Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
VISTA: Internalizing Collective Visual Experience via On-Policy Distillation for Active Multimodal Agents
Zheng Jiang, Houde Qian, Yiming Chen +5
Active multimodal agents use visual tools to acquire task-relevant evidence while reasoning. Although reinforcement learning samples multiple interaction trajectories per input, ou…
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…