-
Grubhub
- Chicago, Illinois
-
05:35
(UTC +08:00)
Highlights
Starred repositories
INFTY Engine: An Optimization Toolkit to Support Continual AI
Auto-Manage Your Personal Task Context with AI.
UniVoice: Unifying Autoregressive ASR and Flow-Matching based TTS with Large Language Models
RLinf is a flexible and scalable open-source infrastructure designed for post-training foundation models (LLMs, VLMs, VLAs) via reinforcement learning.
"LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?"
🛠️ DeepAgent: A General Reasoning Agent with Scalable Toolsets
OmniNWM: Omniscient Navigation World Models for Autonomous Driving
Zen7 Payment Agent is the first implementation project of DePA (Decentralized Payment Agent), pioneers next-generation intelligent payment infrastructure.
Enterprise-grade, commercial-friendly agentic workflow platform for building next-generation SuperAgents.
一个用Go语言编写的性能强大的域名可用性检查扫描工具 A high-performance domain availability scanning tool written in Go.
UR2: Unify RAG and Reasoning through Reinforcement Learning
Open, reproducible benchmarks and practical recipes to reduce I/O bottlenecks and improve end-to-end performance in AI training and bulk inference.
CPG-SPMT: Control-oriented Parameter-Grouped Single Particle Model with Thermal effects
[IROS 2025] MarineGym: A High-Performance Reinforcement Learning Platform for Underwater Robotics
Dataset and evaluation code of ISDrama(ACM-MM 2025): Immersive Spatial Drama Generation through Multimodal Prompting
Redis/Valkey Compatible Distributed Transactional Key-Value Store
Klavis AI (YC X25): MCP integration platforms that let AI agents use tools reliably at any scale
🐾 PawHaven — An open-source, enterprise-grade project built with React, NestJS, pnpm, and a Monorepo architecture — designed to help stray animals find safety and care.
Official Repo of "RobustFlow: Towards Robust Agentic Workflow Generation"
Go bindings for the CUDA Driver and Runtime APIs, cuBLAS, and cuDNN.
An adaptive sampling framework for Reinforce-style LLM post training.
minerproxy矿池中转,原创minerproxy,唯一正版,性能强大, 功能齐全, 9000台无压力不崩溃,BTC ETC ETH LTC等全币种无损抽水,体验拉满的minerproxy, 软防CC, 动态难度调整抽水,不爆内存。支持绝大部分币种的转发、加密、自定义抽水、精确到单台设备的24小时数据统计、自定义隧道推送工具、修改矿池本地算力
[EMNLP'25] s3 - ⚡ Efficient & Effective Search Agent Training via RL for RAG (RLVR for Search with Minimal Data)
High-performance Go BLAS/LAPACK with Intel MKL/OpenBLAS acceleration support
告别加班,拥抱高效! 一款让开发者爱不释手的现代化中后台管理系统模板。基于 Vue 3 + TypeScript + Naive UI 最新技术栈,采用 Bun + Vite 双引擎驱动实现毫秒级热更新,让你的开发速度飞起来!内置 30+ 精心打磨的业务组件和 30+ 完整演示页面,拒绝重复造轮子,复制粘贴即可使用。配备完整 RBAC 权限体系、7个实用自定义指令和响应式设计,从个人项目到企…
VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
Lumina-DiMOO - An Open-Sourced Multi-Modal Large Diffusion Language Model