13 papers
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…
From Forecasting to Planning: Policy World Model for Collaborative State-Action Prediction
Zhida Zhao, Talas Fu, Yifan Wang +2
Despite remarkable progress in driving world models, their potential for autonomous systems remains largely untapped: the world models are mostly learned for world simulation and d…
Learning Universal Features for Generalizable Image Forgery Localization
Hengrun Zhao, Yunzhi Zhuge, Yifan Wang +3
In recent years, advanced image editing and generation methods have rapidly evolved, making detecting and locating forged image content increasingly challenging. Most existing imag…
Mono2Stereo: A Benchmark and Empirical Study for Stereo Conversion
Songsong Yu, Yuxin Chen, Zhongang Qi +5
With the rapid proliferation of 3D devices and the shortage of 3D content, stereo conversion is attracting increasing attention. Recent works introduce pretrained Diffusion Models…
AVS-Mamba: Exploring Temporal and Multi-modal Mamba for Audio-Visual Segmentation
Sitong Gong, Yunzhi Zhuge, Lu Zhang +4
The essence of audio-visual segmentation (AVS) lies in locating and delineating sound-emitting objects within a video stream. While Transformer-based methods have shown promise, th…
GLDesigner: Leveraging Multi-Modal LLMs as Designer for Enhanced Aesthetic Text Glyph Layouts
Junwen He, Yifan Wang, Lijun Wang +7
Text logo design heavily relies on the creativity and expertise of professional designers, in which arranging element layouts is one of the most important procedures. However, this…
AD-H: Language-guided Autonomous Driving with Hierarchical Agents
Zaibin Zhang, Talas Fu, Shiyu Tang +4
Language-guided autonomous driving requires bridging a large abstraction gap between high-level natural-language instructions and low-level vehicle control. End-to-end approaches t…
Multi-modal Instruction Tuned LLMs with Fine-grained Visual Perception
Junwen He, Yifan Wang, Lijun Wang +5
Multimodal Large Language Model (MLLMs) leverages Large Language Models as a cognitive framework for diverse visual-language tasks. Recent efforts have been made to equip MLLMs wit…