kavishka-dot/vulcan-os: Minimal real-time OS for STM32H7, built from scratch for edge ML inference and on-device training
Minimal real-time OS for STM32H7, built from scratch for edge ML inference and on-device training
Repositories
jakerother/ScikitLearn: Deep Learning Pipelines Optimized via Automated Hyperparameter Tuning and Real-Time Processing on a Scalable Distributed Platform Framework.
Deep Learning Pipelines Optimized via Automated Hyperparameter Tuning and Real-Time Processing on a Scalable Distributed Platform Framework.
zunelyat/PyTorch: Elevating enterprise-grade machine learning with highly concurrent, real-time data processing and adaptive distributed intelligence accelerator.
Elevating enterprise-grade machine learning with highly concurrent, real-time data processing and adaptive distributed intelligence accelerator.
adindazu/AI: Neural-Centric AICore Engine, harnessing real-time insights through scalable, distributed, and adaptive machine learning architecture.
Neural-Centric AICore Engine, harnessing real-time insights through scalable, distributed, and adaptive machine learning architecture.
WeiminXiong/Video2GUI: Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining (ICML2026)
Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining (ICML2026)
agentara/skills: Original and practical skills for AI builders.
Original and practical skills for AI builders.
SoumilBhandari/nanoDLM: The simplest diffusion language model. nanoGPT for diffusion LMs — ~600 lines of pure PyTorch, masked discrete diffusion, char-level tiny shakespeare. Watch text crystallize from noise.
The simplest diffusion language model. nanoGPT for diffusion LMs — ~600 lines of pure PyTorch, masked discrete diffusion, char-level tiny shakespeare. Watch text crystallize from n...
lilh76/CODI: The implementation of AAMAS'26 paper "Boosting Offline MARL under Imbalanced Datasets via Compositional Diffusion Models".
The implementation of AAMAS'26 paper "Boosting Offline MARL under Imbalanced Datasets via Compositional Diffusion Models".
ZJunCher/xiaoyan-ai-dev-assistant: 基于 RAG 混合检索与多轮记忆的 AI 研发助手，支持团队知识问答，也适合新手学习 RAG 应用开发。
基于 RAG 混合检索与多轮记忆的 AI 研发助手，支持团队知识问答，也适合新手学习 RAG 应用开发。
863401402/image-provenance: AI image detector and watermark disruption toolkit (client-side, WIP)
AI image detector and watermark disruption toolkit (client-side, WIP)
Nick-Baumann/gobbo-ai: GRRRBLEHHH!
GRRRBLEHHH!
ProfineAI/profine-cli: Profile your PyTorch code on real GPUs. Get a transparent rewrite. Ship measured speedups before the multi-hour run.
Profile your PyTorch code on real GPUs. Get a transparent rewrite. Ship measured speedups before the multi-hour run.
hanyvert/VectLink: Artificially harmonizing disparate data streams through adaptive machine learning, VectLink orchestrates intelligent, scalable networks.
Artificially harmonizing disparate data streams through adaptive machine learning, VectLink orchestrates intelligent, scalable networks.
Sotomayorlab-UChicago/Public-BayesianSteeredBoltz2: This repo contains our customized version of Boltz-2 that conditions the predictive diffusion model on an arbitrary Bayesian likelihood specified by the user.
This repo contains our customized version of Boltz-2 that conditions the predictive diffusion model on an arbitrary Bayesian likelihood specified by the user.
hazexone/HashPilot: Data-Driven Insights Accelerator for Enterprise Systems, Harnessing Machine-Learning to Optimize Performance. featuring Machine-Learning capabilities
Data-Driven Insights Accelerator for Enterprise Systems, Harnessing Machine-Learning to Optimize Performance. featuring Machine-Learning capabilities
Thiago-code-lab/aws-certified-ai-practitioner-brasil: Repositório com recursos em Português (PT-BR) para estudos da certificação AWS Certified AI Practitioner (AIF-C01)
Repositório com recursos em Português (PT-BR) para estudos da certificação AWS Certified AI Practitioner (AIF-C01)
shamiquekhan/SK-AutoD-ML-Library-for-Training-Curve-Auto-Diagnostician: Auto-diagnose deep learning training pathologies: overfitting, unstable LR, exploding gradients, noisy training, and early stopping issues.
Auto-diagnose deep learning training pathologies: overfitting, unstable LR, exploding gradients, noisy training, and early stopping issues.
Ugness/IMDM: Official implementation of "Infinite Mask Diffusion for Few-Step Distillation" (ICML 2026)
Official implementation of "Infinite Mask Diffusion for Few-Step Distillation" (ICML 2026)
nexu-io/html-anything: ✨ The agentic HTML editor — your local AI agent writes the HTML, you ship it. 🚀 75 Skills × 9 Surfaces (magazine · deck · poster · XHS / tweet · prototype · data report · Hyperframes) 🛡️ Sandboxed preview · 📤 1-click to WeChat / X / Zhihu / HTML / PNG 🔑 Zero API key — Claude Code / Cursor / Codex / Gemini / Copilot / OpenCode / Qwen / Aider.
✨ The agentic HTML editor — your local AI agent writes the HTML, you ship it. 🚀 75 Skills × 9 Surfaces (magazine · deck · poster · XHS / tweet · prototype · data report · Hyperfram...
wittiden/BelAgroOptimization: BelAgroOptimization - проект на базе Pyomo для многоуровневой оптимизации сельскохозяйственного производства. Модель учитывает растениеводство, животноводство, использование удобрений, кормовую базу и экономические параметры предприятия.
BelAgroOptimization - проект на базе Pyomo для многоуровневой оптимизации сельскохозяйственного производства. Модель учитывает растениеводство, животноводство, использование удобре...
Shredded-Pork/Flash-GRPO: [ICML 2026] Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization
[ICML 2026] Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization
radixark/miles_diffusion: [Experimental] Miles-diffusion is an post-training framework for large-scale diffusion model training and production workloads, forked from and co-evolving with miles.
[Experimental] Miles-diffusion is an post-training framework for large-scale diffusion model training and production workloads, forked from and co-evolving with miles.
hackThacker/awesome-ml-llm-case-studies: 800+ real-world ML & LLM system design case studies from 150+ companies Google, Meta, Netflix, Uber, Airbnb & more. Production AI, not theory.
800+ real-world ML & LLM system design case studies from 150+ companies Google, Meta, Netflix, Uber, Airbnb & more. Production AI, not theory.
simonlin1212/a-stock-data: A 股全栈数据工具包 — 6层架构 · 15个端点 · 7个数据源 | AI Skill for China A-Share Market Data
A 股全栈数据工具包 — 6层架构 · 15个端点 · 7个数据源 | AI Skill for China A-Share Market Data