autoregressive generation 1continuous environments 1embodied navigation 1pixel-space trajectory 1vision-language navigation 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.RO2026
CAAT: Contact-Aware Attention Scaling and Tactile Masking for Data-Efficient Contact-Rich Manipulation
Jiaming Jiang, Yuzhe Huang, Hao Liang +7
In contact-rich manipulation, visual observations primarily guide motion in free space, whereas tactile observations become particularly informative during contact. However, standa…
cs.CV2026
Traj-VLN: Learning Pixel-Space Interaction via Autoregressive Trajectory Generation
Changfei Fu, Guangcheng Chen, Wenjun Xu +3
The paper introduces a method that fine‑tunes vision‑language models to predict sequences of pixel coordinates, enabling an embodied agent to follow natural language navigation ins…