MUCG workshop on unified multimodal comprehension and generation heads to ECCV 2026

jmin__cho · x · 2026-09-07

The 2nd MUCG workshop (Multimodal LLMs for Unified Comprehension and Generation) takes place September 8, 2026 at ECCV in Malmö, Sweden, featuring 6 keynotes, oral sessions, and posters on unified multimodal intelligence.

Topics span unified multimodal understanding (captioning, VQA, long-video understanding), unified content generation (text-to-image/video, visual editing), joint comprehension-generation architectures (autoregressive, diffusion, flow-based and hybrid paradigms), and synergistic learning across modalities. Submissions are closed.

Original post →

More from Research

Research channel →