Show newer
arXiv - CSCL

Write and Paint: Generative Vision-Language Models are Unified Modal Learners. (arXiv:2206.07699v2 [cs.CV] UPDATED) 

arxiv.org/abs/2206.07699

0
arXiv - CSCL

BigVGAN: A Universal Neural Vocoder with Large-Scale Training. (arXiv:2206.04658v2 [cs.SD] UPDATED) 

arxiv.org/abs/2206.04658

0
arXiv - CSCL

Neuro-Symbolic Procedural Planning with Commonsense Prompting. (arXiv:2206.02928v6 [cs.CL] UPDATED) 

arxiv.org/abs/2206.02928

0
arXiv - CSCL

BITE: Textual Backdoor Attacks with Iterative Trigger Injection. (arXiv:2205.12700v2 [cs.CL] UPDATED) 

arxiv.org/abs/2205.12700

0
arXiv - CSCL

Event Linking: Grounding Event Mentions to Wikipedia. (arXiv:2112.07888v3 [cs.CL] UPDATED) 

arxiv.org/abs/2112.07888

0
arXiv - CSCL

Predictions For Pre-training Language Models. (arXiv:2011.09031v4 [cs.CL] UPDATED) 

arxiv.org/abs/2011.09031

0
arXiv - CSCL

Pairwise Representation Learning for Event Coreference. (arXiv:2010.12808v3 [cs.CL] UPDATED) 

arxiv.org/abs/2010.12808

0
arXiv - CSCL

Auditing large language models: a three-layered approach. (arXiv:2302.08500v1 [cs.CL]) 

arxiv.org/abs/2302.08500

0
arXiv - CSCL

LEVER: Learning to Verify Language-to-Code Generation with Execution. (arXiv:2302.08468v1 [cs.LG]) 

arxiv.org/abs/2302.08468

0
arXiv - CSCL

Evaluating and Improving the Coreference Capabilities of Machine Translation Models. (arXiv:2302.08464v1 [cs.CL]) 

arxiv.org/abs/2302.08464

0
arXiv - CSCL

Large Language Models Fail on Trivial Alterations to Theory-of-Mind Tasks. (arXiv:2302.08399v1 [cs.AI]) 

arxiv.org/abs/2302.08399

0
arXiv - CSCL

LEALLA: Learning Lightweight Language-agnostic Sentence Embeddings with Knowledge Distillation. (arXiv:2302.08387v1 [cs.CL]) 

arxiv.org/abs/2302.08387

0
arXiv - CSCL

Efficiency 360: Efficient Vision Transformers. (arXiv:2302.08374v1 [cs.CV]) 

arxiv.org/abs/2302.08374

0
arXiv - CSCL

Conversation Style Transfer using Few-Shot Learning. (arXiv:2302.08362v1 [cs.CL]) 

arxiv.org/abs/2302.08362

0
arXiv - CSCL

A Survey on Event-based News Narrative Extraction. (arXiv:2302.08351v1 [cs.CL]) 

arxiv.org/abs/2302.08351

0
arXiv - CSCL

Cluster-based Deep Ensemble Learning for Emotion Classification in Internet Memes. (arXiv:2302.08343v1 [cs.CV]) 

arxiv.org/abs/2302.08343

0
arXiv - CSCL

NUAA-QMUL-AIIT at Memotion 3: Multi-modal Fusion with Squeeze-and-Excitation for Internet Meme Emotion Analysis. (arXiv:2302.08326v1 [cs.CL]) 

arxiv.org/abs/2302.08326

0
arXiv - CSCL

Retrieval-augmented Image Captioning. (arXiv:2302.08268v1 [cs.CV]) 

arxiv.org/abs/2302.08268

0
arXiv - CSCL

Tragic and Comical Networks. Clustering Dramatic Genres According to Structural Properties. (arXiv:2302.08258v1 [cs.CL]) 

arxiv.org/abs/2302.08258

0
arXiv - CSCL

Improving Spoken Language Identification with Map-Mix. (arXiv:2302.08229v1 [cs.LG]) 

arxiv.org/abs/2302.08229

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