GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection Share: Download MP3 Similar Tracks InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation Soroush Mehraban SHViT (CVPR2024): Single-Head Vision Transformer with Memory Efficient Macro Design Soroush Mehraban LoRA explained (and a bit about precision and quantization) DeepFindr An introduction to Policy Gradient methods - Deep Reinforcement Learning Arxiv Insights FastV: An Image is Worth 1/2 Tokens After Layer 2 Soroush Mehraban One-step Diffusion with Distribution Matching Distillation Soroush Mehraban Transformers (how LLMs work) explained visually | DL5 3Blue1Brown Autoregressive Image Generation without Vector Quantization Soroush Mehraban Full Fine tuning with Fewer GPUs - Galore, Optimizer Tricks, Adafactor Trelis Research PoseGPT (ChatPose): Chatting about 3D Human Pose Soroush Mehraban But what is a convolution? 3Blue1Brown But what is a neural network? | Deep learning chapter 1 3Blue1Brown Tent: Fully Test-time Adaptation by Entropy Minimization Soroush Mehraban But what are Hamming codes? The origin of error correction 3Blue1Brown
