11 papers
Beyond Visual Similarity: Entity-Aligned Retrieval for Knowledge-Based Visual Question Answering
Hangrui Xu, Zhengxian Wu, Yunyao Yu +6
Knowledge-Based Visual Question Answering (KB-VQA) relies on retrieving external information to answer queries involving long-tail entities. However, existing retrieval pipelines p…
ProMSA:Progressive Multimodal Search Agents for Knowledge-Based Visual Question Answering
ZhengXian Wu, Hangrui Xu, Kai Shi +8
Knowledge-based Visual Question Answering (KB-VQA) requires models to combine image understanding with external knowledge. Most prior methods use a fixed retrieve-then-generate pip…
Stabilizing Unsupervised Self-Evolution of MLLMs via Continuous Softened Retracing reSampling
Yunyao Yu, Zhengxian Wu, Zhuohong Chen +6
In the unsupervised self-evolution of Multimodal Large Language Models, the quality of feedback signals during post-training is pivotal for stable and effective learning. However,…
When Models Judge Themselves: Unsupervised Self-Evolution for Multimodal Reasoning
Zhengxian Wu, Kai Shi, Chuanrui Zhang +10
Recent progress in multimodal large language models has led to strong performance on reasoning tasks, but these improvements largely rely on high-quality annotated data or teacher-…
Anatomical Prior-Driven Framework for Autonomous Robotic Cardiac Ultrasound Standard View Acquisition
Zhiyan Cao, Zhengxi Wu, Yiwei Wang +5
Cardiac ultrasound diagnosis is critical for cardiovascular disease assessment, but acquiring standard views remains highly operator-dependent. Existing medical segmentation models…
UniPR: Unified Object-level Real-to-Sim Perception and Reconstruction from a Single Stereo Pair
Chuanrui Zhang, Yingshuang Zou, ZhengXian Wu +3
Perceiving and reconstructing objects from images are critical for real-to-sim transfer tasks, which are widely used in the robotics community. Existing methods rely on multiple su…
R3G: A Reasoning-Retrieval-Reranking Framework for Vision-Centric Answer Generation
Zhuohong Chen, Zhengxian Wu, Zirui Liao +6
Vision-centric retrieval for VQA requires retrieving images to supply missing visual cues and integrating them into the reasoning process. However, selecting the right images and i…
Language-Guided and Motion-Aware Gait Representation for Generalizable Recognition
Zhengxian Wu, Chuanrui Zhang, Shenao Jiang +6
Gait recognition is emerging as a promising technology and an innovative field within computer vision, with a wide range of applications in remote human identification. However, ex…
RoDyn: Taming Interactive Robot-Dynamic 2.5D World Model for Robotic Manipulation
Chuanrui Zhang, Zhengxian Wu, Guanxing Lu +2
Learned world models hold significant potential as neural simulators for robotic manipulation. However, prevalent 2D video-based models inherently lack the spatial and kinematic re…
DAGait: Generalized Skeleton-Guided Data Alignment for Gait Recognition
Zhengxian Wu, Chuanrui Zhang, Hangrui Xu +2
Gait recognition is emerging as a promising and innovative area within the field of computer vision, widely applied to remote person identification. Although existing gait recognit…
PSGait: Gait Recognition using Parsing Skeleton
Hangrui Xu, Zhengxian Wu, Chuanrui Zhang +4
Gait recognition has emerged as a robust biometric modality due to its non-intrusive nature. Conventional gait recognition methods mainly rely on silhouettes or skeletons. While ef…