Starred repositories
Qwen-Image-Lightning: Speed up Qwen-Image model with distillation
Zero-dependency browser video editor that AI agents can drive — JSON timeline, MCP + REST, live-reloading UI
Ridiculously fast decompression at good ratios. misa77 is 1.5-3x faster than LZ4 for decompression on x86 and ARM (with better ratios!).
Masked Depth Modeling for Spatial Perception
Vision as Unified Multimodal Generation
【SIGGRAPH Asia 2026】Official repo for the paper "PanoWorld: A Generative Spatial World Model for Consistent Whole-House Panorama Synthesis"
[ECCV 2026] Any2Full: Prompting Depth Anything for Depth Completion in One Stage
CPR-VCODEX : Improving the reading experience and consistency for Xteink X4. One-click install or edit stats via the link below: ⬇⬇
A hardware-independent SDK for building e-paper reader firmware.
A PyTorch Library for Accelerating 3D Deep Learning Research
Firmware for the Xteink X3 and X4 e-readers
Matlab and Python toolbox for fast Total Variation proximity operators
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Official implementation of UniSHARP: Universal Sharp Monocular View Synthesis
A Python package for generating HDL wrappers and top modules for HDL sources
Chainloader for Game and Watch for Retro-go and Mario/Zelda stock firmware
Comparison of image-to-3D reconstruction methods
A macOS menu bar application that monitors AI coding assistant usage quotas. Keep track of your Claude, Codex, Antigravity ,and Gemini usage at a glance.
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
Pre-built GNU toolchain from ARM Cortex-M & Cortex-R processors (Cortex-M0/M0+/M3/M4/M7, Cortex-R4/R5/R7).
Stage 0 bootloader for G&W anniversary console
Easy token price estimates for 400+ LLMs. TokenOps.