4 papers · 1 filter
What do VLM-Based Vision-Language Navigation Models Rely on: Interpreting and Steering Policy Behavior
Débora Oliveira Makowski, Samiran Gode, Abhijeet Nayak +4
Modern Vision-Language Navigation (VLN) models rely mostly on pre-trained large Vision-Language Models (VLMs) to predict navigation actions. While this fusion of language instructi…
PointACT: Vision-Language-Action Models with Multi-Scale Point-Action Interaction
Shizhe Chen, Paul Pacaud, Cordelia Schmid
Vision-Language-Action (VLA) models have shown strong potential for general-purpose robotic manipulation by leveraging large pretrained vision-language backbones. However, most exi…
MetricNet: Recovering Metric Scale in Generative Navigation Policies
Abhijeet Nayak, Débora Oliveira Makowski, Samiran Gode +2
Generative navigation policies have made rapid progress in improving end-to-end learned navigation. Despite their promising results, this paradigm has two structural problems. Firs…
FlowNav: Combining Flow Matching and Depth Priors for Efficient Navigation
Samiran Gode, Abhijeet Nayak, Débora N. P. Oliveira +3
Effective robot navigation in unseen environments is a challenging task that requires precise control actions at high frequencies. Recent advances have framed it as an image-goal-c…