9 papers
Gym-V: A Unified Vision Environment System for Agentic Vision Research
Fanqing Meng, Lingxiao Du, Jiawei Gu +9
As agentic systems increasingly rely on reinforcement learning from verifiable rewards, standardized ``gym'' infrastructure has become essential for rapid iteration, reproducibilit…
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…
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…
Vision Graph Prompting via Semantic Low-Rank Decomposition
Zixiang Ai, Zichen Liu, Jiahuan Zhou
Vision GNN (ViG) demonstrates superior performance by representing images as graph structures, providing a more natural way to capture irregular semantic patterns beyond traditiona…
Token Coordinated Prompt Attention is Needed for Visual Prompting
Zichen Liu, Xu Zou, Gang Hua +1
Visual prompting techniques are widely used to efficiently fine-tune pretrained Vision Transformers (ViT) by learning a small set of shared prompts for all tokens. However, existin…
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…
STOP: Integrated Spatial-Temporal Dynamic Prompting for Video Understanding
Zichen Liu, Kunlun Xu, Bing Su +3
Pre-trained on tremendous image-text pairs, vision-language models like CLIP have demonstrated promising zero-shot generalization across numerous image-based tasks. However, extend…
SCAP: Transductive Test-Time Adaptation via Supportive Clique-based Attribute Prompting
Chenyu Zhang, Kunlun Xu, Zichen Liu +2
Vision-language models (VLMs) encounter considerable challenges when adapting to domain shifts stemming from changes in data distribution. Test-time adaptation (TTA) has emerged as…
Selective Visual Prompting in Vision Mamba
Yifeng Yao, Zichen Liu, Zhenyu Cui +2
Pre-trained Vision Mamba (Vim) models have demonstrated exceptional performance across various computer vision tasks in a computationally efficient manner, attributed to their uniq…