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.
Dust: The Radical Idea of Training AI Without Backpropagation

Dust: The Radical Idea of Training AI Without Backpropagation

Comments
4 min read
Understanding Prism: Dynamic Sparse Attention for Joint Video-Audio Generation

Understanding Prism: Dynamic Sparse Attention for Joint Video-Audio Generation

Comments
4 min read
1,107 Tokens Per Second: The LLM That Doesn't Type

1,107 Tokens Per Second: The LLM That Doesn't Type

Comments
5 min read
One Brain, Any Body: Google DeepMind's Keerthana on Gemini ER2 | 谷歌DeepMind Gemini Robotics 2 与通用机器人现状深度访谈

One Brain, Any Body: Google DeepMind's Keerthana on Gemini ER2 | 谷歌DeepMind Gemini Robotics 2 与通用机器人现状深度访谈

Comments
2 min read
One Model, Three Jobs, Zero Retraining: The Spreadsheet Just Got Its Foundation Model

One Model, Three Jobs, Zero Retraining: The Spreadsheet Just Got Its Foundation Model

Comments
5 min read
How AI Rap Duo Video Generators Work Under the Hood (and How to Pick One)

How AI Rap Duo Video Generators Work Under the Hood (and How to Pick One)

Comments 1
3 min read
DAY 1 - GENERATIVE AI

DAY 1 - GENERATIVE AI

Comments
8 min read
RL 5: Learning Automata and stochastic environments (1961–1974)

RL 5: Learning Automata and stochastic environments (1961–1974)

Comments
21 min read
Fine-tuning a 7B model needs 112 GB. The model is only 14 GB of it.

Fine-tuning a 7B model needs 112 GB. The model is only 14 GB of it.

Comments
3 min read
How AI Learns: Forward Pass and Loss Explained with 2 + 1

How AI Learns: Forward Pass and Loss Explained with 2 + 1

Comments
2 min read
Understanding Neural Networks: The Core Idea

Understanding Neural Networks: The Core Idea

Comments
11 min read
UniEvo-VL: On-Policy Self-Distillation for Multimodal Image Generation

UniEvo-VL: On-Policy Self-Distillation for Multimodal Image Generation

Comments
5 min read
RoPE vs sinusoidal positional encoding, measured: 55 logits of drift against 0.0005

RoPE vs sinusoidal positional encoding, measured: 55 logits of drift against 0.0005

Comments
7 min read
Why AI Lies Without Knowing It’s Lying | Victor Amit

Why AI Lies Without Knowing It’s Lying | Victor Amit

1
Comments
21 min read
REAL-Q: How Dynamic Gradient Descent Fixes the Core Flaw in LLM Quantization

REAL-Q: How Dynamic Gradient Descent Fixes the Core Flaw in LLM Quantization

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