| SenseNova-U1.5: Towards Native Unified Visual Intelligence | ✓ Link | 38.6 | SenseNova-U1.5 (w/ CoT) | 2026-09-10 |
| SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture | ✓ Link | 30.0 | SenseNova-U1-SFT (8BA3B, w/ CoT) | 2026-05-12 |
| InterleaveThinker: Reinforcing Agentic Interleaved Generation | ✓ Link | 30.0 | InterleaveThinker + Qwen-Image-Edit-2511 | 2026-06-11 |
| ThinkRL-Edit: Thinking in Reinforcement Learning for Reasoning-Centric Image Editing | | 29.7 | ThinkRL-Edit | 2026-01-06 |
| Unified Thinker: A General Reasoning Modular Core for Image Generation | | 28.9 | Unified Thinker (Qwen3-VL-8B) with Qwen-Image-Edit | 2026-01-06 |
| Think-Then-Generate: Reasoning-Aware Text-to-Image Diffusion with LLM Encoders | ✓ Link | 23.9 | Qwen-Image-Edit (Think-Then-Generate) | 2026-01-15 |
| Uncovering Understanding-Generation Synergy in Native Unified Multimodal Models: From Representation, Task to System | | 18.88 | Native UMM Synergy: End-to-end UMM | 2026-09-01 |
| EditThinker: Unlocking Iterative Reasoning for Any Image Editor | ✓ Link | 17.8 | Qwen-Image-Edit + EditThinker-8B (extra data) | 2025-12-05 |
| Uni-Edit: Intelligent Editing Is A General Task For Unified Model Tuning | ✓ Link | 17.2 | BAGEL-Uni-Edit (thinking) (extra data) | 2026-05-20 |
| DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing | ✓ Link | 13.3 | DeepGen-1.0 | 2026-02-12 |
| Emerging Properties in Unified Multimodal Pretraining | ✓ Link | 11.9 | BAGEL (w/ Self-CoT) | 2025-05-20 |
| InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing | ✓ Link | 9.4 | InternVL-U (4B, w/ CoT) | 2026-03-10 |