Pith. sign in

REVIEW 1 cited by

Cross-token Modeling with Conditional Computation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2109.02008 v3 pith:INIGVSIU submitted 2021-09-05 cs.LG cs.AIcs.CV

classification cs.LGcs.AIcs.CV
keywords cross-tokenmodelaccuracyall-mlpalongcomputationcomputationalconditional
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Mixture-of-Experts (MoE), a conditional computation architecture, achieved promising performance by scaling local module (i.e. feed-forward network) of transformer. However, scaling the cross-token module (i.e. self-attention) is challenging due to the unstable training. This work proposes Sparse-MLP, an all-MLP model which applies sparsely-activated MLPs to cross-token modeling. Specifically, in each Sparse block of our all-MLP model, we apply two stages of MoE layers: one with MLP experts mixing information within channels along image patch dimension, the other with MLP experts mixing information within patches along the channel dimension. In addition, by proposing importance-score routing strategy for MoE and redesigning the image representation shape, we further improve our model's computational efficiency. Experimentally, we are more computation-efficient than Vision Transformers with comparable accuracy. Also, our models can outperform MLP-Mixer by 2.5\% on ImageNet Top-1 accuracy with fewer parameters and computational cost. On downstream tasks, i.e. Cifar10 and Cifar100, our models can still achieve better performance than baselines.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 4 citations worldwide. Full citation record

  1. Fair-MoE: Fairness-Oriented Mixture of Experts in Vision-Language Models

    cs.CV 2025-02 reject novelty 5.0 of 10

    Fair-MoE reports improved accuracy and fairness on Harvard-FairVLMed for some protected attributes by adding sparse mixture-of-experts layers and a variance-based fairness loss to CLIP, but the all-attribute improveme...

Pith tools