人工智能论文原理图集3

1, Multilingual Denoising Pre-training for Neural Machine Translation


2, MarkupLM: Pre-training of Text and Markup Language
for Visually Rich Document Understanding


3, Beyond English-Centric Multilingual Machine Translation


4, Jukebox: A Generative Model for Music


5, Funnel-Transformer: Filtering out Sequential
Redundancy for Efficient Language Processing

6, FNet: Mixing Tokens with Fourier Transforms

7, Unifying Language Learning Paradigms


8, AST: Audio Spectrogram Transformer

9, LARGE-SCALE CONTRASTIVE LANGUAGE-AUDIO PRETRAINING WITH
FEATURE FUSION AND KEYWORD-TO-CAPTION AUGMENTATION

10, HuBERT: Self-Supervised Speech Representation
Learning by Masked Prediction of Hidden Units

11, PSEUDO-LABELING FOR MASSIVELY MULTILINGUAL SPEECH
RECOGNITION


12, PERFORMANCE-EFFICIENCY TRADE-OFFS
IN UNSUPERVISED PRE-TRAINING
FOR SPEECH RECOGNITION

13, SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for
Spoken Language Processing


14, UniSpeech: Unified Speech Representation Learning
with Labeled and Unlabeled Data

15, UNISPEECH-SAT: UNIVERSAL SPEECH REPRESENTATION LEARNING WITH SPEAKER
AWARE PRE-TRAINING

16, wav2vec 2.0: A Framework for Self-Supervised
Learning of Speech Representations

17, WavLM: Large-Scale Self-Supervised Pre-Training
for Full Stack Speech Processing

18, Robust Speech Recognition via Large-Scale Weak Supervision

19, XLS-R: SELF-SUPERVISED CROSS-LINGUAL SPEECH
REPRESENTATION LEARNING AT SCALE

20, UNSUPERVISED CROSS-LINGUAL REPRESENTATION
LEARNING FOR SPEECH RECOGNITION

21, Do Transformers Really Perform Bad
for Graph Representation?

22, Decision Transformer: Reinforcement
Learning via Sequence Modeling


23, Offline Reinforcement Learning as One Big
Sequence Modeling Problem


24,Informer: Beyond Efficient Transformer for Long Sequence
Time-Series Forecasting