Music |
Video |
Movies |
Chart |
Show |
Efficient Transformers with Dynamic Token Pooling (Piotr Nawrot) View | |
GTP-ViT: Efficient Vision Transformers via Graph-Based Token Propagation (ComputerVisionFoundation Videos) View | |
Meta Byte Latent Transformer: Improved Transformer for LLMs (Data Science in your pocket) View | |
Byte Latent Transformer (BLT) by Meta AI - A Tokenizer-free LLM (AI Papers Academy) View | |
Byte Latent Transformer: Patches Scale Better Than Tokens (Xiaol.x) View | |
MSViT: Dynamic Mixed-Scale Tokenization for Vision Transformers (NIVT Transformers) View | |
Attention mechanism: Overview (Google Cloud Tech) View | |
Depth-Wise Convolutions in Vision Transformers for Efficient Training on Small Datasets (Academia Accelerated) View | |
WaveMixSR: Resource-Efficient Neural Network for Image Super-Resolution (ComputerVisionFoundation Videos) View | |
One for All: Unified Workload Prediction for Dynamic Multi-tenant Edge Cloud Platforms - (Academia Accelerated) View |