Distilling Visual Reasoning into Text Space
cs.CV
Submitted: 2026-09-28
Updated: 2026-09-28
Terminology
Sources
- Qwen2.5-VL Technical Report
- SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models
- Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas
- MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning
- Interleaved Latent Visual Reasoning with Selective Perceptual Modeling
- PromptCap: Prompt-Guided Task-Aware Image Captioning
- Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
- VisualToolAgent (VisTA): A Reinforcement Learning Framework for Visual Tool Selection
- Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning
- Latent Visual Reasoning
- Imagine while Reasoning in Space: Multimodal Visualization-of-Thought
- Visual-OPSD: Cross-Modal On-Policy Self-Distillation for Efficient Unified Multimodal Reasoning
- Look Less, Reason More: Rollout-Guided Adaptive Pixel-Space Reasoning
- On the Faithfulness of Visual Thinking: Measurement and Enhancement
- MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
- GPT-4o System Card
- CogCoM: A Visual Language Model with Chain-of-Manipulations Reasoning
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning
- OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models