Story

arxiv_cs_lg ยท Nov 14, 2026 ยท paper

Source brief

LogT: Logically Think with Images for Visual Search

arxiv.orgNov 14, 2026
original source linked

In brief

Thinking with images empowers vision-language models (VLMs) to use an external Zoom-in tool for fine-grained visual search. Recent works employ supervised fine-tuning (SFT) and reinforcement learning (RL) with tool-sp...

Feed lens
eval

Continue reading

Read the original at arxiv.org โ†’Open in live feedRead that dayโ€™s brief

Earlier in this thread 4 items