6 papers · 1 filter
CARE: Experience-Guided Atomic Corrective Execution for Vision-Language-Action Policies
Junlan Xiao, Junwei Jiang, Zaibin Zhang +4
Vision-Language-Action (VLA) policies achieve strong performance in robotic manipulation but remain brittle once execution deviates from nominal trajectories. We propose CARE (Corr…
MinCU: A Fine-Grained Benchmark for Grounded Minimal-Change Understanding in Image Pairs
Chaoqian Mu, Wenhao Wu, Zichen Liang +4
Localizing and describing fine-grained differences between near-identical images is a critical yet underexplored capability for multimodal large language models (MLLMs). Existing b…
MA-VLA: Multi-Arm Vision-Language-Action Model for Collaboration and Compositional Generalization
Zaibin Zhang, Junlan Xiao, Zhongbo Zhang +11
Multi-arm collaboration is becoming a core capability in embodied manipulation. Recent vision-language-action (VLA) models integrate perception, language, and control, but most rep…
Revisiting Salient Object Detection from an Observer-Centric Perspective
Fuxi Zhang, Yifan Wang, Hengrun Zhao +7
Salient object detection is inherently a subjective problem, as observers with different priors may perceive different objects as salient. However, existing methods predominantly f…
AR-MOT: Autoregressive Multi-object Tracking
Lianjie Jia, Yuhan Wu, Binghao Ran +3
As multi-object tracking (MOT) tasks continue to evolve toward more general and multi-modal scenarios, the rigid and task-specific architectures of existing MOT methods increasingl…
Think3D: Thinking with Space for Spatial Reasoning
Zaibin Zhang, Yuhan Wu, Lianjie Jia +10
While Vision-Language Models (VLMs) excel at 2D visual understanding, they remain constrained by 2D-centric paradigm that severely limits genuine 3D spatial reasoning. To bridge th…