| Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding | ✓ Link | 83.1 | Lumina-DiMOO | 2025-10-07 |
| LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning | ✓ Link | 82.9 | LLaDA-V | 2025-05-22 |
| Reinforcement Learning for Multimodal Diffusion Language Models via Bidimensional Trajectory and Thought Optimization | | 81.1 | LLaDA-V + Bi-VRL (ours) | 2026-09-08 |
| PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding | ✓ Link | 79.3 | PLM-8B | 2025-04-17 |
| PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models | ✓ Link | 78.9 | PerceptionDLM-Base (8B) | 2026-06-17 |
| LLaVA-OneVision: Easy Visual Task Transfer | ✓ Link | 78.0 | LLaVA-OneVision-72B | 2024-08-06 |
| MetaphorStar: Image Metaphor Understanding and Reasoning with End-to-End Visual Reinforcement Learning | ✓ Link | 77.6 | MetaphorStar-32B | 2026-02-11 |
| BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset | ✓ Link | 77.5 | BLIP3-o (8B) | 2025-05-14 |
| CoLT: Teaching Multi-Modal Models to Think with Chain of Latent Thoughts | ✓ Link | 77.5 | CoLT | 2026-06-30 |
| From Pixels to Words -- Towards Native One-Vision Models at Scale | ✓ Link | 76.6 | NEO-ov 9B | 2026-05-27 |
| LFM2 Technical Report | ✓ Link | 76.55 | LFM2-VL-3B | 2025-11-28 |
| Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbone | ✓ Link | 76.4 | Dream-VL | 2025-12-27 |
| LatentUM: Unleashing the Potential of Interleaved Cross-Modal Reasoning via a Latent-Space Unified Model | ✓ Link | 76.3 | LatentUM (Base) | 2026-04-02 |
| LLaVA-NeXT: Improved reasoning, OCR, and world knowledge | ✓ Link | 75.9 | LLaVA-NeXT-34B | 2024-01-30 |
| Perceptio: Perception Enhanced Vision Language Models via Spatial Token Generation | | 75.7 | Perceptio (8B) | 2026-03-19 |
| FastVLM: Efficient Vision Encoding for Vision Language Models | ✓ Link | 75.4 | FastVLM-7B | 2024-12-17 |
| Innovator-VL: A Multimodal Large Language Model for Scientific Discovery | ✓ Link | 73.84 | Innovator-VL (8B-Instruct) | 2026-01-27 |
| ARM: An AutoRegressive Large Multimodal Model with Unified Discrete Representations | ✓ Link | 73.1 | ARM-7B | 2026-06-09 |
| Multimodal Autoregressive Pre-training of Large Vision Encoders | ✓ Link | 72.9 | AIMv2 ViT-3B/14 + Llama 3.0 8B | 2024-11-21 |
| ZAYA1-VL-8B Technical Report | ✓ Link | 72.7 | ZAYA1-VL-8B | 2026-05-08 |
| Program-Verified Self-Evolution for Vision-Language Models | ✓ Link | 72.61 | VQS-2B (Qwen3-VL-2B-Instruct) | 2026-09-27 |
| Falcon2-11B Technical Report | | 72.3 | Falcon2-11B VLM | 2024-07-20 |
| Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling | ✓ Link | 72.1 | Janus-Pro-7B | 2025-01-29 |
| Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation | ✓ Link | 71.7 | Cheers (1.5B) | 2026-03-13 |
| DeepSeek-VL: Towards Real-World Vision-Language Understanding | ✓ Link | 70.4 | DeepSeek-VL 7B Chat | 2024-03-08 |
| Conical Visual Concentration for Efficient Large Vision-Language Models | | 70.3 | PyramidDrop (LLaVA-NeXT-7B, 9 patches, trained) | 2025-06-11 |
| VisionTrim: Unified Vision Token Compression for Training-Free MLLM Acceleration | ✓ Link | 70.2 | VisionTrim (Qwen2.5-VL-7B) | 2026-01-30 |
| Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders | ✓ Link | 69.8 | RAE (SigLIP-2) | 2026-01-22 |
| Mobile-O: Unified Multimodal Understanding and Generation on Mobile Device | ✓ Link | 69.4 | Mobile-O-0.5B | 2026-02-23 |
| Emu3: Next-Token Prediction is All You Need | ✓ Link | 68.2 | Emu3 | 2024-09-27 |
| OpenVision 3: A Family of Unified Visual Encoder for Both Understanding and Generation | | 66.0 | OpenVision 3 (VAE + L/2) | 2026-01-21 |
| Accelerating Multimodal Large Language Models with Prior-Corrected Token Reduction | ✓ Link | 64.8 | PriorTR (LLaVA-1.5-7B, 192 tokens) | 2026-06-23 |
| Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation | ✓ Link | 63.7 | Janus | 2024-10-17 |
| ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts | ✓ Link | 62.9 | ViP-LLaVA-13B | 2023-12-01 |
| Low-Rank Approximation for Sparse Attention in Multi-Modal LLMs | | 58.8 | LoRA-Sparse (Vicuna-7B) (extra data) | 2024-06-17 |