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/oist-cnru/Variational-Recurrent-Models

공식 코드

Variational Recurrent Models for Solving Partially Observable Control Tasks

https://github.com/omarfoq/knn-per

공식 코드

Personalized Federated Learning through Local Memorization

https://github.com/open-compass/lawbench

공식 코드

LawBench: Benchmarking Legal Knowledge of Large Language Models

https://github.com/open-dataflow/rare

공식 코드

RARE: Retrieval-Augmented Reasoning Modeling

https://github.com/openai/grok

공식 코드

Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets

https://github.com/opendatalab/charm

공식 코드

Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations

https://github.com/opengvlab/videochat-flash

공식 코드

VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling

https://github.com/optml-group/bibaddiff

공식 코드

From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models

https://github.com/orevaahia/mc4lrnmt

공식 코드

The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation

https://github.com/osu-nlp-group/selm

공식 코드

Memorization for Good: Encryption with Autoregressive Language Models

https://github.com/owenzx/data4comp

공식 코드

Data Factors for Better Compositional Generalization

https://github.com/patrickfinke/memo

공식 코드

Memorization With Neural Nets: Going Beyond the Worst Case

https://github.com/pgfeldman/KeywordExplorer

공식 코드

Polling Latent Opinions: A Method for Computational Sociolinguistics Using Transformer Language Models

https://github.com/physico-benchmark/physico

공식 코드

The Stochastic Parrot on LLM's Shoulder: A Summative Assessment of Physical Concept Understanding

https://github.com/potamides/automatikz

공식 코드

AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ

https://github.com/potamides/uniformers

공식 코드

ByGPT5: End-to-End Style-conditioned Poetry Generation with Token-free Language Models

https://github.com/pratyushmaini/localizing-memorization

공식 코드

Can Neural Network Memorization Be Localized?

https://github.com/princeton-nlp/continual-factoid-memorization

공식 코드

Continual Memorization of Factoids in Large Language Models

https://github.com/privacytrustlab/lood_in_ml

공식 코드

Leave-one-out Distinguishability in Machine Learning

https://github.com/privacytrustlab/ml_privacy_meter

공식 코드

Enhanced Membership Inference Attacks against Machine Learning Models

https://github.com/ptzhangAlg/RecAlg

공식 코드

MemoNet: Memorizing All Cross Features' Representations Efficiently via Multi-Hash Codebook Network for CTR Prediction

https://github.com/py-why/pywhy-llm

공식 코드

Causal Reasoning and Large Language Models: Opening a New Frontier for Causality

https://github.com/pytorch/ignite

공식 코드

Learning explanations that are hard to vary

https://github.com/qhjqhj00/memorag

공식 코드

MemoRAG: Moving towards Next-Gen RAG Via Memory-Inspired Knowledge Discovery

https://github.com/raman1121/diffusion_memorization_hpo

공식 코드

MemControl: Mitigating Memorization in Diffusion Models via Automated Parameter Selection

https://github.com/ranahanocka/ALIGNet

공식 코드

ALIGNet: Partial-Shape Agnostic Alignment via Unsupervised Learning

https://github.com/rcgai/simplyretrieve

공식 코드

SimplyRetrieve: A Private and Lightweight Retrieval-Centric Generative AI Tool

https://github.com/renjie3/memattn

공식 코드

Unveiling and Mitigating Memorization in Text-to-image Diffusion Models through Cross Attention

https://github.com/rinnesz/dwrs

공식 코드

Data Watermarking for Sequential Recommender Systems

https://github.com/ruc-nlpir/genir-survey

공식 코드

From Matching to Generation: A Survey on Generative Information Retrieval

https://github.com/rucaibox/r1-searcher-plus

공식 코드

R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning

https://github.com/rui9812/vlp

공식 코드

To Copy Rather Than Memorize: A Vertical Learning Paradigm for Knowledge Graph Completion

https://github.com/ruoxi-jia-group/forward-inf

공식 코드

The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward Passes

https://github.com/s-huu/jog_llm_memory

공식 코드

Jogging the Memory of Unlearned LLMs Through Targeted Relearning Attacks

https://github.com/sail-sg/DiffMemorize

공식 코드

On Memorization in Diffusion Models

https://github.com/sail-sg/lm-random-memory-access

공식 코드

Beyond Memorization: The Challenge of Random Memory Access in Language Models

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