Repositories
undeemed/a2d: Convert open-weight autoregressive LLMs into diffusion language models - locally, with one command
Convert open-weight autoregressive LLMs into diffusion language models - locally, with one command
uzairansaruzi/hermex: Native iPhone app for your Hermes agent
Native iPhone app for your Hermes agent
nousheentabassum/nousheentabassum: Computer Science Student | Full-Stack Developer | AI & Machine Learning Enthusiast | Building scalable applications with React, Node.js & Python.
Computer Science Student | Full-Stack Developer | AI & Machine Learning Enthusiast | Building scalable applications with React, Node.js & Python.
nousheentabassum/Machine-Learning: Collection of Machine Learning, Statistics, and Data Science notebooks covering EDA, hypothesis testing, regression, classification, clustering, ensemble learning, and association rule mining using Python.
Collection of Machine Learning, Statistics, and Data Science notebooks covering EDA, hypothesis testing, regression, classification, clustering, ensemble learning, and association ...
Brain0-ai/brain0: The black box for AI-written code. Passive decision graph linking every commit to the agent prompts behind it: drift detection, DLP audit of what agents read, evidence-driven risk, MCP memory for coding agents, signed provenance attestations. One command, offline by default.
The black box for AI-written code. Passive decision graph linking every commit to the agent prompts behind it: drift detection, DLP audit of what agents read, evidence-driven risk,...
Optimizer077/awesome-language-diffusion: Awesome Language Diffusion - curated list of 311+ papers, models, and resources on diffusion models for language.
Awesome Language Diffusion - curated list of 311+ papers, models, and resources on diffusion models for language.
parthupman/care: CARE — Covariance-Aware Retained-subspace Erasure. Closed-form, training-free concept erasure for diffusion models with an explicit kept-subspace preservation guarantee.
CARE — Covariance-Aware Retained-subspace Erasure. Closed-form, training-free concept erasure for diffusion models with an explicit kept-subspace preservation guarantee.
Optimizer077/language-diffusion-models: From-scratch, verified course on language diffusion models: 5 runnable notebooks + an interactive in-browser playground.
From-scratch, verified course on language diffusion models: 5 runnable notebooks + an interactive in-browser playground.
TheVantaDev/BOI-Hackathon: The objective of this project is to develop BOI Sentinel AI, a Generative AI powered malware investigation and risk assessment platform capable of automatically analyzing suspicious Android application packages APKs and identifying fraudulent or malicious behavior that may threaten banking customers and digital financial services.
The objective of this project is to develop BOI Sentinel AI, a Generative AI powered malware investigation and risk assessment platform capable of automatically analyzing suspiciou...
Siddhartha17-git/Deep-Learning-: This project demonstrates a simple application of deep learning libraries, with results presented through an interactive web interface.
This project demonstrates a simple application of deep learning libraries, with results presented through an interactive web interface.
woodoodanyysamp0/Lossless-Pro-2026: Advanced real-time video scaling and frame generation utility featuring high-precision spatial upscaling algorithms and low-overhead machine learning frame interpolation.
Advanced real-time video scaling and frame generation utility featuring high-precision spatial upscaling algorithms and low-overhead machine learning frame interpolation.
veryCoolTimo/imagegen-skills: Turn a one-line idea into a production-grade, copy-paste-ready AI image prompt for posters, landing and UI mockups, ads, game art, and logos. A Claude Code skill optimized for gpt-image-2. MIT.
Turn a one-line idea into a production-grade, copy-paste-ready AI image prompt for posters, landing and UI mockups, ads, game art, and logos. A Claude Code skill optimized for gpt-...
DexZane/awesome-web-prompts: A curated collection of AI prompts behind stunning, creative websites
A curated collection of AI prompts behind stunning, creative websites
amitshekhariitbhu/ai-agents-tutorial: Learn AI Agents step by step, from scratch - from function calling to agent loops to multi-agent systems, orchestration, and evaluation.
Learn AI Agents step by step, from scratch - from function calling to agent loops to multi-agent systems, orchestration, and evaluation.
chrisipanaque/qwen-lora-finetune: Fine-tune Qwen2.5-Coder for code generation on your own dataset using QLoRA. Train on JSONL instruction-response pairs and produce a shareable ~16 MB LoRA adapter.
Fine-tune Qwen2.5-Coder for code generation on your own dataset using QLoRA. Train on JSONL instruction-response pairs and produce a shareable ~16 MB LoRA adapter.
Xingyu-Zheng/MrFlow: Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling
Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling
Zsun79/ConferenceWatch: An Agent Skill to watch the deadlines of latest AI conference.
An Agent Skill to watch the deadlines of latest AI conference.
LonglongaaaGo/UltraDiffEdit: TNNLS 2026 🔥 Tuning-Free Latent Diffusion Models for Ultrahigh-Resolution Image Editing
TNNLS 2026 🔥 Tuning-Free Latent Diffusion Models for Ultrahigh-Resolution Image Editing
MONZikWasTaken/Framegen: Real-time neural frame interpolation in the browser: hand-written WGSL runtime on raw WebGPU, 2.9 MB model, 2x-6x any at 3-4 ms per frame. Chrome extension.
Real-time neural frame interpolation in the browser: hand-written WGSL runtime on raw WebGPU, 2.9 MB model, 2x-6x any at 3-4 ms per frame. Chrome extension.
gerwang/DiffReg-PBIR: Physics-based inverse rendering regularized by a diffusion prior used as a material similarity kernel — not fixed targets — to recover relightable geometry, materials, and lighting from multi-view images. ECCV 2026.
Physics-based inverse rendering regularized by a diffusion prior used as a material similarity kernel — not fixed targets — to recover relightable geometry, materials, and lighting...
Aevella/polaris-local-first: Local-first AI workspace for structured context, collaborators, and portable backups.
Local-first AI workspace for structured context, collaborators, and portable backups.
