An Extended Reality sketching application is introduced that offers a new way to use 3D sketches to control the generation of 3D objects with GenAI, highlighting the potential of 3D sketching as a control modality for generative 3D object creation, while identifying object complexity as a key challenge for 3D sketching...
Niklas Pfützenreuter, J. Liebers, Roman Heger et al.· Message Understanding Confer...· 0 citations
Vision-and-Language Navigation (VLN) policies increasingly benefit from strong semantic priors provided by large vision-language models (VLMs). However, standard action supervision does not explicitly encourage intermediate representations to preserve scene geometry, relative orientation, or global episode progress. In...
Anh Dao, Q. Phạm, Le Danh Vinh et al.· 0 citations
Bounded navigation-aware retention preserves navigation performance while considerably reducing GFM-KV memory relative to larger-memory temporal retention, which support jointly examining the geometric representations exposed to the policy and the historical evidence retained for future inference.
Q. Phạm, Anh Dao, Danh Vinh Le et al.· 0 citations
OpenBelief-Nav is presented, an evidence-preserving object memory that retains observation-level phrases, reliability cues, and frame-mask provenance while maintaining separate aggregate geometric and visual representations.
Dinh Tuan Nguyen, Anh Dao, Phuong Nam Dang et al.· 0 citations
HumanoidVLN, a physics-grounded simulator and benchmark for VLN across diverse humanoid embodiments, and compatibility with NaVILA, DualVLN, StreamVLN, and JanusVLN are presented.
Q. Phạm, Anh Dao, T. Nguyen et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
