cs.CVNov 18, 2026

The Elephant in the Question: Unified Models Picture the Concepts Behind Their Answers

Authors: Tobias Braun, Marcus Rohrbach, Lorenzo Cavallaro

Organizations: Technische Universität Darmstadt · University College London · Mohamed bin Zayed University of Artificial Intelligence

Abstract

Visualizing intermediate representations could help us inspect the reasoning steps underlying a model output. Unified multimodal models offer this opportunity by combining understanding and generation in one architecture. Their image generators can access representations formed while processing text. We introduce the V-lens, which uses this connection to visualize a chosen token's hidden state without training a decoder. Across four diffusion-based and two purely autoregressive unified models, the resulting images reveal key intermediate concepts that connect a question to its answer even when the concepts are never named explicitly. Controlled tests show how this content changes with context, token position, and depth. We then introduce lens tuning, which supervises selected hidden states with pictures through the V-lens. Across BAGEL, SenseNova-U1, and HunyuanImage-3.0, the rate of correct visualizations of pronoun referents rises from 2-11% to 86-94%. Surprisingly, such visual supervision also improves text answers without supervising the answer tokens directly. Code is available at https://github.com/multimodal-ai-lab/V-lens.

Figures & tables

Appendix figures & tables29 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Ask, Solve, Generate: Self-Evolving Unified Multimodal Understanding and Generation via Self-Consistency Rewards

    Jun 25, 2026Ritesh Thawkar, Shravan Venkatraman, Omkar Thawakar +5Unified Multimodal ModelsMultimodal Generation

  2. UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs

    May 12, 2026Houcheng Jiang, Jiajun Fu, Junfeng Fang +4Efficient Multimodal InferenceMultimodal Large Language Models

  3. Pixel is All You Need

    Nov 17, 2026Jie Chu, Haoting Shi, Fucheng Zhang +4Generative ModelingUnified Multimodal Models