Latent Implicit Visual Reasoning 文章

ArXiv CS.CV2026-06-05NEWSen作者: Kelvin Li, Chuyi Shang, Leonid Karlinsky, Rogerio Feris, Trevor Darrell, Roei Herzig

摘要

arXiv:2512.21218v2 Announce Type: replace Abstract: While Large Multimodal Models (LMMs) have made significant progress, they remain largely text-centric, relying on language as their core reasoning modality. As a result, they are limited in their ability to handle reasoning tasks that are predominantly visual. Recent approaches have sought to address this by supervising intermediate visual steps with helper images, depth maps, or image crops. However, these strategies impose restrictive priors on what "useful" visual abstractions look like, add heavy annotation costs, and struggle to generalize across tasks. To address this critical limitation, we propose Latent Implicit Visual Reasoning (LIVR), a task-agnostic mechanism that trains LMMs to discover and use latent visual reasoning tokens without explicit intermediate supervision.

相关事件查看全部 (1)

Latent Implicit Visual Reasoning
2026-06-05PRODUCT_LAUNCH影响: MEDIUM

相关公司

暂无数据

相关人物

暂无数据