A Heart Means Recursion: Exploring Visual Meaning and Communication in VLMs
Summary
A research paper exploring how vision-language models (VLMs) use and interpret visual symbols, finding that simple visuals like a red heart can implicitly steer model behavior (e.g., toward recursive coding solutions) and that models can develop creative visual communication strategies that diverge from human conventions.
View Cached Full Text
Cached at: 10/28/26, 07:56 AM
# A Heart Means Recursion: Exploring Visual Meaning and Communication in VLMs Source: [https://arxiv.org/abs/2610.36449](https://arxiv.org/abs/2610.36449) [View PDF](https://arxiv.org/pdf/2610.36449)[HTML \(experimental\)](https://arxiv.org/html/2610.36449v1) > Abstract:Do vision\-language models \(VLMs\) share our ability to communicate visually? We share preliminary findings, starting from a surprising observation: simple visual symbols like a red heart can strongly influence model behavior on seemingly unrelated tasks, such as steering models towards recursive solutions on simple coding problems\. Notably, this steering effect is largely implicit, as models' direct interpretations and thinking traces about visual symbols diverge substantially from their observed behavior\. In visual communication between models, this leads to a generation\-\-interpretation gap: while models tend to send shape primitives that they \(and humans\) find intuitive, these visual cues often fail to steer other models\. In further communication games involving abstract concepts and stories, models can creatively use visuals to transmit meaning to one another, although some communications remain non\-intuitive to humans\. These findings reveal that VLMs might be capable of rich, creative, and visually\-grounded communication, but their interpretation and production of visual meaning diverges from human conventions in surprising ways\. Together this work highlights both the promise and challenges of visual communication between humans and VLMs\. ## Submission history From: Alexa Tartaglini \[[view email](https://arxiv.org/show-email/04c2d37b/2610.36449)\] **\[v1\]**Tue, 27 Oct 2026 00:51:17 UTC \(14,761 KB\)
Similar Articles
LoopVL: Recurrent Visual Intelligence
LoopVL extends Loop Transformers to vision-language models, iteratively updating a unified multimodal state through shared modules (Module-Loop and Model-Loop) and outperforming similarly sized non-recurrent models on understanding and reasoning benchmarks, with notable 'Visual Aha Moments' in attention.
Revealing Interpretable Failure Modes of VLMs
This paper introduces Revelio, a framework that systematically discovers interpretable failure modes in Vision-Language Models (VLMs) by searching over discrete concept combinations. Applied to autonomous driving and indoor robotics, it reveals previously unreported vulnerabilities that lead to crashes or safety hazards.
Inside VLM Chart Reading: Tracing Value Reading from Vertical Bar Charts Across Space and Depth
This paper investigates how vision-language models read exact values from vertical bar charts using controlled counterfactual activation patching, revealing insights into internal computations and differences between models like Qwen and InternVL.
Do VLMs Read or Rewrite? On Transcription Faithfulness in Vision-Language Models
This paper reveals that Vision-Language Models often rewrite rather than faithfully transcribe text when encountering perturbations like typos or visual artifacts, introducing the FaithC4 benchmark to evaluate this behavior across multiple models and languages.
Large Vision-Language Models Get Lost in Attention
This research paper analyzes the internal mechanics of Large Vision-Language Models (LVLMs) using information theory, revealing that attention mechanisms may be redundant while Feed-Forward Networks drive semantic innovation. The authors demonstrate that replacing learned attention weights with random values can yield comparable performance, suggesting current models 'get lost in attention'.