Show newer
arXiv - CSCL

Max-Margin Token Selection in Attention Mechanism. (arXiv:2306.13596v2 [cs.LG] UPDATED) 

arxiv.org/abs/2306.13596

0
arXiv - CSCL

Learning Descriptive Image Captioning via Semipermeable Maximum Likelihood Estimation. (arXiv:2306.13460v2 [cs.CL] UPDATED) 

arxiv.org/abs/2306.13460

0
arXiv - CSCL

DiversiGATE: A Comprehensive Framework for Reliable Large Language Models. (arXiv:2306.13230v2 [cs.CL] UPDATED) 

arxiv.org/abs/2306.13230

0
arXiv - CSCL

Towards Benchmarking and Improving the Temporal Reasoning Capability of Large Language Models. (arXiv:2306.08952v2 [cs.CL] UPDATED) 

arxiv.org/abs/2306.08952

0
arXiv - CSCL

Survey on Sociodemographic Bias in Natural Language Processing. (arXiv:2306.08158v2 [cs.CL] UPDATED) 

arxiv.org/abs/2306.08158

0
arXiv - CSCL

LLMZip: Lossless Text Compression using Large Language Models. (arXiv:2306.04050v2 [cs.IT] UPDATED) 

arxiv.org/abs/2306.04050

0
arXiv - CSCL

Language Models are Bounded Pragmatic Speakers. (arXiv:2305.17760v3 [cs.CL] UPDATED) 

arxiv.org/abs/2305.17760

0
arXiv - CSCL

Cross-Attention is Not Enough: Incongruity-Aware Hierarchical Multimodal Sentiment Analysis and Emotion Recognition. (arXiv:2305.13583v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.13583

0
arXiv - CSCL

Debiased Automatic Speech Recognition for Dysarthric Speech via Sample Reweighting with Sample Affinity Test. (arXiv:2305.13108v3 [eess.AS] UPDATED) 

arxiv.org/abs/2305.13108

0
arXiv - CSCL

Constructing Word-Context-Coupled Space Aligned with Associative Knowledge Relations for Interpretable Language Modeling. (arXiv:2305.11543v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.11543

0
arXiv - CSCL

Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers. (arXiv:2305.07011v2 [cs.CV] UPDATED) 

arxiv.org/abs/2305.07011

0
arXiv - CSCL

mCPT at SemEval-2023 Task 3: Multilingual Label-Aware Contrastive Pre-Training of Transformers for Few- and Zero-shot Framing Detection. (arXiv:2303.09901v2 [cs.CL] UPDATED) 

arxiv.org/abs/2303.09901

0
arXiv - CSCL

Extracting Accurate Materials Data from Research Papers with Conversational Language Models and Prompt Engineering. (arXiv:2303.05352v2 [cs.CL] UPDATED) 

arxiv.org/abs/2303.05352

0
arXiv - CSCL

SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networks. (arXiv:2302.13939v4 [cs.CL] UPDATED) 

arxiv.org/abs/2302.13939

0
arXiv - CSCL

Auditing large language models: a three-layered approach. (arXiv:2302.08500v2 [cs.CL] UPDATED) 

arxiv.org/abs/2302.08500

0
arXiv - CSCL

Mu$^{2}$SLAM: Multitask, Multilingual Speech and Language Models. (arXiv:2212.09553v2 [cs.CL] UPDATED) 

arxiv.org/abs/2212.09553

0
arXiv - CSCL

WACO: Word-Aligned Contrastive Learning for Speech Translation. (arXiv:2212.09359v2 [cs.CL] UPDATED) 

arxiv.org/abs/2212.09359

0
arXiv - CSCL

Imagination is All You Need! Curved Contrastive Learning for Abstract Sequence Modeling Utilized on Long Short-Term Dialogue Planning. (arXiv:2211.07591v2 [cs.CL] UPDATED) 

arxiv.org/abs/2211.07591

0
arXiv - CSCL

BLOOM: A 176B-Parameter Open-Access Multilingual Language Model. (arXiv:2211.05100v4 [cs.CL] UPDATED) 

arxiv.org/abs/2211.05100

0
arXiv - CSCL

SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control. (arXiv:2210.17432v2 [cs.CL] UPDATED) 

arxiv.org/abs/2210.17432

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