Hacker News with Generative AI: Deep Learning

AI masters Minecraft: DeepMind program finds diamonds without being taught (nature.com)
An artificial intelligence (AI) system has for the first time figured out how to collect diamonds in the hugely popular video game Minecraft — a difficult task requiring multiple steps — without being shown how to play.

Artificial Intelligence, Video Games, Minecraft, Deep Learning

6 points by bglazer 5 hours ago | 0 comments

AI image recognition detects bubble-like structures in the universe (phys.org)
To learn more about the deepest reaches of our own galaxy and the mysteries of star formation, Japanese researchers have created a deep learning model.

Artificial Intelligence, Astronomy, Deep Learning, Universe

110 points by PaulHoule 3 days ago | 78 comments

The Matrix Calculus You Need for Deep Learning (explained.ai)
Most of us last saw calculus in school, but derivatives are a critical part of machine learning, particularly deep neural networks, which are trained by optimizing a loss function.

Deep Learning, Machine Learning, Mathematics, Neural Networks

67 points by Anon84 5 days ago | 3 comments

Self-Supervised Learning from Images with JEPA (2023) (arxiv.org)
This paper demonstrates an approach for learning highly semantic image representations without relying on hand-crafted data-augmentations.

Self-Supervised Learning, Computer Vision, Image Recognition, Artificial Intelligence, Deep Learning

40 points by Brysonbw 6 days ago | 10 comments

How DeepSeek Rewrote the Transformer [video] (youtube.com)

Transformers, Deep Learning, Computer Vision, Artificial Intelligence, Video

5 points by chetangole 6 days ago | 0 comments

Physics-Based Deep Learning v4 (arxiv.org)
This document is a hands-on, comprehensive guide to deep learning in the realm of physical simulations.

Deep Learning, Physics, Machine Learning

5 points by __rito__ 7 days ago | 1 comments

Optimizing ML training with metagradient descent (arxiv.org)
A major challenge in training large-scale machine learning models is configuring the training process to maximize model performance, i.e., finding the best training setup from a vast design space.

Machine Learning, Optimization, Deep Learning, Training, Meta-Learning

83 points by ladberg 9 days ago | 13 comments

VGGT: Visual Geometry Grounded Transformer (github.com/facebookresearch)

Computer Vision, Transformers, Artificial Intelligence, Deep Learning, Facebook Research

190 points by xnx 10 days ago | 42 comments

DeepSeek V3 is now the highest scoring non-reasoning model (twitter.com)
Something went wrong, but don’t fret — let’s give it another shot.

Deep Learning, Artificial Intelligence, Benchmarking

14 points by aurareturn 10 days ago | 3 comments

The Original 2012 AlexNet Is Open Source Now (github.com/computerhistory)
This package contains the original 2012 AlexNet code.

Computer Vision, Deep Learning, Open Source, Machine Learning, History

3 points by kwiktrip 10 days ago | 0 comments

Attention is NOT all you need (twitter.com)
Something went wrong, but don’t fret — let’s give it another shot.

Artificial Intelligence, Deep Learning

6 points by eunos 10 days ago | 0 comments

MIT 6.S191: Deep Generative Modeling [video] (youtube.com)

Deep Learning, Artificial Intelligence, Education, Generative AI, Computer Science

7 points by mfiguiere 10 days ago | 0 comments

Deepseek V3-0324 (huggingface.co)
This model is not currently available via any of the supported Inference Providers.

Deep Learning, New Releases

18 points by bananaflag 11 days ago | 2 comments

Mac Studio M3 Ultra can run Deepseek R1 671B in memory using <200W (techradar.com)

Mac, Computers, Deep Learning, Hardware, Power Consumption

7 points by mizzao 12 days ago | 1 comments

PyTorch Internals: Ezyang's Blog (ezyang.com)
This post is a long form essay version of a talk about PyTorch internals, that I gave at the PyTorch NYC meetup on May 14, 2019.

Deep Learning, Python, PyTorch, Open Source, Machine Learning

443 points by Anon84 12 days ago | 24 comments

Quantitative Finance: Kronecker-Factored Approximate Curvature Deep Hedging (arxiv.org)
This paper advances the computational efficiency of Deep Hedging frameworks through the novel integration of Kronecker-Factored Approximate Curvature (K-FAC) optimization.

Quantitative Finance, Deep Learning, Optimization, Machine Learning

5 points by walterbell 13 days ago | 0 comments

Physics-based Deep Learning Book (v0.3, the GenAI edition) (physicsbaseddeeplearning.org)
Welcome to the Physics-based Deep Learning Book (v0.3, the GenAI edition) 👋

Deep Learning, Physics, Generative AI, Books, Machine Learning

5 points by MAXPOOL 14 days ago | 0 comments

Running DeepSeek R1 on my desk (twitter.com)
Something went wrong, but don’t fret — let’s give it another shot.

Deep Learning, Software, Hardware, Twitter

9 points by tambourine_man 15 days ago | 1 comments

Nvidia Blackwell Delivers World-Record DeepSeek-R1 Inference Performance (nvidia.com)
NVIDIA announced world-record DeepSeek-R1 inference performance at NVIDIA GTC 2025.

Deep Learning, Inference, Hardware, Performance, NVIDIA

8 points by daviducolo 16 days ago | 0 comments

Implementing a GPT Model from Scratch [video] (youtube.com)

Generative AI, Programming, Machine Learning, Artificial Intelligence, Deep Learning

4 points by yaiml 17 days ago | 0 comments

Deep Learning Is Not So Mysterious or Different (arxiv.org)
Deep neural networks are often seen as different from other model classes by defying conventional notions of generalization.

Deep Learning, Artificial Intelligence, Machine Learning, Generalization, Neural Networks

485 points by wuubuu 17 days ago | 126 comments

Transformers Without Normalization (jiachenzhu.github.io)
This work demonstrates that Transformers without normalization can achieve the same or better performance using a remarkably simple technique.

Transformers, Deep Learning, Machine Learning

260 points by hellollm 20 days ago | 32 comments

DeepSeek-R1 now available as a managed serverless model in Amazon Bedrock (amazon.com)
As of January 30, DeepSeek-R1 models became available in Amazon Bedrock through the Amazon Bedrock Marketplace and Amazon Bedrock Custom Model Import. Since then, thousands of customers have deployed these models in Amazon Bedrock. Customers value the robust guardrails and comprehensive tooling for safe AI deployment. Today, we’re making it even easier to use DeepSeek in Amazon Bedrock through an expanded range of options, including a new serverless solution.

Amazon Bedrock, AI, Serverless, Deep Learning, Cloud Computing

10 points by tntpreneur 24 days ago | 0 comments

Understanding Transformers (beyond the Math) – kalomaze's kalomazing blog (bearblog.dev)
Maybe you don't want to attempt the conventional approaches for understanding the transformer architecture for language models. If you're anything like me, an informal approach is what you'd prefer - one that helps you reason about what's happening with these models in the abstract, without requiring mastery on the technical level to begin with.

Machine Learning, Deep Learning, Language Models, Transformers

8 points by bilsbie 25 days ago | 2 comments

RingFormer: Rethinking Recurrent Transformer with Adaptive Level Signals (arxiv.org)
Transformers have achieved great success in effectively processing sequential data such as text.

Transformers, Machine Learning, Deep Learning, Computer Science

3 points by PaulHoule 27 days ago | 0 comments

InstantStyle: Free Lunch Towards Style-Preserving in Text-to-Image Generation (github.com/instantX-research)
InstantStyle is a general framework that employs two straightforward yet potent techniques for achieving an effective disentanglement of style and content from reference images.

Generative AI, Computer Vision, Machine Learning, Image Generation, Deep Learning

49 points by klaussilveira 28 days ago | 11 comments

Paper Review: Variational Lossy Auto-Encoders (theahura.substack.com)
This post is part of a series of paper reviews, covering the ~30 papers Ilya Sutskever sent to John Carmack to learn about AI. To see the rest of the reviews, go here.

Machine Learning, Artificial Intelligence, Research Papers, Deep Learning

48 points by theahura 28 days ago | 2 comments

Spark-TTS: Text-2-Speech Model Single-Stream Decoupled Tokens [pdf] (arxiv.org)
Recent advancements in large language models (LLMs) have driven significant progress in zero-shot text-to-speech (TTS) synthesis.

Generative AI, Text-to-Speech, Deep Learning, Artificial Intelligence, Computer Science

78 points by bilekas 29 days ago | 6 comments

ChatGPT is made from 100M of these [The Perceptron] [video] (youtube.com)

Generative AI, Artificial Intelligence, Deep Learning, Computer Science

5 points by barbazoo 30 days ago | 0 comments

DiffRhythm: Fast End-to-End Full-Length Song Generation with Latent Diffusion (aslp-lab.github.io)
Recent advancements in music generation have garnered significant attention, yet existing approaches face critical limitations.

Music Generation, Artificial Intelligence, Machine Learning, Deep Learning

64 points by CrypticShift 30 days ago | 115 comments