HRSID: high resolution sar images dataset for ship detection, semantic segmentation, and instance segmentation tasks.

[ICLR 2025] Video Action Differencing

Build your own visual reasoning model

Training AI for Super Smash Bros. Melee

MiniCPM-o 2.6: A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone

A high-performance distributed file system designed to address the challenges of AI training and inference workloads.

Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama mode…

OctoTools: An agentic framework with extensible tools for complex reasoning

Tiny data-over-sound library

Solve mysteries through SQL.

Verdict is a library for scaling judge-time compute.

A large-scale fine-grained SAR vehicle dataset and benchmark

Implementation of the new SOTA for model based RL, from the paper "Improving Transformer World Models for Data-Efficient RL", in Pytorch

A simple, hackable text-to-speech system in PyTorch and MLX

An implementation of numbered theorem environments in typst

SBX: Stable Baselines Jax (SB3 + Jax) RL algorithms

🤗 smolagents: a barebones library for agents. Agents write python code to call tools and orchestrate other agents.

Official code for "Learning Neural Acoustic Fields" (NeurIPS 2022)

Lightweight flow-level simulator for inter-node service coordination. Useful for testing coordination algorithms, which scale & place service components and decide flow scheduling.

An open, minimalist Gymnasium environment for autonomous coordination in wireless mobile networks.

Getting crystal-like representations with harmonic loss

Textbook on reinforcement learning from human feedback

C++ class that uses RPC coefficients to map an object space coordinate represented in Latitude, Longitude, and Altitude to a sensor position represented in X,Y

TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation

Self-Supervised Learning for SAR ATR with a Joint-Embedding Predictive Architecture

Fully open reproduction of DeepSeek-R1

Use a sparse autoencoder to steer R1 towards American values.

deepseek running locally in your browser