Gaze Attention groups visual embeddings into selectable regions and dynamically restricts attention to task-relevant ones, matching dense baselines with up to 90% fewer visual KV entries via added context tokens.
Robotics: Science and Systems (RSS) , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
DyGRO-VLA is a two-stage optimization framework for cross-task scaling of Vision-Language-Action models via dynamic grouped residual optimization in RL.
citing papers explorer
-
Learning to See What You Need: Gaze Attention for Multimodal Large Language Models
Gaze Attention groups visual embeddings into selectable regions and dynamically restricts attention to task-relevant ones, matching dense baselines with up to 90% fewer visual KV entries via added context tokens.
-
DyGRO-VLA: Cross-Task Scaling of Vision-Language-Action Models via Dynamic Grouped Residual Optimization
DyGRO-VLA is a two-stage optimization framework for cross-task scaling of Vision-Language-Action models via dynamic grouped residual optimization in RL.