# Vision mixture-of-experts

Area: [Mixture-of-experts](https://mlsanity.com/moe/index.md). HTML: https://mlsanity.com/moe/vision-mixture-of-experts/

## Key facts

- Vision mixture-of-experts: 338 papers on arXiv since 2017 (data through 14 Oct 2026).
- 94 of its 338 mapped papers (28%) cite “Scaling Vision with Sparse Mixture of Experts” (2021, arXiv 2106.05974).
- 27 of its 338 mapped papers (8%) cite “From Sparse to Soft Mixtures of Experts” (2023, arXiv 2308.00951).
- 12 new papers 17 Sep–14 Oct.

## Most cited here

- [Scaling Vision with Sparse Mixture of Experts](https://mlsanity.com/paper/2106.05974/) (2021), cited by 94 papers here
- [From Sparse to Soft Mixtures of Experts](https://mlsanity.com/paper/2308.00951/) (2023), cited by 27 papers here
- [Deep Mixture of Experts via Shallow Embedding](https://mlsanity.com/paper/1806.01531/) (2018), cited by 21 papers here
- [Hard Mixtures of Experts for Large Scale Weakly Supervised Vision](https://mlsanity.com/paper/1704.06363/) (2017), cited by 13 papers here
- [Go Wider Instead of Deeper](https://mlsanity.com/paper/2107.11817/) (2021), cited by 11 papers here
- [Robust Mixture-of-Expert Training for Convolutional Neural Networks](https://mlsanity.com/paper/2308.10110/) (2023), cited by 11 papers here
- [Scaling Diffusion Transformers to 16 Billion Parameters](https://mlsanity.com/paper/2407.11633/) (2024), cited by 11 papers here
- [Sparse Mixture-of-Experts are Domain Generalizable Learners](https://mlsanity.com/paper/2206.04046/) (2022), cited by 10 papers here
- [On the Adversarial Robustness of Mixture of Experts](https://mlsanity.com/paper/2210.10253/) (2022), cited by 10 papers here
- [RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths](https://mlsanity.com/paper/2305.18295/) (2023), cited by 10 papers here

## New (17 Sep–14 Oct)

- [CAST: History-Adaptive Spectral Clipping for LLM Pretraining](https://mlsanity.com/paper/2610.19761/) (2026-10-14)
- [PixelMoE: Scaling Pixel-Space Diffusion with LLM-Style Mixture-of-Experts](https://mlsanity.com/paper/2610.18857/) (2026-10-13)
- [RoMod: Temporal Routing Modulation via Mixture-of-Experts for Video Anomaly Detection](https://mlsanity.com/paper/2610.05131/) (2026-10-04)
- [LoopMoEVR: Loop-Based Degradation-Aware Mixture-of-Experts for Unified UHD Video Restoration](https://mlsanity.com/paper/2610.05109/) (2026-10-04)
- [Fine-Tuning VLM for Enhancing AI's Spatial Intelligence: Understanding 3D and 2D Rotations](https://mlsanity.com/paper/2610.04206/) (2026-10-03)
- [DecoMoE: Decoupling Visual Propagation and Expert Computation for Efficient Multimodal MoE Inference](https://mlsanity.com/paper/2609.38823/) (2026-09-30)
- [Breaking the Uniformity Trap: Scaling Video Diffusion Model via SplitMoE](https://mlsanity.com/paper/2609.38140/) (2026-09-29)
- [From Routing Signals to Selective Review: Visual regrounding in MoE VLMs](https://mlsanity.com/paper/2609.38111/) (2026-09-29)
- [DIET: Deletion-response Expert Trimming for Video Diffusion Transformers](https://mlsanity.com/paper/2609.37829/) (2026-09-29)
- [SAGE: Subspace Alignment for Classifier-Free Guidance in Mixture-of-Experts Diffusion Models](https://mlsanity.com/paper/2609.34525/) (2026-09-28)
- [EviDETR: Preserving Query-Relevant Temporal Evidence for Moment Retrieval and Highlight Detection](https://mlsanity.com/paper/2609.30724/) (2026-09-25)
- [C2FXNet: Coarse-to-Fine Scene Expert for Unified Object Detection across Adverse Weather](https://mlsanity.com/paper/2609.25693/) (2026-09-22)