Trending

Piramidal (YC W24) is hiring a ML Engineer to decode brainwaves

Artificial photosynthesis directed toward organic synthesis

Big LLMs weights are a piece of history

Command A: Max performance, minimal compute – 256k context window

Sketch-of-Thought: Efficient LLM Reasoning

AutoHete: An Automatic and Efficient Heterogeneous Training System for LLMs

Arbitrary-Scale Super-Resolution with Neural Heat Fields

Transformers Without Normalization

Any insider takes on Yann LeCun's push against current architectures?

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

CUDA is coming to MLX

#DecodeThis hashtag#PatternRecognition hashtag#ArchitectOfTomorrow hashtag#TechnicalDepth

[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.

Kimi has impressive coding performance! Even deep into context usage.

More Artificial than Intelligent, and it is only getting worse

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

NVIDIA

Save item

cutlass

CUDA Templates for Linear Algebra Subroutines

microsoft

Save item

onnxruntime

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

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.

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

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.