Does increasing VLA parameter count from 7B to 13B improve long-horizon task completion rate and average rewar

Incremental decision making in real-world environments is one of the most challenging tasks in embodied artificial intelligence. One particularly demanding scenario is Vision and Language Navigation (VLN) which requires visual and natural language understanding as well as spatial and temporal reasoning capabilities. The embodied agent needs to ground its understanding of navigation instructions in observations of a real-world environment like Street View. Despite the impressive results of LLMs in other research areas, it is an ongoing problem of how to best connect them with an interactive vis

Research goal: Does increasing VLA parameter count from 7B to 13B improve long-horizon task completion rate and average reward on R2R-CE when evaluated with zero-shot cross-dataset generalization?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 8.7/10.