ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design

Aug-18-2025, 02:29:12 GMT–Neural Information Processing Systems

In this paper, we present a model-accelerator co-design framework to enable efficient on-device MTL, that tackles both training and inference bottlenecks.

artificial intelligence, arxiv preprint arxiv, machine learning, (13 more...)

Neural Information Processing Systems

Aug-18-2025, 02:29:12 GMT

Conferences PDF

Country:
- North America > United States
  - Texas
    - Travis County > Austin (0.04)
    - Brazos County > College Station (0.04)
- Asia > Middle East
  - Jordan (0.04)

Genre:
- Research Report (0.67)

Industry:
- Information Technology (0.93)

Technology:
- Information Technology > Artificial Intelligence
  - Vision (1.00)
  - Machine Learning
    - Neural Networks > Deep Learning (1.00)
    - Statistical Learning (0.68)

Duplicate Docs Excel Report

Title
M3ViT: Mixture-of-ExpertsVisionTransformer forEfficientMulti-taskLearning withModel-AcceleratorCo-design

Similar Docs Excel Report more

Title	Similarity	Source
None found