetic-Real Domain Shortcut for Training-Free Generative Replay-based Class Incremental Learning

Tao Zhang, Qixuan Fan, Yiyuan Liang +7

Class-incremental learning (CIL) requires models to continuously acquire new knowledge while avoiding catastrophic forgetting. While exemplar replay is effective, it raises concern…

cs.CV2026

Vision-Language Attribute Disentanglement and Reinforcement for Lifelong Person Re-Identification

Kunlun Xu, Haotong Cheng, Jiangmeng Li +2

Lifelong person re-identification (LReID) aims to learn from varying domains to obtain a unified person retrieval model. Existing LReID approaches typically focus on learning from…

cs.CL2025

COPO: Causal-Oriented Policy Optimization for Hallucinations of MLLMs

Peizheng Guo, Jingyao Wang, Wenwen Qiang +3

Despite Multimodal Large Language Models (MLLMs) having shown impressive capabilities, they may suffer from hallucinations. Empirically, we find that MLLMs attend disproportionatel…

cs.CV2025

State Space Prompting via Gathering and Spreading Spatio-Temporal Information for Video Understanding

Jiahuan Zhou, Kai Zhu, Zhenyu Cui +3

Recently, pre-trained state space models have shown great potential for video classification, which sequentially compresses visual tokens in videos with linear complexity, thereby…

cs.CV2025

Class-aware Domain Knowledge Fusion and Fission for Continual Test-Time Adaptation

Jiahuan Zhou, Chao Zhu, Zhenyu Cui +3

Continual Test-Time Adaptation (CTTA) aims to quickly fine-tune the model during the test phase so that it can adapt to multiple unknown downstream domain distributions without pre…

cs.CV2025

GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision Model

Zixiang Ai, Zichen Liu, Yuanhang Lei +3

Pre-trained 3D vision models have gained significant attention for their promising performance on point cloud data. However, fully fine-tuning these models for downstream tasks is…