| Region-Level Policy Optimization for Fine-grained MLLM Perception | ✓ Link | 95.3 | Vision-RL² (Qwen3.5-9B) | 2026-09-17 |
| FOCUS: Internal MLLM Representations for Efficient Fine-Grained Visual Question Answering | | 92.15 | LLaVA-OneVision7B w. FOCUS | 2025-06-25 |
| Zooming without Zooming v2: From Seeing Details to Connecting Evidence for Generalizable Multimodal Perception | ✓ Link | 91.62 | ZwZ2-27B | 2026-10-27 |
| Self-Supervised Visual On-Policy Distillation | | 91.48 | S^2VOPD (Qwen3.5-4B, FineVision-12K) (extra data) | 2026-08-14 |
| From Illusion to Intention: Visual Rationale Learning for Reliable Evidence Acquisition | | 90.8 | ViRL 4B | 2026-09-08 |
| Scaffolding Minds: Optimizing Latent Visual Target Representations for Multimodal Reasoning | | 90.6 | Scaffolding Encoder+RL | 2026-09-29 |
| ZoomEye: Enhancing Multimodal LLMs with Human-Like Zooming Capabilities through Tree-Based Image Exploration | ✓ Link | 90.58 | LLaVA-OneVision7B w. ZoomEye | 2024-11-25 |
| Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders | ✓ Link | 90.1 | Penguin-VL 8B | 2026-03-06 |
| Vero: An Open RL Recipe for General Visual Reasoning | ✓ Link | 89.5 | Vero-Qwen3I-8B | 2026-04-06 |
| Step-GUI Technical Report | ✓ Link | 89.0 | Step-GUI-8B | 2025-12-17 |
| Learning Active Perception for Pixel-Space Reasoning via Visual-Intent Stratified GRPO | | 88.5 | VIS-GRPO | 2026-09-08 |
| Xiaomi-Lens-0 Technical Report | ✓ Link | 87.4 | Xiaomi-Lens-0 | 2026-10-16 |
| LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence | ✓ Link | 85.9 | LLaVA-OneVision-2 (8B) | 2026-05-25 |
| Starve to Perceive: Taming Lazy Perception in VLMs with Constrained Visual Bandwidth | | 85.86 | Starve to Perceive | 2026-05-18 |
| SwimBird: Eliciting Switchable Reasoning Mode in Hybrid Autoregressive MLLMs | ✓ Link | 85.5 | SwimBird | 2026-02-05 |
| Visual Para-Thinker: Divide-and-Conquer Reasoning for Visual Comprehension | ✓ Link | 85.4 | Visual Para-Thinker-7B | 2026-02-10 |
| VisReflect: Latent Visual Reflection for Fine-Grained Perception in Long Visual Context | ✓ Link | 84.9 | VisReflect-7B-Image | 2026-06-29 |
| VisionLeaf: Entropy-Guided Leaf-First Reasoning for Efficient and Accurate Think-with-Image | | 84.8 | VisionLeaf (7B) | 2026-06-03 |
| Monet: Reasoning in Latent Visual Space Beyond Images and Language | ✓ Link | 83.25 | Monet-7B | 2025-11-26 |
| Innovator-VL: A Multimodal Large Language Model for Scientific Discovery | ✓ Link | 81.68 | Innovator-VL (8B-Thinking) | 2026-01-27 |
| Instruction-Guided Visual Masking | ✓ Link | 81.2 | IVM-Enhanced GPT4-V | 2024-05-30 |
| Reason Through the Latent! Making Latent Visual Reasoning Necessary | ✓ Link | 81.2 | CVRR (Qwen2.5-VL-7B) | 2026-09-06 |
| ProLaViT: Learning Progressive Latent Visual Thoughts in Structured Latent Space | ✓ Link | 80.11 | ProLaViT (Full) | 2026-07-03 |
| V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs | ✓ Link | 75.39 | SEAL | 2023-12-21 |
| Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders | ✓ Link | 74.9 | Penguin-VL 2B | 2026-03-06 |
| LLaVA-OneVision: Easy Visual Task Transfer | ✓ Link | 74.46 | LLaVA-OneVision7B | 2024-08-06 |
| PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models | ✓ Link | 73.3 | PerceptionDLM-Base (8B) | 2026-06-17 |
| Visual Para-Thinker: Divide-and-Conquer Reasoning for Visual Comprehension | ✓ Link | 72.6 | Visual Para-Thinker-3B | 2026-02-10 |
| Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMs | ✓ Link | 71.2 | AwaRes | 2026-03-14 |
| Kwai Keye-VL Technical Report | ✓ Link | 69.6 | Keye-VL-8B | 2025-07-02 |
| Seeing What Matters: A Training-Free Self-Guided Framework for Multimodal Detail Perception and Reasoning | | 61.78 | SLoFo high-res | 2026-06-03 |