Haoqian Wang
2 papers · Latest:
Computer Vision
MemOVCD: Training-Free Open-Vocabulary Change Detection via Cross-Temporal Memory Reasoning and Global-Local Adaptive Rectification
MemOVCD is a training-free open-vocabulary change detection framework using cross-temporal memory reasoning and adaptive rectification for remote sensing images.
2604.26774
Robotics$M^2$-VLA: Boosting Vision-Language Models for Generalizable Manipulation via Layer Mixture and Meta-Skills
$M^2$-VLA boosts VLM generalization for robotic manipulation using a Layer Mixture strategy and Meta Skill Module, avoiding catastrophic forgetting.
2604.24182
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.