ReMAP: Restoring the Perceptual Cycle with Reasoning-Time Latent Visual Memory

cs.CV, cs.AI, cs.CL

Submitted: 2026-10-04

Updated: 2026-10-04

Comments: 32 pages. Code coming soon

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Qwen2.5-VL Technical Report
• Show, Don't Tell: Morphing Latent Reasoning into Image Generation
• Qwen Look Again: Guiding Vision-Language Reasoning Models to Re-attention Visual Information
• VTPerception-R1: Enhancing Multimodal Reasoning via Explicit Visual and Textual Perceptual Grounding
• LoRA: Low-Rank Adaptation of Large Language Models
• Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs
• Vision-aligned Latent Reasoning for Multi-modal Large Language Model
• VLM-R$^3$: Region Recognition, Reasoning, and Refinement for Enhanced Multimodal Chain-of-Thought
• UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs
• Toward Cognitive Supersensing in Multimodal Large Language Model
• LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models
• Rethinking Token-Level Policy Optimization for Multimodal Chain-of-Thought
• More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models
• ReGround: Restoring Visual Grounding in Multi-Step Reasoning through Self-Diagnosis and Visual Re-Examination
• Multimodal Chain of Continuous Thought for Latent-Space Reasoning in Vision-Language Models
• Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Catching the Details: Self-Distilled RoI Predictors for Fine-Grained MLLM Perception
• Q-Zoom: Query-Aware Adaptive Perception for Efficient Multimodal Large Language Models
• Mastering Complex Control in MOBA Games with Deep Reinforcement Learning

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