# (How) Do MLLMs Report Bistable Images Like Humans?

arXiv: https://arxiv.org/abs/2609.13254 · HTML: https://mlsanity.com/paper/2609.13254/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 66 references that are in the map.
- First posted on arXiv 6 Sep 2026.

## Builds on (most cited first, 26 of 26)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [Dissecting Recall of Factual Associations in Auto-Regressive Language Models](https://mlsanity.com/paper/2304.14767/) (2023)
- [Mechanistic Interpretability for AI Safety -- A Review](https://mlsanity.com/paper/2404.14082/) (2024)
- [Finding Neurons in a Haystack: Case Studies with Sparse Probing](https://mlsanity.com/paper/2305.01610/) (2023)
- [What does CLIP know about a red circle? Visual prompt engineering for VLMs](https://mlsanity.com/paper/2304.06712/) (2023)
- [ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts](https://mlsanity.com/paper/2312.00784/) (2023)
- [Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens](https://mlsanity.com/paper/2411.16724/) (2024)
- [Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations](https://mlsanity.com/paper/2410.02762/) (2024)
- [From Tokens to Words: On the Inner Lexicon of LLMs](https://mlsanity.com/paper/2410.05864/) (2024)
- [Grounding Visual Illusions in Language: Do Vision-Language Models Perceive Illusions Like Humans?](https://mlsanity.com/paper/2311.00047/) (2023)
- [Pixels Versus Priors: Controlling Knowledge Priors in Vision-Language Models through Visual Counterfacts](https://mlsanity.com/paper/2505.17127/) (2025)
- [Can We Talk Models Into Seeing the World Differently?](https://mlsanity.com/paper/2403.09193/) (2024)
- [How Do Vision-Language Models Process Conflicting Information Across Modalities?](https://mlsanity.com/paper/2507.01790/) (2025)
- [Hallucinatory Image Tokens: A Training-free EAZY Approach on Detecting and Mitigating Object Hallucinations in LVLMs](https://mlsanity.com/paper/2503.07772/) (2025)
- [The Illusion-Illusion: Vision Language Models See Illusions Where There Are None](https://mlsanity.com/paper/2412.18613/) (2024)
- [Understanding Language Prior of LVLMs by Contrasting Chain-of-Embedding](https://mlsanity.com/paper/2509.23050/) (2025)
- [Position: An Inner Interpretability Framework for AI Inspired by Lessons from Cognitive Neuroscience](https://mlsanity.com/paper/2406.01352/) (2024)
- [The Art of Deception: Color Visual Illusions and Diffusion Models](https://mlsanity.com/paper/2412.10122/) (2024)
- [Evaluating Vision-Language Models on Bistable Images](https://mlsanity.com/paper/2405.19423/) (2024)
- [Do Large Vision-Language Models Distinguish between the Actual and Apparent Features of Illusions?](https://mlsanity.com/paper/2506.05765/) (2025)
- [The Perceptual Observatory Characterizing Robustness and Grounding in MLLMs](https://mlsanity.com/paper/2512.15949/) (2025)

## Abstract (arXiv)

Bistable images such as the duck-rabbit are classic stimuli in which one image supports multiple mutually incompatible interpretations, typically reported one at a time in humans. We ask whether multimodal large language models (MLLMs) show similar report behavior and what internal computations support it. Using the LLaVA family, we study two tractable dimensions: modulability, whether reports can be biased by bottom-up visual cues and top-down linguistic priors, and exclusivity, whether responses commit to a single interpretation. We test both on the canonical duck-rabbit and on synthetic Visual Anagrams to mitigate memorization confounds. Behaviorally, both visual and linguistic manipulations systematically shift reports in human-consistent ways, while responses remain predominantly exclusive. Mechanistically, these effects arise from competing image-token representations, distinct pathways for bottom-up and top-down modulation, and a link between exclusive reporting and object-count encoding. Code and data are available at https://github.com/rtakatsky/mllm-bistable-images.