Robby955/FormalSLT: Machine-verified statistical learning theory in Lean 4 — 45 modules, 19,521 lines, 0 sorry
Machine-verified statistical learning theory in Lean 4 — 45 modules, 19,521 lines, 0 sorry
Repositories
laishiwen/sven-family: Sven Family is an AI-native product suite that connects creation, collaboration, publishing, and operations into one integrated platform.
Sven Family is an AI-native product suite that connects creation, collaboration, publishing, and operations into one integrated platform.
Mixomo/LM_Studio_Server_Batch_Image_Captioner: Minimal CustomTkinter app for captioning many images through LM Studio's local OpenAI-compatible server to create training datasets for text-to-image models such as Flux, Qwen, Z-Image, Ernie Image, etc.. Each image is sent as a separate request, so context does not accumulate across the batch.
Minimal CustomTkinter app for captioning many images through LM Studio's local OpenAI-compatible server to create training datasets for text-to-image models such as Flux, Qwen, Z-I...
nooncheetahstart/Kahoot-tools-AI: Kahoot || Kahoot helper || Kahoot tools || Kahoot ai
Kahoot || Kahoot helper || Kahoot tools || Kahoot ai
Outpostshewharf/Edgenuity-AI-Helper: edgenuity mod menu || ai chatgpt || edgenuity ai helper || edgenuity
edgenuity mod menu || ai chatgpt || edgenuity ai helper || edgenuity
dxlong2000/AARD: A²RD: Agentic Autoregressive Diffusion for Long Video Consistency
A²RD: Agentic Autoregressive Diffusion for Long Video Consistency
DenAB-NVS/submarine: Sovereign, depth-adaptive AI memory. Open source. Local-first. Model-agnostic.
Sovereign, depth-adaptive AI memory. Open source. Local-first. Model-agnostic.
alfredplpl/T2I-Ja: Text to image generation for Japanese-like Images
Text to image generation for Japanese-like Images
TorMatzAndren/ChronoGit: Deterministic Git Time Machine UI focused on truth, safety, learning, and local-first workflows.
Deterministic Git Time Machine UI focused on truth, safety, learning, and local-first workflows.
wfz666/ICML26-attention-sink: Are attention sinks necessary in diffusion transformers? Code for dynamic sink detection and causal suppression experiments in SD3/SDXL.
Are attention sinks necessary in diffusion transformers? Code for dynamic sink detection and causal suppression experiments in SD3/SDXL.
UnveilStudio/morpheus-cam: Real-time body-driven Stable Diffusion: AMD XDNA2 NPU + Radeon iGPU + NVIDIA CUDA. Three Spout outputs. Built and tested on Razer Blade 14 (2025).
Real-time body-driven Stable Diffusion: AMD XDNA2 NPU + Radeon iGPU + NVIDIA CUDA. Three Spout outputs. Built and tested on Razer Blade 14 (2025).
kerlos/pordee: ตอบสั้นๆ ก็เข้าใจแบบพอดีๆ
ตอบสั้นๆ ก็เข้าใจแบบพอดีๆ
Sudheer13351/Generative-AI-Fake-News-detection: This project uses advanced NLP (BART & T5 models) to combat global misinformation. By leveraging Zero-Shot Classification, it detects fake news across multiple languages without needing vast labeled datasets. Beyond detection, it rewrites content for clarity, providing a powerful, flexible tool to ensure digital trust and safety.
This project uses advanced NLP (BART & T5 models) to combat global misinformation. By leveraging Zero-Shot Classification, it detects fake news across multiple languages without ne...
pouyanfallahi/diabetes-clinical-decision-support: Machine Learning‑Based Clinical Decision Support for Diabetes Prediction — A complete B.Sc. thesis re‑implementation: data preprocessing, dual‑method feature selection, and evaluation of Logistic Regression, Decision Tree, and SVM on the Pima Indians Diabetes Dataset. Includes the full Jupyter notebook and LaTeX report.
Machine Learning‑Based Clinical Decision Support for Diabetes Prediction — A complete B.Sc. thesis re‑implementation: data preprocessing, dual‑method feature selection, and evaluat...
byliutao/CDM: Continuous-Time Distribution Matching for Few-Step Diffusion Distillation👏
Continuous-Time Distribution Matching for Few-Step Diffusion Distillation👏
iam567/LifeManga: ios swift swiftui openai gpt-image manga ai-art
ios swift swiftui openai gpt-image manga ai-art
yanxiaoxiang123/dl-reproducibility-skills: Deep learning reproducibility toolkit v3 — 2025 AAAI/Nature reproducibility standards, PyTorch 2.7 patterns, FSDP2, experiment tracking, full RNG checkpointing
Deep learning reproducibility toolkit v3 — 2025 AAAI/Nature reproducibility standards, PyTorch 2.7 patterns, FSDP2, experiment tracking, full RNG checkpointing
skhalidmahmud/Gesture-to-Speech: Real-time Sign Language to Speech translator powered by TensorFlow and MediaPipe. Features a modern React.js dashboard for seamless AI-driven communication.
Real-time Sign Language to Speech translator powered by TensorFlow and MediaPipe. Features a modern React.js dashboard for seamless AI-driven communication.
Sayhi-bzb/AIEden: an LLM-native world and civilization
an LLM-native world and civilization
AD-Styles/diffusion-models-from-scratch: Implementing DDPM, U-Net, Classifier-Free Guidance, and CLIP-style Cosine Similarity from scratch on FashionMNIST — based on NVIDIA DLI Generative AI with Diffusion Models curriculum. / NVIDIA DLI 'Generative AI with Diffusion Models' 커리큘럼 기반으로 DDPM, U-Net, CFG, CLIP 코사인 유사도를 처음부터 직접 구현한 생성형 AI 포트폴리오.
Implementing DDPM, U-Net, Classifier-Free Guidance, and CLIP-style Cosine Similarity from scratch on FashionMNIST — based on NVIDIA DLI Generative AI with Diffusion Models curricul...
Mutual-Luo/Awesome-Sparse-Attention-Video-Diffusion: Awesome Video Diffusion Transformers Sparse Attention Papers
Awesome Video Diffusion Transformers Sparse Attention Papers
mohdsubhan0987-cloud/Generative-AI-Chatbot-with-RAG: Built a domain-specific Q&A chatbot using LangChain, OpenAI GPT-4, and ChromaDB vector store with hybrid retrieval; achieved 92% answer accuracy and reduced hallucination rate by 40% • Deployed as REST API via FastAPI and containerized with Docker for scalable cloud deployment
Built a domain-specific Q&A chatbot using LangChain, OpenAI GPT-4, and ChromaDB vector store with hybrid retrieval; achieved 92% answer accuracy and reduced hallucination rate by 4...
aqlaboratory/genie3: Genie 3 is a fast, all-atom SE(3)-equivariant diffusion model for protein design. It achieves state-of-the-art performance on unconditional generation, motif scaffolding, and binder design while retaining the computational efficiency of equivariant architectures.
Genie 3 is a fast, all-atom SE(3)-equivariant diffusion model for protein design. It achieves state-of-the-art performance on unconditional generation, motif scaffolding, and binde...