Papers with Code 아카이브

Memorization

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

0

평가표

1

보존된 평가 기록

3

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/chenpf1025/IDN/blob/master/ops.py

A Closer Look at Memorization in Deep Networks

https://github.com/chrisociepa/allamo

PaLM: Scaling Language Modeling with Pathways

https://github.com/codlife/NLP

Wide & Deep Learning for Recommender Systems

https://github.com/conceptofmind/PaLM-flax

PaLM: Scaling Language Modeling with Pathways

https://github.com/cordercorder/knn-models

Generalization through Memorization: Nearest Neighbor Language Models

https://github.com/csong27/auditing-text-generation

Auditing Data Provenance in Text-Generation Models

https://github.com/danielmamay/grokking

Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets

https://github.com/deepakshankar94/Exploring-DL-based-Recommendation-Systems

Wide & Deep Learning for Recommender Systems

https://github.com/deepakshankar94/Movie-Recommendation-System

Wide & Deep Learning for Recommender Systems

https://github.com/dohmatob/multiple-descent-robustness

Fundamental tradeoffs between memorization and robustness in random features and neural tangent regimes

https://github.com/dongdong69/MixAugmentation

mixup: Beyond Empirical Risk Minimization

https://github.com/erichson/noisy_mixup

mixup: Beyond Empirical Risk Minimization

https://github.com/eth-sri/synthpai

Beyond Memorization: Violating Privacy Via Inference with Large Language Models

https://github.com/facebookresearch/ClassyVision

mixup: Beyond Empirical Risk Minimization

https://github.com/facebookresearch/DomainBed

Learning explanations that are hard to vary

https://github.com/facebookresearch/FIND

What they do when in doubt: a study of inductive biases in seq2seq learners

https://github.com/facebookresearch/bounding_data_reconstruction

Reconstructing Training Data with Informed Adversaries

https://github.com/fengtong-xiao/DMBGN

Wide & Deep Learning for Recommender Systems

https://github.com/floraxhuang/Movie-Recommendation-System

Wide & Deep Learning for Recommender Systems

https://github.com/foundation-model-stack/fms-fsdp

PaLM: Scaling Language Modeling with Pathways

https://github.com/freedombenLiu/speech-to-text-wavenet

Neural Machine Translation in Linear Time

https://github.com/ftramer/lm-extraction-benchmark

Quantifying Memorization Across Neural Language Models

https://github.com/google-research/diffstride

mixup: Beyond Empirical Risk Minimization

https://github.com/google-research/heldout-influence-estimation

What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation

https://github.com/google-research/lm-extraction-benchmark

Quantifying Memorization Across Neural Language Models

https://github.com/google/paxml

PaLM: Scaling Language Modeling with Pathways

https://github.com/heegyukim/open-korean-instructions

LIMO: Less is More for Reasoning

https://github.com/henrysteinitz/holographic-reduced-representations

Associative Long Short-Term Memory

https://github.com/henrysteinitz/neural-memory

Associative Long Short-Term Memory

https://github.com/hh-xiaohu/Image-augementation-pytorch

mixup: Beyond Empirical Risk Minimization

https://github.com/hongyi-zhang/Fixup

mixup: Beyond Empirical Risk Minimization

https://github.com/hongyi-zhang/mixup

mixup: Beyond Empirical Risk Minimization

https://github.com/huijieZH/Diffusion-Model-Generalizability

The Emergence of Reproducibility and Generalizability in Diffusion Models

https://github.com/ironjr/grokfast

Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets

https://github.com/iver56/audiomentations

mixup: Beyond Empirical Risk Minimization

https://github.com/jankrepl/mildlyoverfitted

mixup: Beyond Empirical Risk Minimization

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.