BeClaude
Research2026-05-14

Seg-Agent: Test-Time Multimodal Reasoning for Training-Free Language-Guided Segmentation

Source: Arxiv CS.AI

arXiv:2605.12953v1 Announce Type: cross Abstract: Language-guided segmentation transcends the scope limitations of traditional semantic segmentation, enabling models to segment arbitrary target regions based on natural language instructions. Existing approaches typically adopt a two-stage...

arxivpapersreasoningagentsmultimodal