🔥 PyTorch - yfff · Scour

mlr3torch: A Deep Learning Framework in R based on mlr3 and torch 🧠LLM

ParaRNN: Large-Scale Nonlinear RNNs, Trainable in Parallel 🧠LLM

machinelearning.apple.com·2d·Hacker News

meta-pytorch/spmd_types: This module defines a type system for distributed training code, based off of JAX's sharding in types, but adapted for the PyTorch ecosystem. 🧠LLM

github.com·13h·Hacker News

Building Your First Neural Network in Rust with Burn 🦀Rust

djamware.com·1d·DEV

TorchTPU - 在谷歌级规模下原生运行 PyTorch 于 TPU 上 🤖AI

cloud.google.com·4d

BranchyNet: Teaching Neural Networks When to Stop Thinking 💡AI Reasoning

Learning in Low Precision 🗜️Compressed Sensing

rachitsingh.com·4d

Machine learning-driven alignment architecture of heterogeneous data with transient varying semantics 🧠Machine Learning

deepseek-ai/DeepSeek-V4-Flash 🧠LLM

huggingface.co·1d·Hacker News

Neural Networks Explained In Plain English 🧠Machine Learning

blog.algomaster.io·4d

Machine Learning Visualized – Machine Learning Visualized 🧠Machine Learning

ml-visualized.com·1d·Hacker News

Generalization performance of narrow shallow neural networks in the teacher–student setting 🧠Machine Learning

iopscience.iop.org·3d

There Will Be a Scientific Theory of Deep Learning 📐Optimization Theory

Verified Deep Learning with Lean 4 🧠LLM

brettkoonce.github.io·3d·Hacker News

The Deep Learning Trio: Decoding ANN vs. CNN vs. RNN 🧠Machine Learning

Comptime tensor 🤖AI

Graphs in Motion: Spatio-Temporal Dynamics with Graph Neural Networks 🧠LLM

·5d

F\textsuperscript{2}LP-AP: Fast \& Flexible Label Propagation with Adaptive Propagation Kernel 🧠LLM

massimilianoconcas0-del/Relational_Loss_ML: A scale-invariant loss function for Deep Learning. Replace Absolute Loss (MSE) with Relational Loss to achieve 4000x faster convergence and zero-shot transfer across scales. 🧠Machine Learning

github.com·1d·Hacker News

Encoder-Free Human Motion Understanding via Structured Motion Descriptions 📐Linear Algebra

Log in to enable infinite scrolling