[NeurIPS 2025] OmniSVG is the first family of end-to-end multimodal SVG generators that leverage pre-trained Vision-Language Models (VLMs), capable of generating complex and detailed SVGs, from simple icons to intricate anime characters.
Repository Index
142,187 visible repositories in the index
25–48 of 94 · Most stars
Self-Supervised Speech Pre-training and Representation Learning Toolkit
- speech-representation
- mockingjay
- representation-learning
- apc
Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.
- deep-learning
- flax
- jax
- language-model
The collection of pre-trained, state-of-the-art AI models for ailia SDK
- deep-learning
- face-recognition
- face-detection
- object-detection
Many studies have shown that the performance on deep learning is significantly affected by volume of training data. The MedicalNet project provides a series of 3D-ResNet pre-trained models and relative code.
Pre-trained word vectors of 30+ languages
- vector
- word2vec
- language
- fasttext
Bioinformatics'2020: BioBERT: a pre-trained biomedical language representation model for biomedical text mining
PyTorch pre-trained model for real-time interest point detection, description, and sparse tracking (https://arxiv.org/abs/1712.07629)
A Large-scale Chinese Short-Text Conversation Dataset and Chinese pre-training dialog models
mobilenetv3 with pytorch,provide pre-train model
Guide to using pre-trained large language models of source code
- gpt-2
- deep-learning
- source-code
[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
- self-supervised-learning
- action-recognition
- video-understanding
- masked-autoencoder
Language Understanding Evaluation benchmark for Chinese: datasets, baselines, pre-trained models,corpus and leaderboard
- glue
- language-understanding
- bert
- pre-trained-model
Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos
Papers about pretraining and self-supervised learning on Graph Neural Networks (GNN).
- graph-neural-networks
- pretraining
- self-supervised-learning
- deep-learning
Software and pre-trained models for automatic photo quality enhancement using Deep Convolutional Networks
- image-enhancement
- image-processing
- computer-vision
- deep-learning
Pre-Trained Chinese XLNet(中文XLNet预训练模型)
Chinese Pre-Trained Language Models (CPM-LM) Version-I
Data and tools for generating and inspecting OLMo pre-training data.
- data-processing
- large-language-models
- llm
- machile-learning
Easy to use stem (e.g. instrumental/vocals) separation from CLI or as a python package, using a variety of amazing pre-trained models (primarily from UVR)
Skywork series models are pre-trained on 3.2TB of high-quality multilingual (mainly Chinese and English) and code data. We have open-sourced the model, training data, evaluation data, evaluation methods, etc.
Pre-trained ELMo Representations for Many Languages
- nlp
- elmo
- multilingual
Pre-trained Chinese ELECTRA(中文ELECTRA预训练模型)
- nlp
- bert
- electra
- pre-trained-model
CREPE: A Convolutional REpresentation for Pitch Estimation -- pre-trained model (ICASSP 2018)
- pitch-estimation
- tensorflow
- keras
- music-information-retrieval