Show newer
arXiv - CSCL

Personalize Segment Anything Model with One Shot. (arXiv:2305.03048v1 [cs.CV]) 

arxiv.org/abs/2305.03048

0
arXiv - CSCL

Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision. (arXiv:2305.03047v1 [cs.LG]) 

arxiv.org/abs/2305.03047

0
arXiv - CSCL

What changes when you randomly choose BPE merge operations? Not much. (arXiv:2305.03029v1 [cs.CL]) 

arxiv.org/abs/2305.03029

0
arXiv - CSCL

Panda LLM: Training Data and Evaluation for Open-Sourced Chinese Instruction-Following Large Language Models. (arXiv:2305.03025v1 [cs.CL]) 

arxiv.org/abs/2305.03025

0
arXiv - CSCL

Sentence Embedding Leaks More Information than You Expect: Generative Embedding Inversion Attack to Recover the Whole Sentence. (arXiv:2305.03010v1 [cs.CL]) 

arxiv.org/abs/2305.03010

0
arXiv - CSCL

NatCS: Eliciting Natural Customer Support Dialogues. (arXiv:2305.03007v1 [cs.CL]) 

arxiv.org/abs/2305.03007

0
arXiv - CSCL

Adaptive Selection of Anchor Items for CUR-based k-NN search with Cross-Encoders. (arXiv:2305.02996v1 [cs.IR]) 

arxiv.org/abs/2305.02996

0
arXiv - CSCL

On the nonlinear correlation of ML performance between data subpopulations. (arXiv:2305.02995v1 [cs.LG]) 

arxiv.org/abs/2305.02995

0
arXiv - CSCL

SemEval-2023 Task 7: Multi-Evidence Natural Language Inference for Clinical Trial Data. (arXiv:2305.02993v1 [cs.CL]) 

arxiv.org/abs/2305.02993

0
arXiv - CSCL

End-to-end spoken language understanding using joint CTC loss and self-supervised, pretrained acoustic encoders. (arXiv:2305.02937v1 [cs.CL]) 

arxiv.org/abs/2305.02937

0
arXiv - CSCL

An automatically discovered chain-of-thought prompt generalizes to novel models and datasets. (arXiv:2305.02897v1 [cs.CL]) 

arxiv.org/abs/2305.02897

0
arXiv - CSCL

2x Faster Language Model Pre-training via Masked Structural Growth. (arXiv:2305.02869v1 [cs.CL]) 

arxiv.org/abs/2305.02869

0
arXiv - CSCL

CausalAPM: Generalizable Literal Disentanglement for NLU Debiasing. (arXiv:2305.02865v1 [cs.CL]) 

arxiv.org/abs/2305.02865

0
arXiv - CSCL

ReMask: A Robust Information-Masking Approach for Domain Counterfactual Generation. (arXiv:2305.02858v1 [cs.CL]) 

arxiv.org/abs/2305.02858

0
arXiv - CSCL

Semantic Space Grounded Weighted Decoding for Multi-Attribute Controllable Dialogue Generation. (arXiv:2305.02820v1 [cs.CL]) 

arxiv.org/abs/2305.02820

0
arXiv - CSCL

Interpretable Sentence Representation with Variational Autoencoders and Attention. (arXiv:2305.02810v1 [cs.CL]) 

arxiv.org/abs/2305.02810

0
arXiv - CSCL

The Elephant in the Room: Analyzing the Presence of Big Tech in Natural Language Processing Research. (arXiv:2305.02797v1 [cs.CL]) 

arxiv.org/abs/2305.02797

0
arXiv - CSCL

BranchNorm: Robustly Scaling Extremely Deep Transformers. (arXiv:2305.02790v1 [cs.LG]) 

arxiv.org/abs/2305.02790

0
arXiv - CSCL

Automated Code generation for Information Technology Tasks in YAML through Large Language Models. (arXiv:2305.02783v1 [cs.SE]) 

arxiv.org/abs/2305.02783

0
arXiv - CSCL

Unified Model Learning for Various Neural Machine Translation. (arXiv:2305.02777v1 [cs.CL]) 

arxiv.org/abs/2305.02777

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