Show newer
arXiv - CSCL

Task-Optimized Adapters for an End-to-End Task-Oriented Dialogue System. (arXiv:2305.02468v3 [cs.CL] UPDATED) 

arxiv.org/abs/2305.02468

0
arXiv - CSCL

Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling. (arXiv:2304.01373v2 [cs.CL] UPDATED) 

arxiv.org/abs/2304.01373

0
arXiv - CSCL

Aligning a medium-size GPT model in English to a small closed domain in Spanish. (arXiv:2303.17649v3 [cs.CL] UPDATED) 

arxiv.org/abs/2303.17649

0
arXiv - CSCL

cTBLS: Augmenting Large Language Models with Conversational Tables. (arXiv:2303.12024v3 [cs.CL] UPDATED) 

arxiv.org/abs/2303.12024

0
arXiv - CSCL

Exploring Partial Knowledge Base Inference in Biomedical Entity Linking. (arXiv:2303.10330v2 [cs.CL] UPDATED) 

arxiv.org/abs/2303.10330

0
arXiv - CSCL

Query-Utterance Attention with Joint modeling for Query-Focused Meeting Summarization. (arXiv:2303.04487v2 [cs.CL] UPDATED) 

arxiv.org/abs/2303.04487

0
arXiv - CSCL

Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models. (arXiv:2301.13826v2 [cs.CV] UPDATED) 

arxiv.org/abs/2301.13826

0
arXiv - CSCL

UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers. (arXiv:2301.13741v2 [cs.CV] UPDATED) 

arxiv.org/abs/2301.13741

0
arXiv - CSCL

Understanding INT4 Quantization for Transformer Models: Latency Speedup, Composability, and Failure Cases. (arXiv:2301.12017v2 [cs.CL] UPDATED) 

arxiv.org/abs/2301.12017

0
arXiv - CSCL

Matching Exemplar as Next Sentence Prediction (MeNSP): Zero-shot Prompt Learning for Automatic Scoring in Science Education. (arXiv:2301.08771v4 [cs.CL] UPDATED) 

arxiv.org/abs/2301.08771

0
arXiv - CSCL

Continual Contrastive Finetuning Improves Low-Resource Relation Extraction. (arXiv:2212.10823v3 [cs.CL] UPDATED) 

arxiv.org/abs/2212.10823

0
arXiv - CSCL

Generic Temporal Reasoning with Differential Analysis and Explanation. (arXiv:2212.10467v2 [cs.CL] UPDATED) 

arxiv.org/abs/2212.10467

0
arXiv - CSCL

ClarifyDelphi: Reinforced Clarification Questions with Defeasibility Rewards for Social and Moral Situations. (arXiv:2212.10409v3 [cs.CL] UPDATED) 

arxiv.org/abs/2212.10409

0
arXiv - CSCL

I Cast Detect Thoughts: Learning to Converse and Guide with Intents and Theory-of-Mind in Dungeons and Dragons. (arXiv:2212.10060v2 [cs.CL] UPDATED) 

arxiv.org/abs/2212.10060

0
arXiv - CSCL

Synthetic Pre-Training Tasks for Neural Machine Translation. (arXiv:2212.09864v2 [cs.CL] UPDATED) 

arxiv.org/abs/2212.09864

0
arXiv - CSCL

Cross-Lingual Retrieval Augmented Prompt for Low-Resource Languages. (arXiv:2212.09651v3 [cs.CL] UPDATED) 

arxiv.org/abs/2212.09651

0
arXiv - CSCL

DuNST: Dual Noisy Self Training for Semi-Supervised Controllable Text Generation. (arXiv:2212.08724v2 [cs.CL] UPDATED) 

arxiv.org/abs/2212.08724

0
arXiv - CSCL

Transformers learn in-context by gradient descent. (arXiv:2212.07677v2 [cs.LG] UPDATED) 

arxiv.org/abs/2212.07677

0
arXiv - CSCL

MT4SSL: Boosting Self-Supervised Speech Representation Learning by Integrating Multiple Targets. (arXiv:2211.07321v3 [cs.CL] UPDATED) 

arxiv.org/abs/2211.07321

0
arXiv - CSCL

Evaluating context-invariance in unsupervised speech representations. (arXiv:2210.15775v2 [cs.CL] UPDATED) 

arxiv.org/abs/2210.15775

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