whiteboard / infinite canvas SDK

Create apps with Gemini

TensorZero creates a feedback loop for optimizing LLM applications — turning production data into smarter, faster, and cheaper models.

Repo for paper "T2Vid: Translating Long Text into Multi-Image is the Catalyst for Video-LLMs"

An open-source screen recorder built with web technology

Code for MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data

Collection of awesome LLM apps with RAG using OpenAI, Anthropic, Gemini and opensource models.

AWM: Agent Workflow Memory

Agentless🐱: an agentless approach to automatically solve software development problems

SPARS3R: Semantic Prior Alignment and Regularization for Sparse 3D Reconstruction

Repo for Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent

A runtime for writing reliable asynchronous applications with Rust. Provides I/O, networking, scheduling, timers, ...

Code for the book "Rust Web Development"

🐙 OctoBase is the open-source database behind AFFiNE, local-first, yet collaborative. A light-weight, scalable, data engine written in Rust.

A distributed thread-per-core document database

Building AI agents, atomically

Code release of our paper "DI-PCG: Diffusion-based Efficient Inverse Procedural Content Generation for High-quality 3D Asset Creation".

RoMeO: Robust Metric Visual Odometry

Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation".

tiny vision language model

Official implementation for the paper "Full-Order Sampling-Based MPC for Torque-Level Locomotion Control via Diffusion-Style Annealing". DIAL-MPC is a novel sampling-based MPC framework for legged …

A generative world for general-purpose robotics & embodied AI learning.

Adapting the AlphaZero algorithm to remove the need of execution traces to train NPI.

🕹️ A diverse suite of scalable reinforcement learning environments in JAX

Code Repository for Angular Front To Back, Published by Packt

Official repository for "AM-RADIO: Reduce All Domains Into One"

Scaling Properties of Diffusion Models For Perceptual Tasks

Approaching (Almost) Any Machine Learning Problem中译版，在线文档地址：https://ytzfhqs.github.io/AAAMLP-CN/

Code and Data for Our NeurIPS 2024 paper "AMOR: A Recipe for Building Adaptable Modular Knowledge Agents Through Process Feedback"