Skip to content
View songyonger's full-sized avatar
  • Northwestern Polytechnical University
  • Xi'an

Block or report songyonger

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

FastPillars: A Deployment-friendly Pillar-based 3D Detector

Python 171 11 Updated Jan 14, 2025

Train 3D object detection algorithms on custom dataset based on mmdetection3d

Python 3 Updated Jan 9, 2026

A paper list about Token Merge, Reduce, Resample, Drop for MLLMs.

80 Updated Oct 26, 2025
Python 25 2 Updated Nov 16, 2025

A full Python implementation for real car surround view system

Python 1,240 382 Updated Dec 31, 2025

[Neurips’25] Code for the paper "Balanced Token Pruning: Accelerating Vision Language Models Beyond Local Optimization"

Python 29 1 Updated Sep 25, 2025

[NeurIPS 2025 🔥] Official implementation for "Don't Just Chase “Highlighted Tokens” in MLLMs: Revisiting Visual Holistic Context Retention"

Python 53 Updated Dec 17, 2025

毕业设计:《基于CLIP模型的视频文本检索设计与实现》

Python 17 2 Updated Jul 21, 2024

A collection of token reduction (token pruning, merging, clustering, etc.) techniques for ML/AI

283 7 Updated Jan 12, 2026

A paper list of some recent works about Token Compress for Vit and VLM

806 38 Updated Dec 24, 2025

这是一份入门AI/LLM大模型的逐步指南,包含教程和演示代码,带你从API走进本地大模型部署和微调,代码文件会提供Kaggle或Colab在线版本,即便没有显卡也可以进行学习。项目中还开设了一个小型的代码游乐场🎡,你可以尝试在里面实验一些有意思的AI脚本。同时,包含李宏毅 (HUNG-YI LEE)2024生成式人工智能导论课程的完整中文镜像作业。

Python 3,366 367 Updated Sep 10, 2025

The devkit of the nuScenes dataset.

Python 2,642 696 Updated Aug 28, 2025

本Fork代码仓库作为本人记录学习BEVFusion的学习笔记使用,会逐步理解代码并添加大量中文注释。 本仓库代码已参照《bevfusion单显卡训练/测试》做了单GPU训练和测试的修改。 并在本人主机上做过了测试。

Python 104 14 Updated Aug 29, 2023
Jupyter Notebook 17 3 Updated Nov 14, 2023

[CVPR 2023 Best Paper Award] Planning-oriented Autonomous Driving

Python 4,429 502 Updated Oct 29, 2025

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

Python 67,293 12,522 Updated Jan 12, 2026

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…

Python 12,603 2,003 Updated Jan 12, 2026

nuscenes2bag

C++ 43 10 Updated Jan 21, 2025

BEVFusion-ROS-TensorRT-CPP real time inference including ros1 & ros2.

Python 225 46 Updated Jan 15, 2025

Nvidia-IOT-CUDA_BEVFusion with lidar-only mode, deployed on Nvidia AGX ORIN.

Cuda 8 2 Updated Apr 29, 2025

Spatial Sparse Convolution Library

Python 2,218 401 Updated Dec 15, 2024

A project demonstrating Lidar related AI solutions, including three GPU accelerated Lidar/camera DL networks (PointPillars, CenterPoint, BEVFusion) and the related libs (cuPCL, 3D SparseConvolution…

Python 19 3 Updated Aug 23, 2025

A project demonstrating Lidar related AI solutions, including three GPU accelerated Lidar/camera DL networks (PointPillars, CenterPoint, BEVFusion) and the related libs (cuPCL, 3D SparseConvolution…

Python 1,709 304 Updated Nov 25, 2025

Inverse Perspective Mapping

Python 85 13 Updated Feb 17, 2022

Pytorch implementation of "Spatial As Deep: Spatial CNN for Traffic Scene Understanding"

Python 262 70 Updated Apr 28, 2023

Related papers and codes for vision-based robotic grasping

Python 1,429 252 Updated Jun 22, 2023
Next