Show newer
arXiv - CSCL

Exploring the Benefits of Training Expert Language Models over Instruction Tuning. (arXiv:2302.03202v2 [cs.CL] UPDATED) 

arxiv.org/abs/2302.03202

0
arXiv - CSCL

How Many and Which Training Points Would Need to be Removed to Flip this Prediction?. (arXiv:2302.02169v2 [cs.LG] UPDATED) 

arxiv.org/abs/2302.02169

0
arXiv - CSCL

Multimodal Chain-of-Thought Reasoning in Language Models. (arXiv:2302.00923v2 [cs.CL] UPDATED) 

arxiv.org/abs/2302.00923

0
arXiv - CSCL

Weakly-Supervised Questions for Zero-Shot Relation Extraction. (arXiv:2301.09640v2 [cs.CL] UPDATED) 

arxiv.org/abs/2301.09640

0
arXiv - CSCL

Semi-Structured Object Sequence Encoders. (arXiv:2301.01015v3 [cs.CV] UPDATED) 

arxiv.org/abs/2301.01015

0
arXiv - CSCL

Decomposing a Recurrent Neural Network into Modules for Enabling Reusability and Replacement. (arXiv:2212.05970v3 [cs.SE] UPDATED) 

arxiv.org/abs/2212.05970

0
arXiv - CSCL

Average Token Delay: A Latency Metric for Simultaneous Translation. (arXiv:2211.13173v2 [cs.CL] UPDATED) 

arxiv.org/abs/2211.13173

0
arXiv - CSCL

TPU-MLIR: A Compiler For TPU Using MLIR. (arXiv:2210.15016v2 [cs.PL] UPDATED) 

arxiv.org/abs/2210.15016

0
arXiv - CSCL

Best Practices in the Creation and Use of Emotion Lexicons. (arXiv:2210.07206v2 [cs.CL] UPDATED) 

arxiv.org/abs/2210.07206

0
arXiv - CSCL

Better Pre-Training by Reducing Representation Confusion. (arXiv:2210.04246v2 [cs.CL] UPDATED) 

arxiv.org/abs/2210.04246

0
arXiv - CSCL

COMPS: Conceptual Minimal Pair Sentences for testing Robust Property Knowledge and its Inheritance in Pre-trained Language Models. (arXiv:2210.01963v4 [cs.CL] UPDATED) 

arxiv.org/abs/2210.01963

0
arXiv - CSCL

Neural Approaches to Multilingual Information Retrieval. (arXiv:2209.01335v2 [cs.IR] UPDATED) 

arxiv.org/abs/2209.01335

0
arXiv - CSCL

Global Performance Disparities Between English-Language Accents in Automatic Speech Recognition. (arXiv:2208.01157v2 [cs.CL] UPDATED) 

arxiv.org/abs/2208.01157

0
arXiv - CSCL

Visual Spatial Reasoning. (arXiv:2205.00363v2 [cs.CL] UPDATED) 

arxiv.org/abs/2205.00363

0
arXiv - CSCL

A Latent-Variable Model for Intrinsic Probing. (arXiv:2201.08214v2 [cs.CL] UPDATED) 

arxiv.org/abs/2201.08214

0
arXiv - CSCL

Composable Sparse Fine-Tuning for Cross-Lingual Transfer. (arXiv:2110.07560v2 [cs.CL] UPDATED) 

arxiv.org/abs/2110.07560

0
arXiv - CSCL

What Makes Sentences Semantically Related: A Textual Relatedness Dataset and Empirical Study. (arXiv:2110.04845v3 [cs.CL] UPDATED) 

arxiv.org/abs/2110.04845

0
arXiv - CSCL

Learning From How Humans Correct. (arXiv:2102.00225v13 [cs.CL] UPDATED) 

arxiv.org/abs/2102.00225

0
arXiv - CSCL

Offsite-Tuning: Transfer Learning without Full Model. (arXiv:2302.04870v1 [cs.CL]) 

arxiv.org/abs/2302.04870

0
arXiv - CSCL

Learning by Asking for Embodied Visual Navigation and Task Completion. (arXiv:2302.04865v1 [cs.CV]) 

arxiv.org/abs/2302.04865

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.

Resources

Developers

What is Mastodon?

qoto.org

More…

v3.5.19-qoto · Privacy policy