ZoomGain: Mining Global-to-Zoom Perception Gaps for Fine-Grained Visual Supervision
cs.CV, cs.AI
Submitted: 2026-11-10
Updated: 2026-11-10
Code: https://github.com/inclusionAI/ZoomGain
Terminology
Sources
- Qwen3-VL Technical Report
- BabyVision: Visual Reasoning Beyond Language
- STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Dataset
- Meta CLIP 2: A Worldwide Scaling Recipe
- GLM-5: from Vibe Coding to Agentic Engineering
- Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search
- Visual-OPSD: Cross-Modal On-Policy Self-Distillation for Efficient Unified Multimodal Reasoning
- PerceptionBench: Evaluating Atomic Visual Perception in Multimodal Large Language Models
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Kimi K3: Open Frontier Intelligence
- Kimi K2.5: Visual Agentic Intelligence
- GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
- Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology
- Retrieval-Augmented Perception: High-Resolution Image Perception Meets Visual RAG
- Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception
- V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs
- MiMo-VL Technical Report
- Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation
- VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy Distillation
- MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs