Enping-Hu/minimind-deep-dive: 逐行对照 MiniMind 源码精读、并延伸到大模型技术体系的中文学习笔记 —— 预训练 / SFT / DPO / PPO / GRPO、训练机制、MiniMind2→3 版本对照、真实实验证据。
逐行对照 MiniMind 源码精读、并延伸到大模型技术体系的中文学习笔记 —— 预训练 / SFT / DPO / PPO / GRPO、训练机制、MiniMind2→3 版本对照、真实实验证据。
Repositories
nyomnisgarz/amd-diffusion-lab: Stable Diffusion Training on AMD GPUs — DreamBooth, LoRA, SDXL, ControlNet
Stable Diffusion Training on AMD GPUs — DreamBooth, LoRA, SDXL, ControlNet
SantanderAI/causal-perception-implementation: Machine learning research code for causal perception: comparing competing structural causal models (SCMs) via interventional and counterfactual distributions, applied to fair credit decisions. Open source by Santander AI Lab.
Machine learning research code for causal perception: comparing competing structural causal models (SCMs) via interventional and counterfactual distributions, applied to fair credi...
Moh4696/free-ai-models: 10 legit ways to access major AI models (GPT, Claude, Llama, DeepSeek & more) for FREE — step-by-step guides, no subscription, no card.
10 legit ways to access major AI models (GPT, Claude, Llama, DeepSeek & more) for FREE — step-by-step guides, no subscription, no card.
ransjnr/biopython-ml-handbook: Biopython for Machine Learning and Bioinformatics
Biopython for Machine Learning and Bioinformatics
Karovia/fullstack-ai-agent-roadmap: 🎯 从零基础到 AI Agent 全栈工程师 · 110 个详细教程 · 58 万字 · 400+ GitHub 项目精选 · Obsidian 友好 · 中文
🎯 从零基础到 AI Agent 全栈工程师 · 110 个详细教程 · 58 万字 · 400+ GitHub 项目精选 · Obsidian 友好 · 中文
real-stanford/dfexpense: Code for "Diffusion Filtered Exploration via Ensembles (DF-ExpEnse)" (ICML 2026)
Code for "Diffusion Filtered Exploration via Ensembles (DF-ExpEnse)" (ICML 2026)
GaoDalie/-DiffusionGemma-Dflash-TurboQuant-RAG: In June 2026, Google released a rather unusual AI. Its name is "DiffusionGemma."
In June 2026, Google released a rather unusual AI. Its name is "DiffusionGemma."
jwangkun/loops: Loop（循环） 是一种用于AI编程助手（如 Claude Code、Cursor）的自动化工作流指令集。它通过"执行→检查→修复→重复"的闭环模式，让AI能够自主完成开发任务，直到达到预设目标。
Loop（循环） 是一种用于AI编程助手（如 Claude Code、Cursor）的自动化工作流指令集。它通过"执行→检查→修复→重复"的闭环模式，让AI能够自主完成开发任务，直到达到预设目标。
lidge-jun/opencodex: Universal provider proxy for OpenAI Codex — use any LLM with Codex CLI, App, and SDK
Universal provider proxy for OpenAI Codex — use any LLM with Codex CLI, App, and SDK
SamerMashhour/mpm-workflow: Python workflow for regional mineral prospectivity mapping with synthetic geoscience examples.
Python workflow for regional mineral prospectivity mapping with synthetic geoscience examples.
hbddevos/PumpFun-Trainer_V1: An advanced AI‑driven trading utility for Solana meme‑coins, featuring sniper, auto‑sell, MEV protection, multi‑wallet, alerts, and price monitoring.
An advanced AI‑driven trading utility for Solana meme‑coins, featuring sniper, auto‑sell, MEV protection, multi‑wallet, alerts, and price monitoring.
alkhudarigroupuae/PumpFun-Trainer_V1: An advanced AI‑driven trading utility for Solana meme‑coins, featuring sniper, auto‑sell, MEV protection, multi‑wallet, alerts, and price monitoring.
An advanced AI‑driven trading utility for Solana meme‑coins, featuring sniper, auto‑sell, MEV protection, multi‑wallet, alerts, and price monitoring.
axisvoiceupgrade/Topaz-Photo-AI-2026: Topaz Photo AI workflow — denoise, sharpen, upscale and batch enhancement for Windows photographers.
Topaz Photo AI workflow — denoise, sharpen, upscale and batch enhancement for Windows photographers.
tianchong-zerotemp/dianxing: DianXing - AI-Driven End-to-End Code Security Auditing
DianXing - AI-Driven End-to-End Code Security Auditing
QingtaoPan/ELDiff: [ECCV 2026] Official code for paper: ELDiff: When Evidential Learning Meets Text-to-Image Diffusion
[ECCV 2026] Official code for paper: ELDiff: When Evidential Learning Meets Text-to-Image Diffusion
flatkey-ai/awesome-images: Try flatkey.ai for 40% saving! Generate practical images ready for all your work needs!!!
Try flatkey.ai for 40% saving! Generate practical images ready for all your work needs!!!
KTH-RPL/HilDA: HilDA: Hierarchical Distillation with Diffusion for Advancing Self-Supervised LiDAR Pre-training
HilDA: Hierarchical Distillation with Diffusion for Advancing Self-Supervised LiDAR Pre-training
FareedKhan-dev/agentic-quantum-computing: End-to-end agentic quantum-ML pipeline: PennyLane GPU quantum-kernel anomaly detection + LangGraph multi-agent system + locally-hosted Qwen3-14B, benchmarked across network-intrusion, LHC physics, and fraud.
End-to-end agentic quantum-ML pipeline: PennyLane GPU quantum-kernel anomaly detection + LangGraph multi-agent system + locally-hosted Qwen3-14B, benchmarked across network-intrusi...
YOGRAJGARAD/CAUSAL-SEMANTIC-GENERATIVE-AI: A Research-Oriented Causal AI Project focused on Learning Semantic Representations to Improve Robustness and Generalization across Unseen Data Distributions.
A Research-Oriented Causal AI Project focused on Learning Semantic Representations to Improve Robustness and Generalization across Unseen Data Distributions.
shy3130/tickflow-stock-panel: 自托管、零运维的 A 股「选股 + 监控 + 回测」量化工作台 | 基于 TickFlow 数据 | 能力驱动适配全档位订阅 | 自由接入第三方扩展数据(Tushare 等)
自托管、零运维的 A 股「选股 + 监控 + 回测」量化工作台 | 基于 TickFlow 数据 | 能力驱动适配全档位订阅 | 自由接入第三方扩展数据(Tushare 等)
boobyuuuu/two-zone-diffusion-model: Analytic homogeneous and two-zone diffusion models for nearby cosmic-ray sources. Published Article (On the Contribution of Local Sources to the Galactic Cosmic-Ray Spectrum: An Exact Series Solution for Two-Zone Diffusion)
Analytic homogeneous and two-zone diffusion models for nearby cosmic-ray sources. Published Article (On the Contribution of Local Sources to the Galactic Cosmic-Ray Spectrum: An Ex...
Bayrii/text2image-multilingual-retrieval: Multilingual text-to-image retrieval with fine-tuned mCLIP. Search a 5,000-image gallery by text (6 languages), voice (Whisper), or image — no generative AI, pure retrieval. FastAPI + React.
Multilingual text-to-image retrieval with fine-tuned mCLIP. Search a 5,000-image gallery by text (6 languages), voice (Whisper), or image — no generative AI, pure retrieval. FastAP...