Trending

I made my AI think harder by making it argue with itself. It works stupidly well

An illustrated guide to automatic sparse differentiation

Finding paths of least action with gradient descent (2023)

O3 Beats a Master-Level GeoGuessr Player–Even with Fake EXIF Data

Hestus, Inc. (YC S24) Is Hiring an ML Engineer to Revolutionize CAD

Qwen3: Think Deeper, Act Faster

Implement Flash Attention Back End in SGLang – Basics and KV Cache

Vision Transformers Need Registers (extra tokens discarded after last layer)

Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models

You can now train LLMs 3x faster with 30% less memory! (<3.9GB VRAM)

[D] Benchmark: Massive degradation in NVMe Random Read throughput on A100 vs H100 during Multi-GPU Model Loading

[P] Supertonic — Lightning Fast, On-Device TTS (66M Params.)

Visualization of what is inside of AI models. This represents the layers of interconnected neural networks.

DeepSeek-V3.2-REAP: 508B and 345B checkpoints

[R] Formatting Iclr submission for ArXiv

Woman hospitalized after Pluribus ad on smart fridge triggers psychotic episode

After 1 year of slowly adding GPUs, my Local LLM Build is Complete - 8x3090 (192GB VRAM) 64-core EPYC Milan 250GB RAM

Who Really Invented Convolutional Neural Networks? The History of the Technology That Transformed AI

DeepSeek

Save item

DeepSeek-V3.2

Task: text-generation

DeepSeek

Save item

DeepSeek-V3.2-Speciale

Task: text-generation

Tencent

Save item

HunyuanOCR

Task: image-text-to-text

DeepSeek

Save item

DeepSeek-Math-V2

Task: text-generation

DeepSeek

Save item

DeepSeek-V3.2-Exp

Task: text-generation

AI at Meta

Save item

sam-3d-body-dinov3

RL ReSearch

Save item

DR-Tulu-8B

PaddlePaddle

Save item

PaddleOCR-VL

Task: image-text-to-text

Jun Zhang

Save item

PaddleOCR-VL-For-Manga

Task: image-text-to-text

upscayl

Save item

upscayl

🆙 Upscayl - #1 Free and Open Source AI Image Upscaler for Linux, MacOS and Windows.

vwxyzjn

Save item

cleanrl

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

ggml-org

Save item

whisper.cpp

Port of OpenAI's Whisper model in C/C++

NVIDIA

Save item

cuda-python

CUDA Python: Performance meets Productivity

DigitalPhonetics

Save item

IMS-Toucan

Controllable and fast Text-to-Speech for over 7000 languages!

NVIDIA

Save item

cutlass

CUDA Templates and Python DSLs for High-Performance Linear Algebra

openai

Save item

whisper

Robust Speech Recognition via Large-Scale Weak Supervision

huggingface

Save item

transformers

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

NVIDIA

Save item

Megatron-LM

Ongoing research training transformer models at scale