M3ViT: Mixture-Of-Experts Vision Transformer for Efficient Multi-Task Learning with Model-Accelerator Co-Design
Open accessThe DOI matches its OpenAlex record; 13 of the 13 references it cites were found in a registry or an index.
Abstract
Multi-task learning (MTL) encapsulates multiple learned tasks in a single model and often lets those tasks learn better jointly. However, when deploying MTL onto those real-world systems that are often resource-constrained or latency-sensitive, two prominent challenges arise: (i) during training, simultaneously optimizing all tasks is often difficult due to gradient conflicts across tasks; (ii) at inference, current MTL regimes have to activate nearly the entire model even to just execute a single task. Yet most real systems demand only one or two tasks at each moment, and switch between tasks as needed: therefore such all tasks activated inference is also highly inefficient and non-scalable. In this paper, we present a model-accelerator co-design framework to enable efficient on-device MTL. Our framework, dubbed M$^3$ViT, customizes mixture-of-experts (MoE) layers into a vision transformer (ViT) backbone for MTL, and sparsely activates task-specific experts during training. Then at inference with any task of interest, the same design allows for activating only the task-corresponding sparse expert pathway, instead of the full model. Our new model design is further enhanced by hardware-level innovations, in particular, a novel computation reordering scheme tailored for memory-constrained MTL that achieves zero-overhead switching between tasks and can scale to any number of experts. When executing single-task inference, M$^{3}$ViT achieves higher accuracies than encoder-focused MTL methods, while significantly reducing 88% inference FLOPs. When implemented on a hardware platform of one Xilinx ZCU104 FPGA, our co-design framework reduces the memory requirement by 2.4 times, while achieving energy efficiency up to 9.23 times higher than a comparable FPGA baseline. Code is available at: https://github.com/VITA-Group/M3ViT.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Adaptive Mixtures of Local Experts
Jacobs, R. A., Jordan, M. I., Nowlan, S. J., & Hinton, G. E. (1991) · Neural Computation · doi:10.1162/neco.1991.3.1.79 · Cited by 5,384
Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
Zheng, S., Lu, J., Zhao, H., Zhu, X., Luo, Z., Wang, Y., Fu, Y., Feng, J., Xiang, T., Torr, P. H. S., et al. (2020) · arXiv · doi:10.48550/arxiv.2012.15840 · Cited by 4,004
Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
Shazeer, N., Mirhoseini, A., Maziarz, K., Davis, A., Le, Q., Hinton, G., & Dean, J. (2017) · arXiv · doi:10.48550/arxiv.1701.06538 · Cited by 933
Gradient Surgery for Multi-Task Learning
Yu, T., Kumar, S., Gupta, A., Levine, S., Hausman, K., & Finn, C. (2020) · arXiv · doi:10.48550/arxiv.2001.06782 · Cited by 755
End-to-End Human Pose and Mesh Reconstruction with Transformers
Lin, K., Wang, L., & Liu, Z. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00199 · Cited by 740
A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks
Hashimoto, K., xiong, C., Tsuruoka, Y., & Socher, R. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1206 · Cited by 535
Florence: A New Foundation Model for Computer Vision
Yuan, L., Chen, D., Chen, Y.-L., Codella, N., Dai, X., Gao, J., Hu, H., Huang, X., Li, B., Li, C., et al. (2021) · arXiv · doi:10.48550/arxiv.2111.11432 · Cited by 389
UniT: Multimodal Multitask Learning with a Unified Transformer
Hu, R., & Singh, A. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00147 · Cited by 303
Kaiser, L., Gomez, A. N., Shazeer, N., Vaswani, A., Parmar, N., Jones, L., & Uszkoreit, J. (2017) · arXiv · doi:10.48550/arxiv.1706.05137 · Cited by 253
Accelerating Transformer-based Deep Learning Models on FPGAs using Column Balanced Block Pruning
Peng, H., Huang, S., Geng, T., Li, A., Jiang, W., Liu, H., Wang, S., & Ding, C. (2021) · 2021 22nd International Symposium on Quality Electronic Design (ISQED) · doi:10.1109/isqed51717.2021.9424344 · Cited by 105
Cited by
McIntosh, T. R., Susnjak, T., Liu, T., Watters, P., Xu, D., Liu, D., & Halgamuge, M. N. (2025) · Technologies · doi:10.3390/technologies13020051 · Cited by 102
A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models
Guo, C., Cheng, F., Du, Z., Kiessling, J., Ku, J., Li, S., Li, Z., Ma, M., Molom-Ochir, T., Morris, B., et al. (2025) · IEEE Circuits and Systems Magazine · doi:10.1109/mcas.2024.3476008 · Cited by 32
The Evolution of Mixture of Experts: A Survey from Basics to Breakthroughs
Vats, A., Raja, R., Jain, V., & Chadha, A. (2024) · doi:10.20944/preprints202408.0583.v2 · Cited by 10
Metadata
- Authors
- Liang, H., Fan, Z., Sarkar, R., Jiang, Z., Chen, T., Zou, K., Cheng, Y., Hao, C., & Wang, Z.
- Venue
- neural information processing systems
- Published
- 2022-01-01
- Pages
- 28441-28457
- ISSN
- 1049-5258 (ISSN-L)
- OpenAlex
- W7133200090
- Cited by
- 39
- References
- 13
- FWCI
- 3.28
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: M3ViT: Mixture-Of-Experts Vision Transformer for Efficient Multi-Task Learning with Model-Accelerator Co-Design. https://app.cochat.ai/papers/10.52202/068431-2062
- The paper
- Liang, H., Fan, Z., Sarkar, R., Jiang, Z., Chen, T., Zou, K., Cheng, Y., Hao, C., & Wang, Z. (2022). M3ViT: Mixture-Of-Experts Vision Transformer for Efficient Multi-Task Learning with Model-Accelerator Co-Design. neural information processing systems. https://doi.org/10.52202/068431-2062
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.