📄 文章列表
27 篇文章
cn_ai
同一个模型从 30 分到 95 分:拉开差距的不是模型,是Harness
cn_ai
MIT:GPT-6 Astra能直接修改Qwen权重,数学能力暴涨6倍
AlphaSignal
Prime Intellect's Prime Mega MoE Trains Giant AI Models 55% Faster
TDS
Building and Visualising Kolmogorov–Arnold Networks
TDS
What the ReLU Revolution Revealed About Biological Plausibility
TDS
I Trained a Tiny Network to Compress Data. It Drew a Pentagon.
TDS
Reparameterization Tricks: Variance Reduction by Smarter Gradients
TDS
Graph Neural Networks: GCN, MPNN, and GAT, Explained Simply
TDS
The Sigmoid Function: From 'e' to Neural Networks
TDS
Backpropagation Explained for Beginners (Part 3): How Backpropagation Really Works
TDS
Variational Autoencoders (VAEs) Explained: From Theory to ELBO and the Reparameterization Trick
TDS
Backpropagation Explained for Beginners (Part 2): There Has to Be a Better Way
TDS
Backpropagation Explained for Beginners (Part 1): Building the Intuition
AlphaSignal
Sakana AI Builds a Brain-Like Neural Network That Learns Without Backpropagation | AlphaSignal
TDS
A Gentle Introduction to Autoencoders & Latent Space
AlphaSignal
Sakana AI's DiffusionBlocks Trains Giant Neural Networks One Block at a Time | AlphaSignal
AlphaSignal
Meta's TLX Block Attention Beats Flash Attention v2 by 2.3x on Blackwell GPUs | AlphaSignal
TDS
Neural Networks, Explained for Beginners: Start Here If They’ve Confused You
TDS
The Total Derivative: Correcting the Misconception of Backpropagation’s Chain Rule
TDS
LLM Optimization: LoRA and QLoRA
1
2