Oddin: Latent Visual Reasoning in Unified Multimodal Models via Self-Distillation from Image Generation
Unified large multimodal models (ULMMs) are able to perform visual reasoning through interleaved text-image generation, but generating explicit intermediate images incurs significant computational overhead.
By Jaeyong Ko, Hankyeol Kim, Pilsung KangarXiv - cs.CV (CV)
Read the full story
Originally published by arXiv - cs.CV (CV) on Oct 27, 2026.
Comments
Sign in to join the discussion.