Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts
Multimodal Mixture-of-Experts (MoE) models have achieved remarkable performance on vision-language tasks. However, we identify a puzzling phenomenon termed Seeing but Not Thinking: models accurately perceive image content yet fail in subsequent reasoning, while correctly solving identical problems presented as pure text. Through systematic analysis, we first verify that cross-modal semantic sharing exists in MoE architectures, ruling out semantic alignment failure as the sole explanation. We then reveal that visual experts and domain experts exhibit layer-wise separation, with image inputs inducing significant routing divergence from text inputs in middle layers where domain experts conce...
| Authors | Haolei Xu, Haiwen Hong, Hongxing Li et al. |
|---|---|
| Primary category | cs.CV |
| Published | 9 April 2026 |
| Last updated at source | 9 April 2026 |
Connected in the knowledge graph
- takanori-ishikawa/DeepSeek-V4-Flash-0731-Pruned-155B-A13B-GGUFModel · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.