- Rating
- 1
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper investigates whether independent vision and language models develop neurons that respond to corresponding concepts. It identifies cross-modal neuron pairs by correlating their mean activations over paired image–caption data and demonstrates such correspondences across multiple models, including vision encoders trained without text. The findings are supported by reproducibility tests and human and model-based evaluations, with the number of matched neurons exhibiting sublinear power-law scaling with model size.
Critical strengths
- The work investigates neurons that encode similar semantic concepts across vision-language models.
- The work conducts experiments across multiple model architectures.
- The work provides multiple visualizations and analysis.
Critical weaknesses
- The proposed method lacks novelty, as it primarily collects neuron activations and performs statistical correlation analyses.
- The method lacks theoretical guarantees and relies entirely on the neuron correspondences between the original models. Therefore, its effectiveness cannot be guaranteed for arbitrary model pairs.
- The paper lacks discussion and comparison with prior methods, such as VL-SAE [1], which has mapped multimodal representations from CLIP and MLLM models into a unified concept space and leveraged this alignment to improve model performance.
- The proposed method does not demonstrate its potential to further improve model performance. Compared with existing methods [1, 2], the contribution of this work is limited to visualization and statistical analysis, without demonstrating tangible improvements in model capabilities.
[1] Shen, S., Sun, J., Huang, Q., & Wang, S. (2026). Vl-sae: Interpreting and enhancing vision-language alignment with a unified concept set. Advances in Neural Information Processing Systems, 38, 45235-45265.
[2] Renzulli, R., Spadaro, G., Gowda, S., Mazouz, A. E., & Nguyen, V. T. (2026). TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models. arXiv preprint arXiv:2607.04593.
Questions for authors
Overall, the paper lacks discussion and comparisons with highly relevant prior work, offers limited methodological novelty, and focuses solely on analyzing the internal properties of models without demonstrating practical improvements. Therefore, I have reservations about the significance and contribution of this work.
We thank the reviewers for their time and detailed feedback. We have read the reviews carefully and appreciate the questions and suggestions. We plan to continue developing this work and will consider the points raised as we prepare the next iteration.