Show newer
arXiv - CSCL

LeRaC: Learning Rate Curriculum. (arXiv:2205.09180v2 [cs.LG] UPDATED) 

arxiv.org/abs/2205.09180

0
arXiv - CSCL

AdaVAE: Exploring Adaptive GPT-2s in Variational Auto-Encoders for Language Modeling. (arXiv:2205.05862v3 [cs.CL] UPDATED) 

arxiv.org/abs/2205.05862

0
arXiv - CSCL

Building for Tomorrow: Assessing the Temporal Persistence of Text Classifiers. (arXiv:2205.05435v6 [cs.CL] UPDATED) 

arxiv.org/abs/2205.05435

0
arXiv - CSCL

UDAAN: Machine Learning based Post-Editing tool for Document Translation. (arXiv:2203.01644v3 [cs.CL] UPDATED) 

arxiv.org/abs/2203.01644

0
arXiv - CSCL

GUDN: A novel guide network with label reinforcement strategy for extreme multi-label text classification. (arXiv:2201.11582v2 [cs.CL] UPDATED) 

arxiv.org/abs/2201.11582

0
arXiv - CSCL

Does Entity Abstraction Help Generative Transformers Reason?. (arXiv:2201.01787v2 [cs.CL] UPDATED) 

arxiv.org/abs/2201.01787

0
arXiv - CSCL

Surface Form Competition: Why the Highest Probability Answer Isn't Always Right. (arXiv:2104.08315v9 [cs.CL] UPDATED) 

arxiv.org/abs/2104.08315

0
arXiv - CSCL

Rethinking Attention with Performers. (arXiv:2009.14794v4 [cs.LG] UPDATED) 

arxiv.org/abs/2009.14794

0
arXiv - CSCL

Convexifying Transformers: Improving optimization and understanding of transformer networks. (arXiv:2211.11052v1 [cs.LG] CROSS LISTED) 

arxiv.org/abs/2211.11052

0
arXiv - CSCL

Multitask Vision-Language Prompt Tuning. (arXiv:2211.11720v2 [cs.CV] UPDATED) 

arxiv.org/abs/2211.11720

0
arXiv - CSCL

SMAUG: Sparse Masked Autoencoder for Efficient Video-Language Pre-training. (arXiv:2211.11446v2 [cs.CV] UPDATED) 

arxiv.org/abs/2211.11446

0
arXiv - CSCL

Sequentially Sampled Chunk Conformer for Streaming End-to-End ASR. (arXiv:2211.11419v2 [cs.SD] UPDATED) 

arxiv.org/abs/2211.11419

0
arXiv - CSCL

L3Cube-MahaSBERT and HindSBERT: Sentence BERT Models and Benchmarking BERT Sentence Representations for Hindi and Marathi. (arXiv:2211.11187v2 [cs.CL] UPDATED) 

arxiv.org/abs/2211.11187

0
arXiv - CSCL

Explaining (Sarcastic) Utterances to Enhance Affect Understanding in Multimodal Dialogues. (arXiv:2211.11049v2 [cs.CL] UPDATED) 

arxiv.org/abs/2211.11049

0
arXiv - CSCL

KnowGL: Knowledge Generation and Linking from Text. (arXiv:2210.13952v5 [cs.CL] UPDATED) 

arxiv.org/abs/2210.13952

0
arXiv - CSCL

Selection Induced Collider Bias: A Gender Pronoun Uncertainty Case Study. (arXiv:2210.00131v2 [cs.CL] UPDATED) 

arxiv.org/abs/2210.00131

0
arXiv - CSCL

ConvNext Based Neural Network for Audio Anti-Spoofing. (arXiv:2209.06434v3 [cs.SD] UPDATED) 

arxiv.org/abs/2209.06434

0
arXiv - CSCL

DM$^2$S$^2$: Deep Multi-Modal Sequence Sets with Hierarchical Modality Attention. (arXiv:2209.03126v2 [cs.MM] UPDATED) 

arxiv.org/abs/2209.03126

0
arXiv - CSCL

BabelBERT: Massively Multilingual Transformers Meet a Massively Multilingual Lexical Resource. (arXiv:2208.01018v2 [cs.CL] UPDATED) 

arxiv.org/abs/2208.01018

0
arXiv - CSCL

MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge. (arXiv:2206.08853v2 [cs.LG] UPDATED) 

arxiv.org/abs/2206.08853

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