Trending

Fine-tune Google's Gemma 3

Orpheus-3B – Emotive TTS by Canopy Labs

How 'inference' is driving competition to Nvidia's AI chip dominance

Introduction to Deep Learning (CMU)

Writing an LLM from scratch, part 10 – dropout

Wolfram: Learning about Innovation from Half a Century of Conway's Game of Life

Show HN: We built an agentic image editor that preserves the original structure

Artificial Intelligence: Foundations of Computational Agents

Nvidia DGX Spark

[D] I'm having problem quantizing T5 model.

Writer vs DeepSeek: can AI really replace the human touch?

[R][D] Interpretability as a Side Effect? Are Activation Functions Biasing Your Models?

#DecodeThis hashtag#PatternRecognition hashtag#ArchitectOfTomorrow hashtag#TechnicalDepth

CUDA is coming to MLX

[P] LSTM to recognize baseball players based on their swing keypoint data

Grok Rolls out Pornographic Anime Companion, lands Department of Defense Contract- still identifying as Adolf Hitler

[P] Help with Contrastive Learning (MRI + Biomarkers) – Looking for Guidance/Mentor (Willing to Pay)

AI Terms Simply Explained.

DeepSeek

Save item

DeepSeek-R1-0528

chatdoc.com

Save item

OCRFlux-3B

Task: image-text-to-text

OpenAI

Save item

whisper-large-v3

Task: automatic-speech-recognition

Kyutai

Save item

stt-1b-en_fr

Task: automatic-speech-recognition

lightx2v

Save item

Wan2.1-T2V-14B-StepDistill-CfgDistill

Task: text-to-video

NVIDIA

Save item

Cosmos-Predict2-2B-Text2Image

Task: text-to-image

Guande He

Save item

Self-Forcing

Task: text-to-video

Tencent

Save item

HunyuanVideo-Avatar

Task: image-to-video

Beijing Academy of Artificial Intelligence

Save item

RoboBrain2.0-7B

Task: robotics

tracel-ai

Save item

burn

Burn is a next generation Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.

microsoft

Save item

onnxruntime

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Deci-AI

Save item

super-gradients

Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS.

NVIDIA

Save item

cutlass

CUDA Templates for Linear Algebra Subroutines

Dao-AILab

Save item

flash-attention

Fast and memory-efficient exact attention

modelscope

Save item

FunASR

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

jax-ml

Save item

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

ultralytics

Save item

yolov5

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

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.