Circuit diagrams and firmware source code for Gboard DIY keyboards

😩「能不能好好说话？」 拼音首字母缩写翻译工具

This is an implementation of the Point Mask Transformer model for outdoor point cloud semantic segmentation.

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, Llava, GLM4v, Ph…

Conversion between Traditional and Simplified Chinese

Streamline Integration Framework

[ICLR 2025] You Only Sample Once: Taming One-Step Text-To-Image Synthesis by Self-Cooperative Diffusion GANs

[ECCVW 2022] The codes for the work "Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation"

NVIDIA Image Scaling SDK

Fast and memory-efficient exact attention

demo: @greater_repeater_bot

[CVPR 2025] DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation & [ICLR 2024] DFormer & [NeuriPS 2025] OmniSegmentor

Python library to use Pleias-RAG models

📝 EchoAI: Explore knowledges with your own studymate.

The official repository for tariff

Yet Another Document Translator

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

A list of papers and datasets about point cloud analysis (processing)

This repo is meant to serve as a guide for Machine Learning/AI technical interviews.

Getting crystal-like representations with harmonic loss

Guess What Moves: Unsupervised Video and Image Segmentation by Anticipating Motion

PytorchAutoDrive: Segmentation models (ERFNet, ENet, DeepLab, FCN...) and Lane detection models (SCNN, RESA, LSTR, LaneATT, BézierLaneNet...) based on PyTorch with fast training, visualization, ben…

A fine-tuned model from Qwen2-1.5B-Instruct, capable of handling sensitive topics like violence, explicit content. / 从 Qwen2-1.5B-Instruct 微调，能处理各类敏感话题

Official GitHub repository for Argoverse dataset

The official Python client for the Hugging Face Hub.