assistant tools for attention visualization in deep learning

Depth-Consistent 3D Gaussian Splatting

PyTorch implementation of JiT https://arxiv.org/abs/2511.13720

🌞 CareGPT (关怀GPT)是一个医疗大语言模型，同时它集合了数十个公开可用的医疗微调数据集和开放可用的医疗大语言模型，包含LLM的训练、测评、部署等以促进医疗LLM快速发展。Medical LLM, Open Source Driven for a Healthy Future.

LiDAR-GS++: Improving LiDAR Gaussian Reconstruction via Diffusion Priors

[ACM CSUR 2025] Understanding World or Predicting Future? A Comprehensive Survey of World Models

[PKU EPIC Lab] 面向小白的具身智能入门指南

A curated list of papers & resources on depth estimation & depth completion with foundation models

A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.

We are committed to the open-sourcing quantitative knowledge, aiming to bridge the information gap between the domestic and international quantitative finance industries. 我们致力于量化知识的开源与汉化，打破国内外量化金融行…

[CVPR 2025] UniScene: Unified Occupancy-centric Driving Scene Generation

Lidar Localization and Mapping

[NeurIPS 2025] Flow x RL. "ReinFlow: Fine-tuning Flow Policy with Online Reinforcement Learning". Support VLAs e.g., pi0, pi0.5. Fully open-sourced.

Contexts Optical Compression

The best ChatGPT that $100 can buy.

[ICCV 2025 Oral] Back on Track: Bundle Adjustment for Dynamic Scene Reconstruction (BA-Track)

OKVIS2-X: Open Keyframe-based Visual-Inertial SLAM Configurable with Dense Depth or LiDAR, and GNSS

An open source code repository of driving world models, with training, inferencing, evaluation tools, and pretrained checkpoints.

This is a 3DGS(3D Gaussian Splatting) viewer built on Three.js, with features for marking, measurements, text watermarks, etc.

一款开源免费，完全离线、数据 AES 加密的现代化电子礼簿系统。专为红白喜事设计，提供高效录入、Excel/PDF 专业报表导出一站式礼金管理解决方案。

(CVPR 2025 highlight✨) Official repository of paper "LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models"

[NeurIPS'25 (Spotlight)] DeltaFlow: An Efficient Multi-frame Scene Flow Estimation Method

基于多智能体LLM的中文金融交易框架 - TradingAgents中文增强版

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

[NeurIPS 2025 (Spotlight)] The implementation for the paper "4DGT Learning a 4D Gaussian Transformer Using Real-World Monocular Videos"

verl: Volcano Engine Reinforcement Learning for LLMs

强化学习中文教程（蘑菇书🍄），在线阅读地址：https://datawhalechina.github.io/easy-rl/