- New York City
Stars
[NeurIPS'25] KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems
Making ENS domains Google-visible - Open-source architecture for Web3 identity SEO and Knowledge Panel optimization
OmniNWM: Omniscient Navigation World Models for Autonomous Driving
Open-source ad fraud detection for small businesses using machine learning. Detect click fraud and bot traffic from Google Ads, Facebook Ads, and other platforms. Completely free.
INFTY Engine: An Optimization Toolkit to Support Continual AI
"LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?"
🏆 Research implementation of W-5 Multi-Agent AI Consensus Framework for football match outcome prediction | AI-powered sports analytics using LLMs + Machine Learning | 85.9% accuracy
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.
A curated list of awesome papers, resources, and tools for Visual Prompt Tuning (VPT).
CPG-SPMT: Control-oriented Parameter-Grouped Single Particle Model with Thermal effects
the official code for ESCNet: Entity-enhanced and Stance Checking Network for Multi-modal Fact-Checking
[IROS 2025] MarineGym: A High-Performance Reinforcement Learning Platform for Underwater Robotics
🐾 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.
https://dev.to/answeryt/the-demo-spell-and-production-dilemma-of-ai-agents-how-i-built-a-self-learning-agent-system-4okk
🔥[VLDB'26] Official repository for the paper "LEAD: Iterative Data Selection for Efficient LLM Instruction Tuning".
Official Repo of "RobustFlow: Towards Robust Agentic Workflow Generation"
TVM Documentation in Chinese Simplified / TVM 中文文档
MarkDiffusion: An Open-Source Toolkit for Generative Watermarking of Latent Diffusion Models
[CVPR'25] Official PyTorch implementation of AvatarArtist: Open-Domain 4D Avatarization.
**Deep Video Discovery (DVD)** is a deep-research style question answering agent designed for understanding extra-long videos.
[EMNLP2025]Official implementation: Agent-style vision question answer in Autonomous Driving!
🚀 EvoAgentX: Building a Self-Evolving Ecosystem of AI Agents
The code of AMoPO: Adaptive Multi-objective Preference Optimization without Rewards and References.
( TPAMI2022 / CVPR2019 Oral ) Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation
Nexent is a zero-code platform for auto-generating agents — no orchestration, no complex drag-and-drop required. Nexent also offers powerful capabilities for agent running control, data processing …