New paper on Native Unified Multimodal Models
liuziwei7 · x · 2026-09-02
Ziwei Liu shares a new paper on "Native Unified Multimodal Models." The research uncovers the synergy between understanding and generation in these models.
More from Multimodal
- Runway unveils Solaris, an interface world model that generates interactive UIs in real time — aigclink · 2026-09-02
- Runway's Solaris world model renders interactive UIs frame by frame, no code needed — aigclink · 2026-09-02
- Fable 5.1 generation: High-fidelity "Planet Endor" showcase — petergyang · 2026-09-02
- H3-World: Turning Video Generators into Interactive World Models — Danze Chen · 2026-09-02
- Opus 5 Generates Speaking Video with Matched Facial Expressions — repligate · 2026-09-02
- You can distill consistent surface meshes from the Atlas world model — MatthewChang · 2026-09-02