# Interleaved Latent Visual Reasoning with Selective Perceptual Modeling

arXiv: https://arxiv.org/abs/2512.05665 · HTML: https://mlsanity.com/paper/2512.05665/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 0 of its 30 references that are in the map.
- First posted on arXiv 5 Dec 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Built on by (most cited first, 30 of 33)

- [Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception](https://mlsanity.com/paper/2602.11858/) (2026)
- [The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook](https://mlsanity.com/paper/2604.02029/) (2026)
- [Forest Before Trees: Latent Superposition for Efficient Visual Reasoning](https://mlsanity.com/paper/2601.06803/) (2026)
- [FutureVLA: Joint Visuomotor Prediction for Vision-Language-Action Model](https://mlsanity.com/paper/2603.10712/) (2026)
- [Step-wise Rubric Rewards for LLM Reasoning](https://mlsanity.com/paper/2605.17291/) (2026)
- [Imagination Helps Visual Reasoning, But Not Yet in Latent Space](https://mlsanity.com/paper/2602.22766/) (2026)
- [Show, Don't Tell: Morphing Latent Reasoning into Image Generation](https://mlsanity.com/paper/2602.02227/) (2026)
- [What's Holding Back Latent Visual Reasoning?](https://mlsanity.com/paper/2605.18445/) (2026)
- [VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning](https://mlsanity.com/paper/2608.26105/) (2026)
- [Grouter: Decoupling Routing from Representation for Accelerated MoE Training](https://mlsanity.com/paper/2603.06626/) (2026)
- [Walk the Talk: Bridging the Reasoning-Action Gap for Thinking with Images via Multimodal Agentic Policy Optimization](https://mlsanity.com/paper/2604.06777/) (2026)
- [Beyond Visual Memory: Mechanistic Diagnostics of Latent Visual Reasoning](https://mlsanity.com/paper/2606.01287/) (2026)
- [MedMCP-Calc: Benchmarking LLMs for Realistic Medical Calculator Scenarios via MCP Integration](https://mlsanity.com/paper/2601.23049/) (2026)
- [Leveraging Error Diversity in Group Rollouts for Reinforcement Learning](https://mlsanity.com/paper/2605.17333/) (2026)
- [ProLaViT: Learning Progressive Latent Visual Thoughts in Structured Latent Space](https://mlsanity.com/paper/2607.02907/) (2026)
- [ReGuLaR: Relation-Grounded Latent Reasoning for Large Vision-Language Models](https://mlsanity.com/paper/2605.30587/) (2026)
- [Dual Attention Guided Defense Against Malicious Edits](https://mlsanity.com/paper/2512.14333/) (2025)
- [Segment-Level Attribution for Selective Learning of Long Reasoning Traces](https://mlsanity.com/paper/2602.00425/) (2026)
- [DeepLatent: Think with Images via Parallel Latent Visual Reasoning](https://mlsanity.com/paper/2606.00562/) (2026)
- [Cosine Misleads: Auxiliary Losses Reshape Vision Language Models, Not Their Latents](https://mlsanity.com/paper/2606.05753/) (2026)
- [GLaQ: Grounding Latent Queries in Visual Evidence for Multimodal Reasoning](https://mlsanity.com/paper/2608.15517/) (2026)
- [RACANet: Reliability-Aware Crowd Anchor Network for RGB-T Crowd Counting](https://mlsanity.com/paper/2604.24543/) (2026)
- [VideoLatent: Video-Language Learning via Latent Self-Forcing](https://mlsanity.com/paper/2606.22870/) (2026)
- [Parallelized Autoregressive Decoding for Omni-Modal Dense Video Captioning](https://mlsanity.com/paper/2607.02963/) (2026)
- [MARS-RA: Rank Aggregation for Credit Assignment via Multimodal Comparisons in Embodied Multi-Agent Cooperation](https://mlsanity.com/paper/2607.27967/) (2026)
- [Perception Before Reasoning: Dynamic Latent Reasoning for Video Understanding and Question Answering](https://mlsanity.com/paper/2608.04124/) (2026)
- [Circuit-MLLM: Topological Logic-Guided Latent-Space Visual Reasoning for Circuit Schematic Understanding](https://mlsanity.com/paper/2609.15668/) (2026)
- [Uni-LaDiR: Latent Diffusion Unifies Multimodal Reasoning](https://mlsanity.com/paper/2609.19878/) (2026)
- [Distilling Visual Reasoning into Text Space](https://mlsanity.com/paper/2609.34408/) (2026)
- [Rethinking Latent Visual Reasoning: Grounding Latent Reasoning in Visual Evidence](https://mlsanity.com/paper/2609.34563/) (2026)

## Abstract (arXiv)

Interleaved reasoning paradigms enhance Multimodal Large Language Models (MLLMs) with visual feedback but are hindered by the prohibitive computational cost of re-encoding pixel-dense images. A promising alternative, latent visual reasoning, circumvents this bottleneck yet faces limitations: methods either fail to capture intermediate state evolution due to single-step, non-interleaved structures, or sacrifice precise perceptual modeling by over-compressing features. We introduce Interleaved Latent Visual Reasoning (ILVR), a framework that unifies dynamic state evolution with precise perceptual modeling. ILVR interleaves textual generation with latent visual representations that act as specific, evolving cues for subsequent reasoning. Specifically, we employ a self-supervision strategy where a momentum teacher model selectively distills relevant features from ground-truth intermediate images into sparse supervision targets. This adaptive selection mechanism guides the model to autonomously generate context-aware visual signals. Extensive experiments on multimodal reasoning benchmarks demonstrate that ILVR outperforms existing approaches, effectively bridging the gap between fine-grained perception and sequential multimodal reasoning. The code is available at https://github.com/XD111ds/ILVR.