Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

Fish-like autosuggestions for zsh

Parallelized pytorch implementation of iCEM

Model Predictive Path Integral (MPPI) with approximate dynamics implemented in pytorch

Generate production-quality SVG+PNG technical diagrams from natural language. 7 styles, UML support, and AI/Agent workflow patterns.

Minimal guide to configure Opencode to use free Nemotron 3 Super models.

A web-based collaborative LaTeX editor

An extremely fast Python linter and code formatter, written in Rust.

ZMQ-based inference server that exposes robot simulators (e.g. LIBERO) over TCP for remote policy evaluation

An all-in-one enhancement suite for Google Gemini & AI Studio - timeline navigation, folder management, prompt library, and chat export in one powerful extension. / Google Gemini & AI Studio 全能增强插件…

[ICLR'26] This repository is the implementation of "3D Aware Region Prompted Vision Language Model"

PaperBanana: Automating Academic Illustration For AI Scientists

Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

一个基于nano banana pro🍌的原生AI PPT生成应用，迈向＂Vibe PPT＂; 支持上传任意模板图片，上传任意素材&智能解析，一句话/大纲/页面描述自动生成PPT，口头修改指定区域、一键导出可编辑ppt - An AI-native slides generator based on nano banana pro🍌

Unofficial implementation of the Dreamer 4 world model in PyTorch.

[ICML 2026] Official repo for "DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models"

Material for gpu-mode lectures

Benchmarking Knowledge Transfer in Lifelong Robot Learning

Open-source unified multimodal model

A high-throughput and memory-efficient inference and serving engine for LLMs

Code and models for the paper "One Transformer Fits All Distributions in Multi-Modal Diffusion"

TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

LLaDA2.0 is the diffusion language model series developed by InclusionAI team, Ant Group.

"Paper2Slides: From Paper to Presentation in One Click"

Official inference repo for FLUX.2 models