-
Northwestern Polytechnical University
- Xi'an
Stars
FastPillars: A Deployment-friendly Pillar-based 3D Detector
Train 3D object detection algorithms on custom dataset based on mmdetection3d
A paper list about Token Merge, Reduce, Resample, Drop for MLLMs.
A full Python implementation for real car surround view system
[Neurips’25] Code for the paper "Balanced Token Pruning: Accelerating Vision Language Models Beyond Local Optimization"
[NeurIPS 2025 🔥] Official implementation for "Don't Just Chase “Highlighted Tokens” in MLLMs: Revisiting Visual Holistic Context Retention"
A collection of token reduction (token pruning, merging, clustering, etc.) techniques for ML/AI
A paper list of some recent works about Token Compress for Vit and VLM
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。
The devkit of the nuScenes dataset.
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。
[CVPR 2023 Best Paper Award] Planning-oriented Autonomous Driving
A high-throughput and memory-efficient inference and serving engine for LLMs
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…
BEVFusion-ROS-TensorRT-CPP real time inference including ros1 & ros2.
Nvidia-IOT-CUDA_BEVFusion with lidar-only mode, deployed on Nvidia AGX ORIN.
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…
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…
Pytorch implementation of "Spatial As Deep: Spatial CNN for Traffic Scene Understanding"
Related papers and codes for vision-based robotic grasping