Show newer
arXiv - CSCL

QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models. (arXiv:2310.08041v1 [cs.CL]) 

arxiv.org/abs/2310.08041

0
arXiv - CSCL

Exploring Large Language Models for Multi-Modal Out-of-Distribution Detection. (arXiv:2310.08027v1 [cs.CL]) 

arxiv.org/abs/2310.08027

0
arXiv - CSCL

Harnessing Large Language Models' Empathetic Response Generation Capabilities for Online Mental Health Counselling Support. (arXiv:2310.08017v1 [cs.CL]) 

arxiv.org/abs/2310.08017

0
arXiv - CSCL

Think, Act, and Ask: Open-World Interactive Personalized Robot Navigation. (arXiv:2310.07968v1 [cs.RO]) 

arxiv.org/abs/2310.07968

0
arXiv - CSCL

Clustering of Spell Variations for Proper Nouns Transliterated from the other languages. (arXiv:2310.07962v1 [cs.CL]) 

arxiv.org/abs/2310.07962

0
arXiv - CSCL

A New Approach Towards Autoformalization. (arXiv:2310.07957v1 [cs.CL]) 

arxiv.org/abs/2310.07957

0
arXiv - CSCL

D2 Pruning: Message Passing for Balancing Diversity and Difficulty in Data Pruning. (arXiv:2310.07931v1 [cs.LG]) 

arxiv.org/abs/2310.07931

0
arXiv - CSCL

Crosslingual Structural Priming and the Pre-Training Dynamics of Bilingual Language Models. (arXiv:2310.07929v1 [cs.CL]) 

arxiv.org/abs/2310.07929

0
arXiv - CSCL

The Expresssive Power of Transformers with Chain of Thought. (arXiv:2310.07923v1 [cs.LG]) 

arxiv.org/abs/2310.07923

0
arXiv - CSCL

Pit One Against Many: Leveraging Attention-head Embeddings for Parameter-efficient Multi-head Attention. (arXiv:2310.07911v1 [cs.CL]) 

arxiv.org/abs/2310.07911

0
arXiv - CSCL

LangNav: Language as a Perceptual Representation for Navigation. (arXiv:2310.07889v1 [cs.CV]) 

arxiv.org/abs/2310.07889

0
arXiv - CSCL

TabLib: A Dataset of 627M Tables with Context. (arXiv:2310.07875v1 [cs.CL]) 

arxiv.org/abs/2310.07875

0
arXiv - CSCL

Assessing Evaluation Metrics for Neural Test Oracle Generation. (arXiv:2310.07856v1 [cs.CL]) 

arxiv.org/abs/2310.07856

0
arXiv - CSCL

Synthetic Data Generation with Large Language Models for Text Classification: Potential and Limitations. (arXiv:2310.07849v1 [cs.CL]) 

arxiv.org/abs/2310.07849

0
arXiv - CSCL

Framework for Question-Answering in Sanskrit through Automated Construction of Knowledge Graphs. (arXiv:2310.07848v1 [cs.CL]) 

arxiv.org/abs/2310.07848

0
arXiv - CSCL

Does Synthetic Data Make Large Language Models More Efficient?. (arXiv:2310.07830v1 [cs.CL]) 

arxiv.org/abs/2310.07830

0
arXiv - CSCL

Antarlekhaka: A Comprehensive Tool for Multi-task Natural Language Annotation. (arXiv:2310.07826v1 [cs.CL]) 

arxiv.org/abs/2310.07826

0
arXiv - CSCL

Non-autoregressive Text Editing with Copy-aware Latent Alignments. (arXiv:2310.07821v1 [cs.CL]) 

arxiv.org/abs/2310.07821

0
arXiv - CSCL

Faithfulness Measurable Masked Language Models. (arXiv:2310.07819v1 [cs.CL]) 

arxiv.org/abs/2310.07819

0
arXiv - CSCL

Exploring the Relationship between Analogy Identification and Sentence Structure Encoding in Large Language Models. (arXiv:2310.07818v1 [cs.CL]) 

arxiv.org/abs/2310.07818

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