Trending

Probabilistic Artificial Intelligence

Nexar Dashcam Crash Prediction Challenge

Generative AI Hype Peaking

Llama.cpp AI Performance with the GeForce RTX 5090 Review

Paper Review: Variational Lossy Auto-Encoders

16-Bit to 1-Bit: Visual KV Cache Quantization for Efficient Multimodal LLMs

Update: we got our revenge and now beat Deepmind, Microsoft, Zhipu AI and Alibaba

[D] Paged Attention Performance Analysis

[D] Recent paddleocr version accuracy

Lidar helps gas industry find methane leaks and avoid costly losses

[R] AI Learns to Speedrun Mario in 24 Hours (2 Million Attempts!)

ROCm 7.0 RC1 More than doubles performance of LLama.cpp

What do we call the moment AI can autonomously build a chip fab — and what happens after?

4x 3090 local ai workstation

[R] Built an open-source matting model (Depth-Anything + U-Net). What would you try next?

Swift

Save item

VibeVoice-Large

Task: text-to-speech

DeepSeek

Save item

DeepSeek-V3.1

Task: text-generation

DeepSeek

Save item

DeepSeek-V3.1-Base

rednote-hilab

Save item

dots.ocr

Task: image-text-to-text

Unsloth AI

Save item

DeepSeek-V3.1-GGUF

AI at Meta

Save item

dinov3-vit7b16-pretrain-lvd1689m

Task: image-feature-extraction

ldf

Save item

Motion-Lora-Camera-Push-In-Wan-14B-720p-I2V

DeepSeek

Save item

DeepSeek-R1-0528

OpenAI

Save item

whisper-large-v3

Task: automatic-speech-recognition

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.

roboflow

Save item

notebooks

A collection of tutorials on state-of-the-art computer vision models and techniques. Explore everything from foundational architectures like ResNet to cutting-edge models like YOLO11, RT-DETR, SAM 2, Florence-2, PaliGemma 2, and Qwen2.5VL.

tracel-ai

Save item

burn

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

Dao-AILab

Save item

flash-attention

Fast and memory-efficient exact attention

microsoft

Save item

qlib

Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exploring ideas to implementing productions. Qlib supports diverse ML modeling paradigms, including supervised learning, market dynamics modeling, and RL, and is now equipped with https://github.com/microsoft/RD-Agent to automate R&D process.

microsoft

Save item

onnxruntime

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

google-deepmind

Save item

mujoco

Multi-Joint dynamics with Contact. A general purpose physics simulator.

deepinsight

Save item

insightface

State-of-the-art 2D and 3D Face Analysis Project

huggingface

Save item

pytorch-image-models

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more