Starred repositories
A scalable manifold learning (SUDE) method that can cope with large-scale and high-dimensional data in an efficient manner
A novel Clustering algorithm by measuring Direction Centrality (CDC) locally. It adopts a density-independent metric based on the distribution of K-nearest neighbors (KNNs) to distinguish between i…
本项目设计并实现了一个基于知识图谱 RAG 与大语言模型的医疗智能问答系统。系统以 DiseaseKG 医疗数据集为基础，依托 Neo4j 构建包含 4.4 万实体与 31 万关系的领域知识图谱；结合 BERT 命名实体识别与 32B 大模型意图识别，通过精确的图谱检索与受控的答案生成，有效缓解大模型在医疗场景中的幻觉问题，显著提升回答的准确性与可靠性。
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
Official Pytorch implementation of "Improved Probabilistic Image-Text Representations" (ICLR 2024)
The code of the paper of "A Differentiable Semantic Metric Approximation in Probabilistic Embedding for Cross-Modal Retrieval" accepted by NeurIPS' 2022.
A curated list of awesome neural radiance fields papers
A collaboration friendly studio for NeRFs
Infinite Photorealistic Worlds using Procedural Generation
Source code for the X Recommendation Algorithm
Official PyTorch implementation of the paper "Integrating Language Guidance into Image-Text Matching for Correcting False Negatives"
Summary of Related Research on Image-Text Matching
An anomaly detection library comprising state-of-the-art algorithms and features such as experiment management, hyper-parameter optimization, and edge inference.
Google Research
The Paper List of Large Multi-Modality Model (Perception, Generation, Unification), Parameter-Efficient Finetuning, Vision-Language Pretraining, Conventional Image-Text Matching for Preliminary Ins…
🎉 A magical vue admin https://panjiachen.github.io/vue-element-admin
PyTorch source code for "Stacked Cross Attention for Image-Text Matching" (ECCV 2018)
The official repository for ERNIE 4.5 and ERNIEKit – its industrial-grade development toolkit based on PaddlePaddle.
A python toolkit for parsing captions (in natural language) into scene graphs (as symbolic representations).
Code for the ICML 2021 (long talk) paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"
A quickstart and benchmark for pytorch distributed training.
Easy-to-use and powerful LLM and SLM library with awesome model zoo.
BertViz: Visualize Attention in Transformer Models