Show newer
arXiv - CSCL

Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints. (arXiv:2212.05055v2 [cs.LG] UPDATED) 

arxiv.org/abs/2212.05055

0
arXiv - CSCL

Towards Building Text-To-Speech Systems for the Next Billion Users. (arXiv:2211.09536v3 [cs.CL] UPDATED) 

arxiv.org/abs/2211.09536

0
arXiv - CSCL

Modular Hybrid Autoregressive Transducer. (arXiv:2210.17049v2 [cs.CL] UPDATED) 

arxiv.org/abs/2210.17049

0
arXiv - CSCL

Alibaba-Translate China's Submission for WMT 2022 Quality Estimation Shared Task. (arXiv:2210.10049v2 [cs.CL] UPDATED) 

arxiv.org/abs/2210.10049

0
arXiv - CSCL

Alibaba-Translate China's Submission for WMT 2022 Metrics Shared Task. (arXiv:2210.09683v2 [cs.CL] UPDATED) 

arxiv.org/abs/2210.09683

0
arXiv - CSCL

A Kernel-Based View of Language Model Fine-Tuning. (arXiv:2210.05643v2 [cs.LG] UPDATED) 

arxiv.org/abs/2210.05643

0
arXiv - CSCL

FRMT: A Benchmark for Few-Shot Region-Aware Machine Translation. (arXiv:2210.00193v2 [cs.CL] UPDATED) 

arxiv.org/abs/2210.00193

0
arXiv - CSCL

Write and Paint: Generative Vision-Language Models are Unified Modal Learners. (arXiv:2206.07699v3 [cs.CV] UPDATED) 

arxiv.org/abs/2206.07699

0
arXiv - CSCL

Descartes: Generating Short Descriptions of Wikipedia Articles. (arXiv:2205.10012v3 [cs.CL] UPDATED) 

arxiv.org/abs/2205.10012

0
arXiv - CSCL

Unsupervised Keyphrase Extraction via Interpretable Neural Networks. (arXiv:2203.07640v2 [cs.CL] UPDATED) 

arxiv.org/abs/2203.07640

0
arXiv - CSCL

Aligning AI With Shared Human Values. (arXiv:2008.02275v6 [cs.CY] UPDATED) 

arxiv.org/abs/2008.02275

0
arXiv - CSCL

Complex QA and language models hybrid architectures, Survey. (arXiv:2302.09051v1 [cs.CL]) 

arxiv.org/abs/2302.09051

0
arXiv - CSCL

CK-Transformer: Commonsense Knowledge Enhanced Transformers for Referring Expression Comprehension. (arXiv:2302.09027v1 [cs.CV]) 

arxiv.org/abs/2302.09027

0
arXiv - CSCL

Designing and Evaluating Interfaces that Highlight News Coverage Diversity Using Discord Questions. (arXiv:2302.08997v1 [cs.HC]) 

arxiv.org/abs/2302.08997

0
arXiv - CSCL

Towards Fine-Grained Information: Identifying the Type and Location of Translation Errors. (arXiv:2302.08975v1 [cs.CL]) 

arxiv.org/abs/2302.08975

0
arXiv - CSCL

Grimm in Wonderland: Prompt Engineering with Midjourney to Illustrate Fairytales. (arXiv:2302.08961v1 [cs.CL]) 

arxiv.org/abs/2302.08961

0
arXiv - CSCL

Like a Good Nearest Neighbor: Practical Content Moderation with Sentence Transformers. (arXiv:2302.08957v1 [cs.CL]) 

arxiv.org/abs/2302.08957

0
arXiv - CSCL

AfriSenti: A Twitter Sentiment Analysis Benchmark for African Languages. (arXiv:2302.08956v1 [cs.CL]) 

arxiv.org/abs/2302.08956

0
arXiv - CSCL

Handling the Alignment for Wake Word Detection: A Comparison Between Alignment-Based, Alignment-Free and Hybrid Approaches. (arXiv:2302.08950v1 [cs.CL]) 

arxiv.org/abs/2302.08950

0
arXiv - CSCL

Entry Separation using a Mixed Visual and Textual Language Model: Application to 19th century French Trade Directories. (arXiv:2302.08948v1 [cs.CL]) 

arxiv.org/abs/2302.08948

0
Show older
Qoto Mastodon

QOTO: Question Others to Teach Ourselves
An inclusive, Academic Freedom, instance
All cultures welcome.
Hate speech and harassment strictly forbidden.

Trending now

Resources

Developers

What is Mastodon?

qoto.org

More…

v3.5.19-qoto · Privacy policy