2 papers
cs.CV2026
Symmetry-Aware Likelihood-Orbit Aggregation for Selective Left-Right Claim Verification
Zhouzhi Xiong, Chuxi Zhang, Weizhen He +3
Frozen vision-language models (VLMs) remain unreliable on fine-grained left-right claims, and raw claim likelihoods need not reliably rank verification errors. After a horizontal-r…
cs.CV2026
DenseScout: Algorithm-System Co-design for Budgeted Tiny Object Selection on Edge Platforms
Zhouzhi Xiong, Zimo Zeng, Yi Chen +3
Deploying high-resolution tiny-object perception on edge platforms requires not only accurate localization, but also selecting a small set of informative patches under compute, tra…