Decompose, Look, and Reason: Reinforced Latent Reasoning for VLMs

arXiv:2604.07518 · cs.CL · Submitted 2026-04-08 · Read on arXiv

cs.CL

Submitted: 2026-04-08

Updated: 2026-08-30

Terminology

• Benchmark — 16× in this paper · explained in 2 episodes
• Latent Reasoning — 15× in this paper · explained in 2 episodes
• Embeddings — 14× in this paper · explained in 2 episodes
• Grounding — 10× in this paper · explained in 3 episodes
• Multimodal Reasoning — 10× in this paper · explained in 5 episodes
• Visual Grounding — 8× in this paper · explained in 2 episodes
• Alignment — 7× in this paper · explained in 1 episode
• GRPO — 7× in this paper · explained in 6 episodes
• Latent Space — 6× in this paper · explained in 7 episodes
• Verification — 6× in this paper · explained in 2 episodes
• Interpretability — 5× in this paper · explained in 15 episodes
• Latent Visual Reasoning — 5× in this paper · explained in 2 episodes
• Multimodal Chain-of-Thought — 4× in this paper
• Reinforcement Learning — 4× in this paper · explained in 4 episodes
• Spherical Gaussian Latent Policy — 4× in this paper
• Ablation — 3× in this paper · explained in 1 episode
• Accuracy — 3× in this paper · explained in 1 episode
• Active Exploration — 2× in this paper · explained in 2 episodes
• Core — 2× in this paper · explained in 2 episodes
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Latent Representation — 2× in this paper · explained in 2 episodes
• Structured Reasoning — 2× in this paper · explained in 3 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Abstraction — 1× in this paper · explained in 1 episode
• AdamW Optimizer — 1× in this paper · explained in 1 episode
• Chain-of-Thought (CoT) — 1× in this paper · explained in 4 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Feature Extraction — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• LoRA Fine-Tuning — 1× in this paper · explained in 3 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Reward Function — 1× in this paper · explained in 2 episodes
• Vision-Language Models (VLMs) — 1× in this paper · explained in 6 episodes

Sources

• Latent Visual Reasoning
• MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
• Qwen3-VL Technical Report
• ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning
• Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers
• Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
• VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning
• Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning
• Monet: Reasoning in Latent Visual Space Beyond Images and Language
• Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey
• Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning
• Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens
• Multimodal Chain-of-Thought Reasoning in Language Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering