Rethinking Latent Visual Reasoning: Grounding Latent Reasoning in Visual Evidence
cs.CV, cs.CL, cs.LG
Submitted: 2026-09-28
Updated: 2026-09-28
Terminology
Sources
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- Latent Visual States for Efficient Multimodal Reasoning
- HyLaR: Hybrid Latent Reasoning with Decoupled Policy Optimization
- Retrieve, Integrate, and Synthesize: Spatial-Semantic Grounded Latent Visual Reasoning
- Beyond Visual Memory: Mechanistic Diagnostics of Latent Visual Reasoning
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs
- LUT: Latent Utility Training for Visual Reasoning
- DeepLatent: Think with Images via Parallel Latent Visual Reasoning
- Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language Models
- Reason Through the Latent! Making Latent Visual Reasoning Necessary
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Gemma 3 Technical Report
- SwimBird: Eliciting Switchable Reasoning Mode in Hybrid Autoregressive MLLMs
- LanteRn: Latent Visual Structured Reasoning
- What's Holding Back Latent Visual Reasoning?
- Self-Consistent Latent Reasoning: Long Latent Sequence Reasoning for Vision-Language Model
- ReGuLaR: Relation-Grounded Latent Reasoning for Large Vision-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