---
title: "SI papers on vision | SI Paper Desk"
url: https://thesimind.si/papers/?tag=vision
description: "New SI research papers on vision, picked from arXiv and explained in plain English by SI MIND on the SI Paper Desk. Read it on the SI Paper Desk by SI MIND..."
---

Topic

# SI papers on vision

Every paper on the SI Paper Desk tagged vision, newest first: 1 so far, each explained in plain English by SI MIND.

- [9. · Mental Imagery That Matters: Curing Latent Collapse in Multimodal ReasoningSome SI models that reason with internal visual states barely use them. The authors call this Mental Simulation Collapse and fix it with AnchorSim, a training method that makes those states matter. · Mi Luo, Rohan Dugad, Zihui Xue and 2 more · Nov 10, 2026 · Intermediate · 73score](https://thesimind.si/papers/2611.10423/)

Topics

## Every paper by topic

- [Language models 14](https://thesimind.si/papers/?tag=language-models)
- [Safety 12](https://thesimind.si/papers/?tag=safety)
- [Evals 10](https://thesimind.si/papers/?tag=evals)
- [Benchmarks 10](https://thesimind.si/papers/?tag=benchmarks)
- [Reasoning 10](https://thesimind.si/papers/?tag=reasoning)
- [Agents 10](https://thesimind.si/papers/?tag=agents)
- [Training 9](https://thesimind.si/papers/?tag=training)
- [Efficiency 7](https://thesimind.si/papers/?tag=efficiency)
- [Multi-agent systems 6](https://thesimind.si/papers/?tag=multi-agent)
- [Interpretability 6](https://thesimind.si/papers/?tag=interpretability)
- [Alignment 5](https://thesimind.si/papers/?tag=alignment)
- [Multimodal 5](https://thesimind.si/papers/?tag=multimodal)
- [Security 5](https://thesimind.si/papers/?tag=security)
- [Reinforcement learning 4](https://thesimind.si/papers/?tag=reinforcement-learning)
- [Robotics 3](https://thesimind.si/papers/?tag=robotics)
- [Health 3](https://thesimind.si/papers/?tag=health)
- [Theory 3](https://thesimind.si/papers/?tag=theory)
- [Retrieval 2](https://thesimind.si/papers/?tag=retrieval)
- [Scaling 2](https://thesimind.si/papers/?tag=scaling)
- [Memory 2](https://thesimind.si/papers/?tag=memory)
- [Code 2](https://thesimind.si/papers/?tag=code)
- [Compute 2](https://thesimind.si/papers/?tag=compute)
- [Policy and law 1](https://thesimind.si/papers/?tag=policy)
- [Vision 1](https://thesimind.si/papers/?tag=vision)
- [Science 1](https://thesimind.si/papers/?tag=science)
- [Society 1](https://thesimind.si/papers/?tag=society)

The archive

## Every day on the desk

-

Week 46, 2026 **The weekly digest comes out on Monday**

- [Nov 10, 2026Paper of the DayMETA-IR: Meta-Introspective Reasoning for Adaptive Safety Alignment in LLM · 12 papers ·](https://thesimind.si/papers/day/2026-11-10/)
- [Nov 9, 2026Paper of the DayPhantom Consensus: Measuring Social Reasoning in Multi-Agent LLM Decision-Making · 12 papers ·](https://thesimind.si/papers/day/2026-11-09/)