2 papers
cs.CV2026
Test-time Scaling over Perception: Resolving the Grounding Paradox in Thinking with Images
Zheng Jiang, Yiming Chen, Nan He +4
Recent multimodal large language models (MLLMs) support Thinking with Images, invoking visual tools such as zooming and cropping to inspect image regions during inference. Yet thes…
cs.LG2026
SubFLOT: Submodel Extraction for Efficient and Personalized Federated Learning via Optimal Transport
Zheng Jiang, Nan He, Yiming Chen +1
Federated Learning (FL) enables collaborative model training while preserving data privacy, but its practical deployment is hampered by system and statistical heterogeneity. While…