livr-visual-reasoning

【设计与创意】Enable richer visual reasoning in multimodal models via learnable latent tokens trained with visual bottlenecking. Introduces special tokens that implicitly learn task-relevant visual abstractions without explicit supervision, through attention masking forcing visual information through latents—improving vision-heavy tasks without task-specific annot…

独立 GitHub 快照 · 自动分类 · 以原作者文档为准