SLVR: Structured Latent Visual Reasoning via Human-like Reasoning Flows
cs.CV, cs.AI
Submitted: 2026-10-01
Updated: 2026-10-01
Terminology
Sources
- Qwen2.5-VL Technical Report
- Reasoning in the Dark: Interleaved Vision-Text Reasoning in Latent Space
- Thinking with Generated Images
- SPOT: Span-level Pause-of-Thought for Efficient and Interpretable Latent Reasoning in Large Language Models
- Visually Prompted Benchmarks Are Surprisingly Fragile
- Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
- Thinking with Programming Vision: Towards a Unified View for Thinking with Images
- Training Large Language Models to Reason in a Continuous Latent Space
- GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
- Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space
- Multimodal Chain of Continuous Thought for Latent-Space Reasoning in Vision-Language Models
- Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens
- Mull-Tokens: Modality-Agnostic Latent Thinking
- Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers
- Latent Chain-of-Thought for Visual Reasoning
- Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey
- LaViT: Aligning Latent Visual Thoughts for Multi-modal Reasoning
- Latent Sketchpad: Sketching Visual Thoughts to Elicit Multimodal Reasoning in MLLMs
- Multimodal Latent Reasoning via Hierarchical Visual Cues Injection
- Multimodal Chain-of-Thought Reasoning in Language Models
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