9 papers
Image-Conditioned Instance Prompt Network for Referring Remote Sensing Image Segmentation
Biaoyu Ren, Qingsheng Wang, Cun Xu +2
Referring Remote Sensing Image Segmentation (RRSIS) is a situated, task-driven cross-modal task related to the embodied perception paradigm, requiring models to align visual-spatia…
Scaling World Model for Hierarchical Manipulation Policies
Qian Long, Yueze Wang, Jiaxi Song +13
Vision-Language-Action (VLA) models are promising for generalist robot manipulation but remain brittle in out-of-distribution (OOD) settings, especially with limited real-robot dat…
EVEv2: Improved Baselines for Encoder-Free Vision-Language Models
Haiwen Diao, Xiaotong Li, Yufeng Cui +6
Existing encoder-free vision-language models (VLMs) are rapidly narrowing the performance gap with their encoder-based counterparts, highlighting the promising potential for unifie…
Unified Vision-Language-Action Model
Yuqi Wang, Xinghang Li, Wenxuan Wang +5
Vision-language-action models (VLAs) have garnered significant attention for their potential in advancing robotic manipulation. However, previous approaches predominantly rely on t…
End-to-End Vision Tokenizer Tuning
Wenxuan Wang, Fan Zhang, Yufeng Cui +5
Existing vision tokenization isolates the optimization of vision tokenizers from downstream training, implicitly assuming the visual tokens can generalize well across various tasks…
Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities
Jing Liu, Wenxuan Wang, Yisi Zhang +5
Referring expression segmentation (RES) aims at segmenting the entities' masks that match the descriptive language expression. While traditional RES methods primarily address objec…