What's Holding Back Latent Visual Reasoning?
cs.CV, cs.AI, cs.CL, cs.LG
Submitted: 2026-05-18
Updated: 2026-11-07
Terminology
Sources
- Qwen3-VL Technical Report
- Reasoning in the Dark: Interleaved Vision-Text Reasoning in Latent Space
- Interleaved Latent Visual Reasoning with Selective Perceptual Modeling
- BLINK: Multimodal Large Language Models Can See but Not Perceive
- Training Large Language Models to Reason in a Continuous Latent Space
- Vision-aligned Latent Reasoning for Multi-modal Large Language Model
- Latent Visual Reasoning
- LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning?
- GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
- LanteRn: Latent Visual Structured Reasoning
- Monet: Reasoning in Latent Visual Space Beyond Images and Language
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- Forest Before Trees: Latent Superposition for Efficient Visual Reasoning
- V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs
- VSP: Assessing the dual challenges of perception and reasoning in spatial planning tasks for VLMs
- VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models
- Do Latent Tokens Think? A Causal and Adversarial Analysis of Chain-of-Continuous-Thought
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