DEV Community

Deep Learning

This tag is for discussing, sharing articles, and asking questions primarily on deep learning - a subfield of machine learning.

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
MicroTorch: A Zero-Dependency Tensor Autograd Engine from Scratch in Python

MicroTorch: A Zero-Dependency Tensor Autograd Engine from Scratch in Python

Comments
1 min read
🚀 Why LLMs Won’t Reach AGI on Words Alone: The Rise of Spatial Intelligence & Test-Time Compute.

🚀 Why LLMs Won’t Reach AGI on Words Alone: The Rise of Spatial Intelligence & Test-Time Compute.

Comments
1 min read
Spectral Normalisation: Why Bounding the Lipschitz Constant Stabilises Deep Networks

Spectral Normalisation: Why Bounding the Lipschitz Constant Stabilises Deep Networks

Comments
8 min read
Building a Healthcare LLM from Scratch with PyTorch: Mixtral-Inspired Mixture-of-Experts, Pretraining, and Full Fine-Tuning

Building a Healthcare LLM from Scratch with PyTorch: Mixtral-Inspired Mixture-of-Experts, Pretraining, and Full Fine-Tuning

Comments
6 min read
Proximal Policy Optimization: Why Clipping the Update Beats Trusting the Gradient

Proximal Policy Optimization: Why Clipping the Update Beats Trusting the Gradient

Comments
9 min read
Cosmos 3 Edge, Part 2: Physical AI Workflows, Action Reasoning, and Action Chunks

Cosmos 3 Edge, Part 2: Physical AI Workflows, Action Reasoning, and Action Chunks

Comments
7 min read
Tech & AI Synthesis: BitDecoding-FP4: Native FP4 KV Cache Decoding via Algorithm-System Co-Design

Tech & AI Synthesis: BitDecoding-FP4: Native FP4 KV Cache Decoding via Algorithm-System Co-Design

Comments
3 min read
Equivariant Neural Networks: Why Baking Symmetry Into the Architecture Beats Learning It From Data

Equivariant Neural Networks: Why Baking Symmetry Into the Architecture Beats Learning It From Data

Comments
8 min read
Mirror Descent: Why the Right Geometry Changes Gradient Descent

Mirror Descent: Why the Right Geometry Changes Gradient Descent

Comments
7 min read
Frank-Wolfe: Why Linear Oracles Beat Projections on Constrained Problems

Frank-Wolfe: Why Linear Oracles Beat Projections on Constrained Problems

Comments
9 min read
UMM-JEPA: Predicting What the Model Understands, Not What the Decoder Wants

UMM-JEPA: Predicting What the Model Understands, Not What the Decoder Wants

Comments
13 min read
Speculative Decoding: Why Drafting Tokens in Parallel Speeds Up Autoregressive Generation

Speculative Decoding: Why Drafting Tokens in Parallel Speeds Up Autoregressive Generation

Comments
7 min read
Tech & AI Synthesis: Reflection Anchors for Propagation-Aware Visual Retention in Long-Chain Multimodal Reasoning

Tech & AI Synthesis: Reflection Anchors for Propagation-Aware Visual Retention in Long-Chain Multimodal Reasoning

Comments
3 min read
A Blackwell Fingerprint in Open Weights: What It Proves, and What It Doesn't

A Blackwell Fingerprint in Open Weights: What It Proves, and What It Doesn't

Comments
10 min read
AI Models Are Starting to Engineer Other AI Models

AI Models Are Starting to Engineer Other AI Models

1
Comments
8 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.