| RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time | ✓ Link | 8.33 | | | Qwen-Image-Edit with Prompt Tuning (RationalRewards 8B) | 2026-04-13 |
| SenseNova-U1.5: Towards Native Unified Visual Intelligence | ✓ Link | 8.3 | | | SenseNova-U1.5-8B-MoT | 2026-09-10 |
| Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation | ✓ Link | 8.290 | | | JoyAI-Image-Edit (w/ PE) | 2026-05-05 |
| Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing | ✓ Link | 8.271 | | | Mage-Flow-Edit-Turbo | 2026-07-21 |
| FireRed-Image-Edit-1.0 Techinical Report | ✓ Link | 7.943 | | | FireRed-Image-Edit-1.0 | 2026-02-12 |
| NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation | ✓ Link | 7.87 | | | NextFlow RL | 2026-01-05 |
| Auto-Rubric as Reward: From Implicit Preferences to Explicit Multimodal Generative Criteria | ✓ Link | 7.85 | | | ARR-RPO (Gemini 3.1 Pro-ARR) | 2026-05-08 |
| Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback | ✓ Link | 7.83 | | | UniWorld-V2 | 2025-10-19 |
| REASONEDIT: Towards Reasoning-Enhanced Image Editing Models | ✓ Link | 7.77 | | | ReasonEdit-Q (thinking + reflection) | 2025-11-27 |
| RegionE: Adaptive Region-Aware Generation for Efficient Image Editing | ✓ Link | 7.731 | | | Qwen-Image-Edit + RegionE | 2025-10-29 |
| EditThinker: Unlocking Iterative Reasoning for Any Image Editor | ✓ Link | 7.73 | | | Qwen-Image-Edit + EditThinker-8B (extra data) | 2025-12-05 |
| LongCat-Image Technical Report | ✓ Link | 7.64 | | | LongCat-Image-Edit | 2025-12-08 |
| Emu3.5: Native Multimodal Models are World Learners | ✓ Link | 7.59 | | | Emu3.5 (34B, AR) | 2025-10-30 |
| Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer | ✓ Link | 7.57 | | | Z-Image-Edit | 2025-11-27 |
| Qwen-Image Technical Report | ✓ Link | 7.56 | | | Qwen-Image-Edit | 2025-08-04 |
| SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing | ✓ Link | 7.52 | | | SpatialEdit | 2026-04-06 |
| SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture | ✓ Link | 7.47 | | | SenseNova-U1-8B-MoT | 2026-05-12 |
| UniSpace: Unified Visual Representation and Scalable Multimodal Modeling | ✓ Link | 7.407 | | | UniSpace | 2026-08-09 |
| Lance: Unified Multimodal Modeling by Multi-Task Synergy | ✓ Link | 7.3 | | | Lance (3B) | 2026-05-18 |
| TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models | ✓ Link | 7.29 | | | Tuna | 2025-12-01 |
| DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing | ✓ Link | 7.17 | | | DeepGen-1.0 | 2026-02-12 |
| Steering Visual Generation in Unified Multimodal Models with Understanding Supervision | | 7.17 | | | BAGEL-7B (UNO) | 2026-05-07 |
| NoHumansRequired: Autonomous High-Quality Image Editing Triplet Mining | | 7.12 | 6.88 | 8.07 | BAGEL-NHR-EDIT | 2025-07-18 |
| AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward | ✓ Link | 7.08 | | | AlphaGRPO | 2026-05-12 |
| Semantic Generative Tuning for Unified Multimodal Models | ✓ Link | 6.94 | | | SGT-BAGEL (7B+7B) | 2026-05-18 |
| InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing | ✓ Link | 6.88 | | | InternVL-U (4B, w/ CoT) | 2026-03-10 |
| VIBE: Visual Instruction Based Editor | ✓ Link | 6.81 | | | VIBE | 2026-01-05 |
| Step1X-Edit: A Practical Framework for General Image Editing | ✓ Link | 6.70 | 6.76 | 7.09 | Step1X-Edit | 2025-04-24 |
| ARM: An AutoRegressive Large Multimodal Model with Unified Discrete Representations | ✓ Link | 6.68 | | | ARM-7B | 2026-06-09 |
| LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model | ✓ Link | 6.61 | | | LLaDA2.0-Uni (16B) | 2026-04-22 |
| Intern Lumina U2: A Multi-Codebook Diffusion Large Language Model for Omni-Visual Understanding and Image Generation | ✓ Link | 6.54 | | | Intern Lumina U2 (NVIDIA) | 2026-10-14 |
| Emerging Properties in Unified Multimodal Pretraining | ✓ Link | 6.52 | 6.83 | 7.36 | BAGEL | 2025-05-20 |
| OmniGen2: Towards Instruction-Aligned Multimodal Generation | ✓ Link | 6.41 | | | OmniGen2 | 2025-06-23 |
| Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generation | ✓ Link | 5.83 | | | Skywork UniPic | 2025-08-05 |