Yuxiang Lin's Projects
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
Source code for models described in the paper "AudioCLIP: Extending CLIP to Image, Text and Audio" (https://arxiv.org/abs/2106.13043)
Papers and resources on Reasoning in Language Models (LLMs), including Chain-of-Thought, Instruction-Tuning, Multimodality.
A curated list of facial expression recognition in both 7-emotion classification and affect estimation.
Official repository of "Chatting Makes Perfect: Chat-based Image Retrieval"
Some note while learning computer vision by OpenCV, C++ version
A simple spider to crawl Amazon keyword rankings using Scrapy framework.
People Die, but Long Live GitHub
🤡 Personal Profile
基于节点编辑器开发的用于可视化构建神经网络的神器。Based on node editor development artifacts for visualization to build neural networks.
Recent LLM-based CV and related works. Welcome to comment/contribute!
Meta-Transformer for Unified Multimodal Learning
OpenMMLab Detection Toolbox and Benchmark
OpenMMLab's next-generation platform for general 3D object detection.
OpenMMLab Text Detection, Recognition and Understanding Toolbox
OpenMMLab YOLO series toolbox and benchmark. Implemented RTMDet, RTMDet-Rotated,YOLOv5, YOLOv6, YOLOv7, YOLOv8,YOLOX, PPYOLOE, etc.
Mosh front-end course project, pure html and css project.
Modeling, training, eval, and inference code for OLMo
An open source implementation of CLIP.
Python课上的大作业ppt展示,介绍了Kaggle上一个关于驾驶员安全驾驶的预测竞赛实现
Question and Answer based on Anything.
中文领域心理健康对话大模型SoulChat