This repo is for all course work required to be certified for the AI Engineering Bootcamp

Shorter but not Worse: Frugal Reasoning via Easy Samples as Length Regularizers in Math RLVR

Official implementation of "Continuous Autoregressive Language Models"

An Open-Source Large-Scale Reinforcement Learning Project for Search Agents

🎒 Token-Oriented Object Notation (TOON) – JSON for LLM prompts at half the tokens. Spec, benchmarks & TypeScript implementation.

NOFX: Defining the Next-Generation AI Trading Operating System. A multi-exchange Al trading platform(Binance/Hyperliquid/Aster) with multi-Ai competition(deepseek/qwen/claude)self-evolution, and re…

Grab any element on in your app and give it to Cursor, Claude Code, etc

Agentic AI system to solve Kaggle Competitions

An Open Source Toolkit For LLM Distillation

Fast State-of-the-Art Static Embeddings

Uses LlamaIndex for graph building from content. Vector, GraphRAG, and Full text hybrid search. Docling document processing. Configurable with what graph database, vector database, search database,…

Defeating the Training-Inference Mismatch via FP16

NVIDIA Clara Open Models

Awesome Protein Representation Learning

"AI-Trader: Can AI Beat the Market?" Live Trading Bench: https://ai4trade.ai

E2Rank: Your Text Embedding can Also be an Effective and Efficient Listwise Reranker

Official repository for EMNLP 2025 Paper "LimRank: Less is More for Reasoning-Intensive Information Reranking"

xth Place Solution to the Kaggle RSNA Intracranial Aneurysm Detection Competition

Website for "Real Deep Research for AI, Robotics and Beyond"

Official repo for paper "Video-As-Prompt: Unified Semantic Control for Video Generation"

Paper and implementation of UNet-related model.

The code used to train and run inference with MMDocIR

Fast search index for SPLADE sparse retrieval models implemented in Python using Numpy and Numba

torchcomms: a modern PyTorch communications API

Post-training with Tinker