Agency for Science, Technology and Research

Vision-language-action policies process hundreds of visual tokens per step, which drives up inference latency. APS-VLA keeps the backbone frozen and uses a lightweight scorer conditioned on the current observation, instruction and proprioception to pick tokens, training the retained representation both to reproduce policy outputs and to predict the subsequent visual change. On LIBERO with 128 tokens retained, mean success is 95.75%, 1.25 points below the unpruned 97.00%, and inference latency falls to 68.75 ms.

Vision-language-action policies process hundreds of visual tokens per step, which drives up inference latency. APS-VLA keeps the backbone frozen and uses a lightweight scorer conditioned on the current observation, instruction and proprioception to pick tokens, training the retained representation both to reproduce policy outputs and to predict the subsequent visual change. On LIBERO with 128 tokens retained, mean success is 95.75%, 1.25 points below the unpruned 97.00%, and inference latency falls to 68.75 ms.

Cross-modal retinal image rigid registration has largely relied on a two-step pipeline that segments vessels first and detects keypoints second, so registration quality is capped by segmentation accuracy. The MICRO benchmark gathers 1,365 cross-modal retinal image pairs spanning preoperative, intraoperative and postoperative surgery phases, each with expert-annotated control points. Built on that benchmark, the one-step OFS2Reg constructs keypoint topology constraints directly through a frequency-guided structure preservation descriptor and cross-modal vessel structure similarity learning, reaching a 0.784 success rate and 5.08-pixel RMSE on the MICRO-pre subset.

Cross-modal retinal image rigid registration has largely relied on a two-step pipeline that segments vessels first and detects keypoints second, so registration quality is capped by segmentation accuracy. The MICRO benchmark gathers 1,365 cross-modal retinal image pairs spanning preoperative, intraoperative and postoperative surgery phases, each with expert-annotated control points. Built on that benchmark, the one-step OFS2Reg constructs keypoint topology constraints directly through a frequency-guided structure preservation descriptor and cross-modal vessel structure similarity learning, reaching a 0.784 success rate and 5.08-pixel RMSE on the MICRO-pre subset.

Medical imaging foundation models have traded generality against pixel-level precision, and most return a label without evidence. EVLF-FM feeds both disease-level and pixel-level visual features into a language model, first with supervised fine-tuning and then with reinforcement learning on verifiable rewards, spanning six specialties and 10 imaging modalities. On internal diagnostic validation it reached the highest mean accuracy among evaluated models, 0.895, and averaged 0.842 Acc@0.5 for medical visual grounding across nine modalities.

Medical imaging foundation models have traded generality against pixel-level precision, and most return a label without evidence. EVLF-FM feeds both disease-level and pixel-level visual features into a language model, first with supervised fine-tuning and then with reinforcement learning on verifiable rewards, spanning six specialties and 10 imaging modalities. On internal diagnostic validation it reached the highest mean accuracy among evaluated models, 0.895, and averaged 0.842 Acc@0.5 for medical visual grounding across nine modalities.

The authors introduce Ego2World, a benchmark that compiles annotated cooking activities into executable planning environments under partial observation, linking source steps and objects to symbolic action rules, persistent world states, and explicit task conditions while maintaining world state and agent belief separately; evaluating six planners on 105 tasks shows accepted operations often leave task goals unmet, and execution traces and condition checks distinguish interrupted runs, partial attainment, and completed execution without goal attainment; in a separate paired Qwen-Plus study, persistent belief improves action validity by 4.15 percentage points and reduces visual-query attempts by 90.27%, with higher token use and no detected completion gain.

The authors introduce Ego2World, a benchmark that compiles annotated cooking activities into executable planning environments under partial observation, linking source steps and objects to symbolic action rules, persistent world states, and explicit task conditions while maintaining world state and agent belief separately; evaluating six planners on 105 tasks shows accepted operations often leave task goals unmet, and execution traces and condition checks distinguish interrupted runs, partial attainment, and completed execution without goal attainment; in a separate paired Qwen-Plus study, persistent belief improves action validity by 4.15 percentage points and reduces visual-query attempts by 90.27%, with higher token use and no detected completion gain.