2 papers
cs.CL2026
Compound interpretation is based on analogy
Tian Shen, Harald Baayen
How compound meanings are best predicted from constituent meanings remains a central question in computational models of lexical semantics. Comparing different computational models…
cs.RO2026
CometVLA: Co-Training on an Embodied Data Pyramid towards Physical Understanding
Hanwen Wan, Dafeng Chi, Linbo Zhai +6
Vision-language-action (VLA) models remain brittle in manipulation tasks that require physical commonsense. Current physical VQA data is typically disembodied and misaligned with r…