Show newer

GPT-4 Technical Report. (arXiv:2303.08774v3 [cs.CL] UPDATED) 

NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions. (arXiv:2303.08233v2 [cs.CL] UPDATED) 

MEDBERT.de: A Comprehensive German BERT Model for the Medical Domain. (arXiv:2303.08179v2 [cs.CL] UPDATED) 

Audio Visual Language Maps for Robot Navigation. (arXiv:2303.07522v2 [cs.RO] UPDATED) 

Parachute: Evaluating Interactive Human-LM Co-writing Systems. (arXiv:2303.06333v2 [cs.HC] UPDATED) 

ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction. (arXiv:2303.05063v2 [cs.CL] UPDATED) 

Model-Agnostic Meta-Learning for Natural Language Understanding Tasks in Finance. (arXiv:2303.02841v2 [cs.CL] UPDATED) 

Linear Spaces of Meanings: Compositional Structures in Vision-Language Models. (arXiv:2302.14383v2 [cs.LG] UPDATED) 

Chain of Hindsight Aligns Language Models with Feedback. (arXiv:2302.02676v6 [cs.LG] UPDATED) 

Editing Language Model-based Knowledge Graph Embeddings. (arXiv:2301.10405v4 [cs.CL] UPDATED) 

Zero-Shot Rumor Detection with Propagation Structure via Prompt Learning. (arXiv:2212.01117v3 [cs.CL] UPDATED) 

Multi-Modal Few-Shot Temporal Action Detection. (arXiv:2211.14905v2 [cs.CV] UPDATED) 

Seeing What You Miss: Vision-Language Pre-training with Semantic Completion Learning. (arXiv:2211.13437v2 [cs.CV] UPDATED) 

Visually Grounded Commonsense Knowledge Acquisition. (arXiv:2211.12054v2 [cs.CV] UPDATED) 

Deep Temporal Modelling of Clinical Depression through Social Media Text. (arXiv:2211.07717v2 [cs.CL] UPDATED) 

Grammatical Error Correction: A Survey of the State of the Art. (arXiv:2211.05166v3 [cs.CL] UPDATED) 

Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language Models. (arXiv:2210.16433v3 [cs.CL] UPDATED) 

End-to-End Entity Detection with Proposer and Regressor. (arXiv:2210.10260v3 [cs.CL] UPDATED) 

Zero-Shot On-the-Fly Event Schema Induction. (arXiv:2210.06254v2 [cs.CL] UPDATED) 

MAP: Multimodal Uncertainty-Aware Vision-Language Pre-training Model. (arXiv:2210.05335v2 [cs.CV] UPDATED) 

Show older
Qoto Mastodon

QOTO: Question Others to Teach Ourselves
An inclusive, Academic Freedom, instance
All cultures welcome.
Hate speech and harassment strictly forbidden.