Official repo for: Epipolar Geometry Improves Video Generation Models

GenAI Agent Framework, the Pydantic way

Readest is a modern, feature-rich ebook reader designed for avid readers offering seamless cross-platform access, powerful tools, and an intuitive interface to elevate your reading experience.

📄 Configuration files that enhance Cursor AI editor experience with custom rules and behaviors

Large-scale text-video dataset. 10 million captioned short videos.

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.

Common recipes to run vLLM

tfw your scratch paper becomes your todo list

A high-throughput and memory-efficient inference and serving engine for LLMs

"rsync for cloud storage" - Google Drive, S3, Dropbox, Backblaze B2, One Drive, Swift, Hubic, Wasabi, Google Cloud Storage, Azure Blob, Azure Files, Yandex Files

🍭 Soothing pastel theme for iTerm2

🌈 Convert videos to high-quality GIFs on your Mac

🔬 Visualize attention layers from Stable Diffusion

Major CS conference publication stats (including accepted and submitted) by year.

Attention mappers and visualisation for transformer-based Physical AI policies

Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity. 🔔 Official updates only via twitter @Martin9…

Data Apps & Dashboards for Python. No JavaScript Required.

A final sanity checklist to help your CS paper get accepted, not desk rejected.

A debugging and profiling tool that can trace and visualize python code execution

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

Package for extracting and mapping the results of every single tensor operation in a PyTorch model in one line of code.

Fast and minimalist 3D viewer.

[ICCV 2025] PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videos

Implementing FlowEdit, maybe other inversion techniques for the Wan video generation model