Beyond Routing: Characterising Expert Tuning and Representation in Vision Mixture-of-Experts
The paper explores the specialization of experts in Vision Mixture-of-Experts (MoE) models. It highlights the importance of analyzing expert tuning and representation beyond just routing categories. The findings suggest that expert specialization is more complex and involves broader tuning to various visual and semantic dimensions.
- ▪Mixture-of-Experts models are analyzed to understand expert specialization beyond routing categories.
- ▪The study employs a contrastive objective on natural images to characterize expert tuning using visual neuroscience tools.
- ▪Results indicate that an animate-inanimate distinction is a dominant factor in expert partitioning, stable across independently trained models.
arXiv cs.AI files mainly under ai research. We currently carry 1,128 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv cs.AI |
| Canonical URL | https://arxiv.org/abs/2605.20610 |
| Publication time | Fri, 22 May 2026 00:00:00 -0400 |
| Retrieval time | 2026-05-22T04:02:00.009Z |
| Last seen | 2026-05-22T04:02:00.009Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | lUvsy3OQRX3G |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Computer Vision and Pattern Recognition arXiv:2605.20610 (cs) [Submitted on 20 May 2026] Title:Beyond Routing: Characterising Expert Tuning and Representation in Vision Mixture-of-Experts Authors:Gene Tangtartharakul, Katherine R. Storrs View a PDF of the paper titled Beyond Routing: Characterising Expert Tuning and Representation in Vision Mixture-of-Experts, by Gene Tangtartharakul and Katherine R. Storrs View PDF HTML (experimental) Abstract:Mixture-of-Experts (MoE) models are often interpreted by analysing which categories are routed to which experts. However, routing alone does not reveal what each expert actually encodes.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
