Show newer
arXiv - CSCL

Zero-shot Triplet Extraction by Template Infilling. (arXiv:2212.10708v2 [cs.CL] UPDATED) 

arxiv.org/abs/2212.10708

0
arXiv - CSCL

Development of Hybrid ASR Systems for Low Resource Medical Domain Conversational Telephone Speech. (arXiv:2210.13397v3 [cs.CL] UPDATED) 

arxiv.org/abs/2210.13397

0
arXiv - CSCL

Attacking Open-domain Question Answering by Injecting Misinformation. (arXiv:2110.07803v3 [cs.CL] UPDATED) 

arxiv.org/abs/2110.07803

0
arXiv - CSCL

Procedures as Programs: Hierarchical Control of Situated Agents through Natural Language. (arXiv:2109.08214v2 [cs.CL] UPDATED) 

arxiv.org/abs/2109.08214

0
arXiv - CSCL

DreamLLM: Synergistic Multimodal Comprehension and Creation. (arXiv:2309.11499v1 [cs.CV]) 

arxiv.org/abs/2309.11499

0
arXiv - CSCL

Chain-of-Verification Reduces Hallucination in Large Language Models. (arXiv:2309.11495v1 [cs.CL]) 

arxiv.org/abs/2309.11495

0
arXiv - CSCL

Text2Reward: Automated Dense Reward Function Generation for Reinforcement Learning. (arXiv:2309.11489v1 [cs.LG]) 

arxiv.org/abs/2309.11489

0
arXiv - CSCL

Controlled Generation with Prompt Insertion for Natural Language Explanations in Grammatical Error Correction. (arXiv:2309.11439v1 [cs.CL]) 

arxiv.org/abs/2309.11439

0
arXiv - CSCL

You Only Look at Screens: Multimodal Chain-of-Action Agents. (arXiv:2309.11436v1 [cs.CL]) 

arxiv.org/abs/2309.11436

0
arXiv - CSCL

Kosmos-2.5: A Multimodal Literate Model. (arXiv:2309.11419v1 [cs.CL]) 

arxiv.org/abs/2309.11419

0
arXiv - CSCL

Safurai 001: New Qualitative Approach for Code LLM Evaluation. (arXiv:2309.11385v1 [cs.CL]) 

arxiv.org/abs/2309.11385

0
arXiv - CSCL

Long-Form End-to-End Speech Translation via Latent Alignment Segmentation. (arXiv:2309.11384v1 [cs.CL]) 

arxiv.org/abs/2309.11384

0
arXiv - CSCL

Discuss Before Moving: Visual Language Navigation via Multi-expert Discussions. (arXiv:2309.11382v1 [cs.RO]) 

arxiv.org/abs/2309.11382

0
arXiv - CSCL

Studying Lobby Influence in the European Parliament. (arXiv:2309.11381v1 [cs.CL]) 

arxiv.org/abs/2309.11381

0
arXiv - CSCL

Incremental Blockwise Beam Search for Simultaneous Speech Translation with Controllable Quality-Latency Tradeoff. (arXiv:2309.11379v1 [cs.CL]) 

arxiv.org/abs/2309.11379

0
arXiv - CSCL

GECTurk: Grammatical Error Correction and Detection Dataset for Turkish. (arXiv:2309.11346v1 [cs.CL]) 

arxiv.org/abs/2309.11346

0
arXiv - CSCL

Improving Article Classification with Edge-Heterogeneous Graph Neural Networks. (arXiv:2309.11341v1 [cs.LG]) 

arxiv.org/abs/2309.11341

0
arXiv - CSCL

TRAVID: An End-to-End Video Translation Framework. (arXiv:2309.11338v1 [cs.CL]) 

arxiv.org/abs/2309.11338

0
arXiv - CSCL

Leveraging Data Collection and Unsupervised Learning for Code-switched Tunisian Arabic Automatic Speech Recognition. (arXiv:2309.11327v1 [eess.AS]) 

arxiv.org/abs/2309.11327

0
arXiv - CSCL

DISC-LawLLM: Fine-tuning Large Language Models for Intelligent Legal Services. (arXiv:2309.11325v1 [cs.CL]) 

arxiv.org/abs/2309.11325

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