cs.AINov 11, 2026

Emergent Vision-Shaped Thinking in Text-Only Reasoning through Multimodal Training

Authors: Qi Zhang, Bohan Wang, Qianru Sun, Hanwang Zhang

Organizations: Nanyang Technological University · Singapore Management University

Abstract

Does multimodal training shape how a language model thinks, even when the input is text only? We test this with targeted causal ablations across 10 multimodal configurations from 6 model families, with matched text-only backbones and cross-family transfer controls. We contrast spatial-imagery tasks that invite mental scene construction with symbol-manipulation tasks solvable by symbolic rules alone. We identify a vision-language axis in hidden-state space and ablate its projection at inference. In Chameleon-7B, this ablation drops accuracy on BIG-Bench Hard (BBH) navigate by 27.6 pp while leaving boolean expressions intact (+5.6 pp), a 33.2 pp double dissociation. The effect is direction-specific and layer-localized, extends to mental-simulation tasks such as mental rotation, paper folding, and perspective taking, and is not explained by task difficulty, reasoning depth, or sequential update load. Together, these results reveal emergent vision-shaped thinking (EVT): text-only reasoning that causally recruits representations introduced or strengthened by vision-language training, without assuming an image-like internal format. The measured effect is spatially concentrated at 7-8B and broadens to non-spatial visual attribute binding in the tested 32B configuration. In dual-path unified models (BAGEL, Janus-Pro), the causal handle localizes to the generation pathway as a compact one-dimensional carrier. The understanding pathway also encodes spatial information in a higher-rank, probe-decodable form, but is not the causal handle. To separate decodability from causal use, we analyze concentration, alignment, and semantic location. These diagnostics explain why behavior, probing, and intervention can diverge. Multimodal training thus reshapes the geometry of text-only reasoning, not just how visual input is processed.

Figures & tables

Appendix figures & tables36 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Jul 21, 2025

Position: Reasoning After Perception Means Reasoning Without Vision

A common belief in multimodal research is that the perceptual weaknesses of vision--language models can be compensated by stronger language reasoning (e.g., chain-of-thought, in-context learning, or external tools). We challenge this assumption. We argue that for a broad class of visual tasks hard to specify in language, failures stem from a structural fatality where the temporal decision of when to reason strictly dictates the spatial constraint of where reasoning takes place. When visual reasoning is deferred to language generation, current architectures do not merely delay computation; they displace it from the continuous visual representation to a discrete textual space. Consequently, the sequential Perception-then-Reasoning'' paradigm degenerates perception into a passive, one-off feature encoding process, rendering it functionally equivalent to Reasoning-in-Text-Space'', where task-critical spatial signals are collapsed before reasoning begins. We substantiate this claim with the Turing Eye Test (TET): tasks that must be resolved in visual space and are hard to verbalize; results show text-only reasoning cannot remedy these perceptual failures. Our findings suggest rethinking the architectural divide: shifting from reasoning about perception to reasoning within perception. This facilitates actively reasoning-driven perception that operates directly on pixel-level visual representations, rather than within a collapsed textual space.
Feb 16, 2026

Seeing to Generalize: How Visual Data Corrects Binding Shortcuts

Vision Language Models (VLMs) are designed to extend Large Language Models (LLMs) with visual capabilities, yet in this work we observe a surprising phenomenon: VLMs can outperform their underlying LLMs on purely text-only tasks, particularly in long-context information retrieval. To investigate this effect, we build a controlled synthetic retrieval task and find that a transformer trained only on text achieves perfect in-distribution accuracy but fails to generalize out of distribution, while subsequent training on an image-tokenized version of the same task nearly doubles text-only OOD performance. Mechanistic interpretability reveals that visual training changes the model's internal binding strategy: text-only training encourages positional shortcuts, whereas image-based training disrupts them through spatial translation invariance, forcing the model to adopt a more robust symbolic binding mechanism that persists even after text-only examples are reintroduced. We further characterize how binding strategies vary across training regimes, visual encoders, and initializations, and show that analogous shifts occur during pretrained LLM-to-VLM transitions. Our findings suggest that cross-modal training can enhance reasoning and generalization even for tasks grounded in a single modality.
Apr 17, 2026

Do Vision-Language Models Truly Perform Vision Reasoning? A Rigorous Study of the Modality Gap

Reasoning in vision-language models (VLMs) has recently attracted significant attention due to its broad applicability across diverse downstream tasks. However, it remains unclear whether the superior performance of VLMs stems from genuine vision-grounded reasoning or relies predominantly on the reasoning capabilities of their textual backbones. To systematically measure this, we introduce CrossMath, a novel multimodal reasoning benchmark designed for controlled cross-modal comparisons. Specifically, we construct each problem in text-only, image-only, and image+text formats guaranteeing identical task-relevant information, verified by human annotators. This rigorous alignment effectively isolates modality-specific reasoning differences while eliminating confounding factors such as information mismatch. Extensive evaluation of state-of-the-art VLMs reveals a consistent phenomenon: a substantial performance gap between textual and visual reasoning. Notably, VLMs excel with text-only inputs, whereas incorporating visual data (image+text) frequently degrades performance compared to the text-only baseline. These findings indicate that current VLMs conduct reasoning primarily in the textual space, with limited genuine reliance on visual evidence. To mitigate this limitation, we curate a CrossMath training set for VLM fine-tuning. Empirical evaluations demonstrate that fine-tuning on this training set significantly boosts reasoning performance across all individual and joint modalities, while yielding robust gains on two general visual reasoning tasks. Source code is available at https://github.com/xuyige/CrossMath.