7 papers
CofactVLA: Deconfounding Vision-Language-Action Models via Counterfactual Intervention
Yan Zhang, Yinan Wu, Haoran Duan +1
Vision-Language-Action (VLA) models have driven significant progress in robotic manipulation, yet they fundamentally struggle with the vision-override phenomenon. Driven by the sev…
QuoVLA: Quotient Space for Vision-Language-Action Models
Xuan Wang, Yinan Wu, Haoran Duan +1
Vision-Language-Action (VLA) models commonly adapt pretrained Vision-Language Models (VLMs) to robot control by mapping visual observations and language instructions to continuous…
Selective Coupling of Decoupled Informative Regions: Masked Attention Alignment for Data-Free Quantization of Vision Transformers
Biao Qian, Yang Wang, Yong Wu +1
Data-Free Quantization (DFQ) addresses data security concerns by synthesizing samples, without accessing real data. It has garnered increasing attention in the context of Vision Tr…
ConsDreamer: Advancing Multi-View Consistency for Zero-Shot Text-to-3D Generation
Yuan Zhou, Shilong Jin, Litao Hua +3
Recent advances in zero-shot text-to-3D generation have revolutionized 3D content creation by enabling direct synthesis from textual descriptions. While state-of-the-art methods le…
From Gaze to Insight: Bridging Human Visual Attention and Vision Language Model Explanation for Weakly-Supervised Medical Image Segmentation
Jingkun Chen, Haoran Duan, Xiao Zhang +3
Medical image segmentation remains challenging due to the high cost of pixel-level annotations for training. In the context of weak supervision, clinician gaze data captures region…
THU-Warwick Submission for EPIC-KITCHEN Challenge 2025: Semi-Supervised Video Object Segmentation
Mingqi Gao, Haoran Duan, Tianlu Zhang +1
In this report, we describe our approach to egocentric video object segmentation. Our method combines large-scale visual pretraining from SAM2 with depth-based geometric cues to ha…