Matryoshka Diffusion Models
Paper
•
2310.15111
•
Published
•
40
Shared params
-
-
SortedNet, a Place for Every Network and Every Network in its Place: Towards a Generalized Solution for Training Many-in-One Neural Networks
Paper • 2309.00255 • Published • 1 -
Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference Using Sorted Fine-Tuning (SoFT)
Paper • 2309.08968 • Published • 22 -
Matryoshka Representation Learning
Paper • 2205.13147 • Published • 9 -
Matryoshka: Stealing Functionality of Private ML Data by Hiding Models in Model
Paper • 2206.14371 • Published • 3 -
MatFormer: Nested Transformer for Elastic Inference
Paper • 2310.07707 • Published • 1 -
Network In Network
Paper • 1312.4400 • Published • 1 -
Composable Sparse Fine-Tuning for Cross-Lingual Transfer
Paper • 2110.07560 • Published • 1 -
Visual Programming: Compositional visual reasoning without training
Paper • 2211.11559 • Published • 1 -
One Wide Feedforward is All You Need
Paper • 2309.01826 • Published • 31 -
Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts
Paper • 2306.04845 • Published • 4 -
Improving Differentiable Architecture Search via Self-Distillation
Paper • 2302.05629 • Published • 1 -
TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-device ASR Models
Paper • 2309.01947 • Published • 1 -
NetDistiller: Empowering Tiny Deep Learning via In-Situ Distillation
Paper • 2310.19820 • Published • 1 -
Beyond Universal Transformer: block reusing with adaptor in Transformer for automatic speech recognition
Paper • 2303.13072 • Published • 1 -
Learning a Consensus Sub-Network with Polarization Regularization and One Pass Training
Paper • 2302.10798 • Published • 1 -
An EMO Joint Pruning with Multiple Sub-networks: Fast and Effect
Paper • 2303.16212 • Published • 1 -
Looped Transformers are Better at Learning Learning Algorithms
Paper • 2311.12424 • Published • 1 -
Looped Transformers as Programmable Computers
Paper • 2301.13196 • Published • 1 -
Learning Stackable and Skippable LEGO Bricks for Efficient, Reconfigurable, and Variable-Resolution Diffusion Modeling
Paper • 2310.06389 • Published • 1 -
Sliced Recursive Transformer
Paper • 2111.05297 • Published • 1 -
Transformer in Transformer
Paper • 2103.00112 • Published • 1 -
Go Wider Instead of Deeper
Paper • 2107.11817 • Published • 1 -
Sparse Universal Transformer
Paper • 2310.07096 • Published -
Matryoshka Multimodal Models
Paper • 2405.17430 • Published • 30 -
MoEUT: Mixture-of-Experts Universal Transformers
Paper • 2405.16039 • Published -
Beyond KV Caching: Shared Attention for Efficient LLMs
Paper • 2407.12866 • Published