VLN-CE
PulseAugur coverage of VLN-CE — every cluster mentioning VLN-CE across labs, papers, and developer communities, ranked by signal.
-
MobileVLA-R1 2.0 enhances robot instruction following with reasoning and RL
Researchers have introduced MobileVLA-R1 2.0, a new framework designed to enhance the ability of mobile robots to follow complex, long-horizon instructions. This system integrates structured reasoning with reinforcement…
-
New Traj-VLN method trains vision-language models for navigation in pixel space
Researchers have developed Traj-VLN, a novel approach for Vision-and-Language Navigation in Continuous Environments (VLN-CE). This method focuses on training Vision-Language Models (VLMs) to generate navigation trajecto…
-
New CoFL-S framework enhances low-level action generation for robot navigation
Researchers have introduced CoFL-S, a novel framework designed to improve low-level action generation for Vision-Language Navigation (VLN) tasks. This approach predicts a language-conditioned flow field within the robot…