DavidDevGt/MMDiT: MultiModal Diffusion Transformer
MultiModal Diffusion Transformer
Repositories
lucidrains/touch-dreaming: Implementation of the architecture proposed in "Learning Versatile Humanoid Manipulation with Touch Dreaming"
Implementation of the architecture proposed in "Learning Versatile Humanoid Manipulation with Touch Dreaming"
gozen3ji/consulting-pptx-skill: AIにまじなPPTXを作らせるClaude Codeスキル — スライド規約＋38型SlideSpec＋生成パイプライン＋機械チェック
AIにまじなPPTXを作らせるClaude Codeスキル — スライド規約＋38型SlideSpec＋生成パイプライン＋機械チェック
carnot-tech/consulting-pptx-skill: AIにまじなPPTXを作らせるClaude Codeスキル — スライド規約＋62型スライド型カタログ（SlideSpec 36型＋自由記述27パーツ）＋生成パイプライン＋機械チェック
AIにまじなPPTXを作らせるClaude Codeスキル — スライド規約＋62型スライド型カタログ（SlideSpec 36型＋自由記述27パーツ）＋生成パイプライン＋機械チェック
Wyrcan-io/roadmap: A text-first, 12-stage engineering curriculum for AI/ML × Cloud × DevOps × MLOps (12–24 months). Canonical books & official docs only.
A text-first, 12-stage engineering curriculum for AI/ML × Cloud × DevOps × MLOps (12–24 months). Canonical books & official docs only.
icodesign/remote-installer: Quickly install signed iOS and Android builds on real devices over the internet without waiting for Testlight or Play Beta.
Quickly install signed iOS and Android builds on real devices over the internet without waiting for Testlight or Play Beta.
adtexterry-lgtm/unigit-ecosystem: UNIGIT public brand and ecosystem hub — AI should work for everyone.
UNIGIT public brand and ecosystem hub — AI should work for everyone.
ZekunCheng/novoweave: NovoWeave — a conceptual generative protein-design framework (non-functional pseudocode).
NovoWeave — a conceptual generative protein-design framework (non-functional pseudocode).
JaroslavHron/CASUS2026: Introduction to finite elements for multiphase reaction diffusion systems using Firedrake
Introduction to finite elements for multiphase reaction diffusion systems using Firedrake
Yean-Sec/StrikeAgent_AtkBrain-Flash: 由夜安团队研发的AI渗透测试平台，涵盖红队打点、SRC、CTF，特别是在红队领域有极为亮眼的存在
由夜安团队研发的AI渗透测试平台，涵盖红队打点、SRC、CTF，特别是在红队领域有极为亮眼的存在
yuxiangh383/option-return-prediction: Companion code for predicting returns of delta-neutral portfolio.
Companion code for predicting returns of delta-neutral portfolio.
dreamers-laboratory/ai-evaluation-framework: Accuracy, latency p95, and cost benchmarking for model-based solutions, with per-field ground-truth scoring.
Accuracy, latency p95, and cost benchmarking for model-based solutions, with per-field ground-truth scoring.
panghea/ComfyUI-MiniMax-H3-Inpaint-Tools: Rewrite part of a finished MiniMax H3 clip - a rectangle, a time span, or the audio alone - by masking the latent instead of regenerating it. Ten ComfyUI nodes.
Rewrite part of a finished MiniMax H3 clip - a rectangle, a time span, or the audio alone - by masking the latent instead of regenerating it. Ten ComfyUI nodes.
lotchuazzz-crypto/papergraph-mcp: Turn arXiv and LaTeX mathematical papers into theorem dependency graphs for AI agents through MCP.
Turn arXiv and LaTeX mathematical papers into theorem dependency graphs for AI agents through MCP.
shtjww/llm-inference-capacity-handbook: 大模型推理案头手册（开源版）：给定 GPU 算力，一个模型能扛多少 QPS？三层模型 × 三面墙 × 排队论 × 开环压测
大模型推理案头手册（开源版）：给定 GPU 算力，一个模型能扛多少 QPS？三层模型 × 三面墙 × 排队论 × 开环压测
BoardUI/boardui: React design system for agentic interfaces. Every free BoardUI component as source, with a working AI chat app on your own model key as the homepage.
React design system for agentic interfaces. Every free BoardUI component as source, with a working AI chat app on your own model key as the homepage.
coleam00/ai-software-factory: A repository that ships without anyone reading the diff: GitHub issues in, merged pull requests out, with the gates that make that defensible.
A repository that ships without anyone reading the diff: GitHub issues in, merged pull requests out, with the gates that make that defensible.
jarrenrocks/bot-crossing: A video game for AI agents.
A video game for AI agents.
hbofz/NeSLE: GPU-native NES emulator + RL stack: thousands of parallel NES envs on one CUDA GPU, training PPO agents on Super Mario Bros.
GPU-native NES emulator + RL stack: thousands of parallel NES envs on one CUDA GPU, training PPO agents on Super Mario Bros.
Liora2050348900/dsh-token-optimizer: Layered token optimization plugin for DeepSeek Harness: text-to-image for long content, incremental diff on repeated file reads, structure-aware compression, result caching, deduplication, sampling, context pruning, and per-session tool schema trimming. Reversible and pluggable — reduces context overhead and API spend.
Layered token optimization plugin for DeepSeek Harness: text-to-image for long content, incremental diff on repeated file reads, structure-aware compression, result caching, dedupl...
LunarXuan/image-prompt-reverse: High-fidelity AI image prompt reverse-engineering skill for Codex
High-fidelity AI image prompt reverse-engineering skill for Codex
RandyHaylor/krea2-tiled-diffusion-comfyui: ComfyUI custom node: Krea 2 tiled diffusion, fusing latent tiles every sampling step rather than blending finished tiles
ComfyUI custom node: Krea 2 tiled diffusion, fusing latent tiles every sampling step rather than blending finished tiles
Laleeth/The-AI-Engineer-s-Playbook: Practical engineering knowledge for building and operating production AI systems — LLMs, RAG, agents, inference, evaluation, system design, and AI infrastructure.
Practical engineering knowledge for building and operating production AI systems — LLMs, RAG, agents, inference, evaluation, system design, and AI infrastructure.