Stars
The python library for real-time communication
Library for Jacobian descent with PyTorch. It enables the optimization of neural networks with multiple losses (e.g. multi-task learning).
Official implementation of "WhisperNER: Unified Open Named Entity and Speech Recognition"
[NeurIPS'24 Oral] Official repository for the paper "Scale Equivariant Graph Metanetworks"
Official implementation of "Improved Generalization of Weight Space Networks via Augmentations", ICML 2024
Faster Whisper transcription with CTranslate2
Official PyTorch Implementation for Fast Adaptive Multitask Optimization (FAMO)
The implementation of "Prismer: A Vision-Language Model with Multi-Task Experts".
Official implementation of Auxiliary learning as an Bargaining Game.
[NeurIPS 2022] "Signal Processing for Implicit Neural Representations" by Dejia Xu*, Peihao Wang*, Yifan Jiang, Zhiwen Fan, Zhangyang Wang
Multi-task model for named-entity recognition, relation extraction, entity mention detection and coreference resolution.
A PyTorch Library for Multi-Task Learning
The Implementation of "Auto-Lambda: Disentangling Dynamic Task Relationships" [TMLR 2022].
Official PyTorch Implementation for Conflict-Averse Gradient Descent (CAGrad)
PyTorch code for SpERT: Span-based Entity and Relation Transformer
Pytorch reimplementation for "Gradient Surgery for Multi-Task Learning"
PyTorch implementation of Never Give Up: Learning Directed Exploration Strategies
Code for Personalized Federated Learning with Gaussian Processes
GP-Tree: A Gaussian Process Classifier for Few-Shot Incremental Learning
Official code implementation for "Personalized Federated Learning using Hypernetworks" [ICML 2021]
Self-Supervised Learning for Domain Adaptation on Point-Clouds
Code for our paper: *Shamsian, *Kleinfeld, Globerson & Chechik, "Learning Object Permanence from Video"
higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.