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.
More from Research
- TRL adds Score Centering, a simple fix for RLHF training instability — lvwerra · 2026-10-27
- Latent-Foresight: world models that learn to predict their own future — abursuc · 2026-10-27
- UK AISI papers: no good safeguards yet against misuse of biological AI tools — davidmanheim · 2026-10-27
- CMU's XYBench: LLMs answer queries literally and reinforce user misconceptions — valentina__py · 2026-10-27
- arXiv advice from T. Dietterich: wrong primary category will almost surely get your paper on hold — tdietterich · 2026-10-27
- arXiv has 4,000+ papers on hold amid submission surge; moderator shares how to avoid it — tdietterich · 2026-10-27