A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning. arXiv:2307.09218.

[NeurIPS 2024 & ACL 2024 NLP4ConvAI Oral] Train LLMs with diverse system messages reflecting individualized preferences to generalize to unseen system messages

Continual Learning of Large Language Models: A Comprehensive Survey

Code release for Dataless Knowledge Fusion by Merging Weights of Language Models (https://openreview.net/forum?id=FCnohuR6AnM)

Organize your experiments into discrete steps that can be cached and reused throughout the lifetime of your research project.

Code for paper "CrossFit 🏋️: A Few-shot Learning Challenge for Cross-task Generalization in NLP" (https://arxiv.org/abs/2104.08835)

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less Data

A collection of incremental learning paper implementations including PODNet (ECCV20) and Ghost (CVPR-W21).

Awesome Incremental Learning

Tools for training explainable models using attribution priors.

A simple tool to update bib entries with their official information (e.g., DBLP or the ACL anthology).

Yichi Zhang et al. A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learning. EMNLP 2020.

Code for LAMOL: LAnguage MOdeling for Lifelong Language Learning

Transformers for Information Retrieval, Text Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI

Official code release for ACL 2020 paper "Contextualizing Hate Speech Classifiers with Post hoc Explanation"

Source code for "Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence Models", ICLR 2020.

Grounded conversational dataset for end-to-end conversational AI (official DSTC7 data)

A repository for explaining feature attributions and feature interactions in deep neural networks.

Implementation of Bayesian Gradient Descent

Continual Learning with Hypernetworks. A continual learning approach that has the flexibility to learn a dedicated set of parameters, fine-tuned for every task, that doesn't require an increase in …

A PyTorch Library for Meta-learning Research

Source code for paper "Looking Beyond Label Noise: Shifted Label Distribution Matters in Distantly Supervised Relation Extraction" (EMNLP 2019)

Macbook | Clock, right on the touch bar

Evaluate three types of task shifting with popular continual learning algorithms.

Continuum Learning with GEM: Gradient Episodic Memory