Open-vocabulary visual grounding enables robots to localise task-relevant entities from natural-language queries without dependence on predefined perceptual taxonomies. However, existing benchmarks largely rely on short category labels and web-scraped imagery, leaving it unclear whether open-vocabulary models can robus...
Linus Nwankwo, Muslim Alaran, Christian Rauch et al.· 0 citations
Latent world models enable planning by predicting the effects of actions in a learned representation space, but their predictions can become unreliable when test-time conditions differ from training. Existing test-time adaptation methods address this by updating parts of the pretrained model, often modifying millions o...
Krishnam Soni, Aditya Sehgal, Vedant Dave et al.· 0 citations
InfiNoVA is introduced, a data-augmentation framework that converts synchronized multi-camera demonstrations into a dense distribution of geometrically consistent training views that improves frame-level fidelity and temporal consistency while reducing task-critical hallucinations observed in generative novel-view synt...
Sai Puneeth Reddy Gottam, Elmar Rueckert, Vedant Dave· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.