Attention Maps Know When to Think: Training-Free Difficulty-Aware Chain-of-Thought for Reasoning Segmentation
cs.CV, cs.AI
Submitted: 2026-10-30
Updated: 2026-10-30
Comments: Accepted to WACV 2027
Code: https://github.com/chanseul01/DA-CoT
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- SAM 3: Segment Anything with Concepts
- GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
- SAM-R1: Leveraging SAM for Reward Feedback in Multimodal Segmentation via Reinforcement Learning
- Think Before You Segment: High-Quality Reasoning Segmentation with GPT Chain of Thoughts
- Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement
- VisionReasoner: Unified Reasoning-Integrated Visual Perception via Reinforcement Learning
- RSVP: Reasoning Segmentation via Visual Prompting and Multi-modal Chain-of-Thought
- Ref-Diff: Zero-shot Referring Image Segmentation with Generative Models
- SAM 2: Segment Anything in Images and Videos
- Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks
- To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning
- How Multimodal LLMs Solve Image Tasks: A Lens on Visual Grounding, Task Reasoning, and Answer Decoding
- MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs
- Multimodal Chain-of-Thought Reasoning in Language Models
- Least-to-Most Prompting Enables Complex Reasoning in Large Language Models
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