NVIDIA Isaac GR00T N1 is the world's first open foundation model for generalized humanoid robot reasoning and skills.

Unlock Pose Diversity: Accurate and Efficient Implicit Keypoint-based Spatiotemporal Diffusion for Audio-driven Talking Portrait

SynCity: Training-Free Generation of 3D Worlds

TTS Towards Human-Sounding Speech

TxAgent: An AI Agent for Therapeutic Reasoning Across a Universe of Tools

Multi functional app to find duplicates, empty folders, similar images etc.

Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models

Build your own visual reasoning model

Fully local web research and report writing assistant

A Conversational Speech Generation Model

A curated list of 120+ LLM libraries category wise.

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

koding with any LLMs

High performance UI layout library in C.

Toolkit for linearizing PDFs for LLM datasets/training

A lightweight data processing framework built on DuckDB and 3FS.

ImSwitch is a software solution in Python that aims at generalizing microscope control by providing a solution for flexible control of multiple microscope modalities.

LIMO: Less is More for Reasoning

Implementation of Better Embeddings with Coupled Adam research paper

KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge ba…

Implementation of research paper: DarwinLM: Evolutionary Structured Pruning of Large Language Models

Training-free Post-training Efficient Sub-quadratic Complexity Attention. Implemented with OpenAI Triton.

Sources for the book "Machine Learning in Production"

Official Repo for Open-Reasoner-Zero

Genome modeling and design across all domains of life

Simple extension on vLLM to help you speed up reasoning model without training.