Papers with Code 아카이브

Language Modeling

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

1

평가표

0

보존된 평가 기록

0

코드

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

https://github.com/cstorm125/thai2fit

Regularizing and Optimizing LSTM Language Models

https://github.com/cuber2460/bert

Semi-supervised Sequence Learning

https://github.com/cuhksz-nlp/SAPar

XLNet: Generalized Autoregressive Pretraining for Language Understanding

https://github.com/cui0523/Code6/tree/main/mass

MASS: Masked Sequence to Sequence Pre-training for Language Generation

https://github.com/cure-lab/mma-diffusion

GuardT2I: Defending Text-to-Image Models from Adversarial Prompts

https://github.com/custodio78/Speech_Recognition

Listen, Attend and Spell

https://github.com/cydonia999/variational-autoencoders-for-collaborative-filtering-pytorch

Variational Autoencoders for Collaborative Filtering

https://github.com/d-gurgurov/im2latex

TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models

https://github.com/d-robotics-ai-lab/dosod

YOLO-World: Real-Time Open-Vocabulary Object Detection

https://github.com/d2l-ai/d2l-en

ControlVAE: Tuning, Analytical Properties, and Performance Analysis

https://github.com/d2l-ai/d2l-tr

ControlVAE: Tuning, Analytical Properties, and Performance Analysis

https://github.com/da03/Residual-EBM

Residual Energy-Based Models for Text Generation

https://github.com/daQuincy/DeepMusicvStyle

mu-Forcing: Training Variational Recurrent Autoencoders for Text Generation

https://github.com/damo-nlp-sg/videollama2

Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding

https://github.com/damo-nlp-sg/videollama3

Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding

https://github.com/dangitstam/topic-rnn

TopicRNN: A Recurrent Neural Network with Long-Range Semantic Dependency

https://github.com/daniellawson9999/online-decision-transformer

Online Decision Transformer

https://github.com/danoneata/espnet

Improved training of end-to-end attention models for speech recognition

https://github.com/dare0021/MemN2N_Bench

End-To-End Memory Networks

https://github.com/dariush-salami/gcn-gesture-recognition

Structured Sequence Modeling with Graph Convolutional Recurrent Networks

https://github.com/dashenzi721/hra

DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing

https://github.com/dashstander/block-recurrent-transformer

Block-Recurrent Transformers

https://github.com/data-prep-kit/data-prep-kit

Data-Prep-Kit: getting your data ready for LLM application development

https://github.com/datphamvn/hsevo

Algorithm Evolution Using Large Language Model

https://github.com/david-li0406/read

Fine-grained Contrastive Learning for Relation Extraction

https://github.com/davidkim205/komt

Direct Preference Optimization: Your Language Model is Secretly a Reward Model

https://github.com/davidsvaughn/dts-tf

Character-Aware Neural Language Models

https://github.com/davidsvy/cosformer-pytorch

ReZero is All You Need: Fast Convergence at Large Depth

https://github.com/davidtangGT/MEGNET

Order Matters: Sequence to sequence for sets

https://github.com/davisliang/fairseq/tree/main/examples/xlmv

XLM-V: Overcoming the Vocabulary Bottleneck in Multilingual Masked Language Models

https://github.com/dayeonki/rewrite_mt

Tower: An Open Multilingual Large Language Model for Translation-Related Tasks

https://github.com/dbmdz/historic-ner

Towards Robust Named Entity Recognition for Historic German

https://github.com/ddpalacios/Evolving-Architecture

Evolving Deep Neural Networks

https://github.com/declare-lab/hyperred

RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction

https://github.com/declare-lab/red-instruct

Language Model Unalignment: Parametric Red-Teaming to Expose Hidden Harms and Biases

https://github.com/declare-lab/tango

Improving Text-To-Audio Models with Synthetic Captions

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