Active vision manipulation requires a policy to control both its camera and its end-effectors, yet camera motion determines which evidence remains visible within finite observation windows. Acquiring a new view can displace task-critical cues, while retaining a view forgoes potentially useful observations. We formulate...
ViTaR is introduced, which reframes tactile feedback from an action-generating perceptual input to an execution modulator that selects and scales bounded residual corrections atop a frozen VLA, preserving pretrained capabilities by construction.
Yi Wang, Ren-Jun Wu, Jin-Yan Liu et al.· 0 citations
SparkVLA is presented, a stop-aware hierarchical VLA that resolves this mutual dependency by formulating both decisions as a single ranking: Stop competes against every action-prefix length in a unified candidate set, and the system selects the highest-scoring option, eliminating threshold tuning and requiring only off...
Xun-Yao Lei, Ren-Jun Wu, Tianlin Huo et al.· 1 citation
This work proposes MemCatalyst, a set of data poisoning tools, aiming to amplify the data auditing performance on VLMs, and forces VLMs to over-learn specific inconsistencies between image features and textual semantics during training, thereby increasing their susceptibility to membership information auditing.
Xukun Luan, Jinyan Liu, Yuhui Gong et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
