Collection by
Apr 7, 2024
Apr 7, 2024
Collections
Discover the best community collections!
Collections including paper arxiv:2106.05974
Collection by
Apr 6, 2024
Apr 6, 2024
-
Scaling Vision with Sparse Mixture of Experts
Paper • 2106.05974 • Published • 3 -
Routers in Vision Mixture of Experts: An Empirical Study
Paper • 2401.15969 • Published • 2 -
Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts
Paper • 2206.02770 • Published • 3 -
Experts Weights Averaging: A New General Training Scheme for Vision Transformers
Paper • 2308.06093 • Published • 2
Collection by
Dec 22, 2024
Dec 22, 2024
-
Non-asymptotic oracle inequalities for the Lasso in high-dimensional mixture of experts
Paper • 2009.10622 • Published • 1 -
MoE-LLaVA: Mixture of Experts for Large Vision-Language Models
Paper • 2401.15947 • Published • 51 -
MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts
Paper • 2401.04081 • Published • 71 -
MoE-Infinity: Activation-Aware Expert Offloading for Efficient MoE Serving
Paper • 2401.14361 • Published • 2
Collection by
Apr 18, 2024
Apr 18, 2024
-
Mixtral of Experts
Paper • 2401.04088 • Published • 158 -
MoE-LLaVA: Mixture of Experts for Large Vision-Language Models
Paper • 2401.15947 • Published • 51 -
MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts
Paper • 2401.04081 • Published • 71 -
EdgeMoE: Fast On-Device Inference of MoE-based Large Language Models
Paper • 2308.14352 • Published
Collection by
Feb 27, 2024
Feb 27, 2024
-
Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
Paper • 1701.06538 • Published • 6 -
Sparse Networks from Scratch: Faster Training without Losing Performance
Paper • 1907.04840 • Published • 3 -
ZeRO: Memory Optimizations Toward Training Trillion Parameter Models
Paper • 1910.02054 • Published • 5 -
A Mixture of h-1 Heads is Better than h Heads
Paper • 2005.06537 • Published • 2
Collection by
Nov 4, 2024
Nov 4, 2024
-
Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
Paper • 1701.06538 • Published • 6 -
Sparse Networks from Scratch: Faster Training without Losing Performance
Paper • 1907.04840 • Published • 3 -
ZeRO: Memory Optimizations Toward Training Trillion Parameter Models
Paper • 1910.02054 • Published • 5 -
A Mixture of h-1 Heads is Better than h Heads
Paper • 2005.06537 • Published • 2