Show newer
arXiv - CSCL

To Asymmetry and Beyond: Structured Pruning of Sequence to Sequence Models for Improved Inference Efficiency. (arXiv:2304.02721v1 [cs.CL]) 

arxiv.org/abs/2304.02721

0
arXiv - CSCL

ParroT: Translating During Chat Using Large Language Models. (arXiv:2304.02426v2 [cs.CL] UPDATED) 

arxiv.org/abs/2304.02426

0
arXiv - CSCL

Large Language Models as Master Key: Unlocking the Secrets of Materials Science with GPT. (arXiv:2304.02213v2 [cs.CL] UPDATED) 

arxiv.org/abs/2304.02213

0
arXiv - CSCL

Unlocking the Potential of ChatGPT: A Comprehensive Exploration of its Applications, Advantages, Limitations, and Future Directions in Natural Language Processing. (arXiv:2304.02017v2 [cs.CL] UPDATED) 

arxiv.org/abs/2304.02017

0
arXiv - CSCL

RPTQ: Reorder-based Post-training Quantization for Large Language Models. (arXiv:2304.01089v2 [cs.CL] UPDATED) 

arxiv.org/abs/2304.01089

0
arXiv - CSCL

ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance. (arXiv:2303.16894v2 [cs.CV] UPDATED) 

arxiv.org/abs/2303.16894

0
arXiv - CSCL

Task-oriented Memory-efficient Pruning-Adapter. (arXiv:2303.14704v2 [cs.CL] UPDATED) 

arxiv.org/abs/2303.14704

0
arXiv - CSCL

Return of the RNN: Residual Recurrent Networks for Invertible Sentence Embeddings. (arXiv:2303.13570v2 [cs.CL] UPDATED) 

arxiv.org/abs/2303.13570

0
arXiv - CSCL

Zero-Shot Cross-Lingual Summarization via Large Language Models. (arXiv:2302.14229v2 [cs.CL] UPDATED) 

arxiv.org/abs/2302.14229

0
arXiv - CSCL

Dataless Knowledge Fusion by Merging Weights of Language Models. (arXiv:2212.09849v2 [cs.CL] UPDATED) 

arxiv.org/abs/2212.09849

0
arXiv - CSCL

From exemplar to copy: the scribal appropriation of a Hadewijch manuscript computationally explored. (arXiv:2210.14061v4 [cs.CL] UPDATED) 

arxiv.org/abs/2210.14061

0
arXiv - CSCL

Toxicity in Multilingual Machine Translation at Scale. (arXiv:2210.03070v2 [cs.CL] UPDATED) 

arxiv.org/abs/2210.03070

0
arXiv - CSCL

Boosting Multi-Modal E-commerce Attribute Value Extraction via Unified Learning Scheme and Dynamic Range Minimization. (arXiv:2207.07278v2 [cs.CV] UPDATED) 

arxiv.org/abs/2207.07278

0
arXiv - CSCL

Sparse*BERT: Sparse Models Generalize To New tasks and Domains. (arXiv:2205.12452v3 [cs.CL] UPDATED) 

arxiv.org/abs/2205.12452

0
arXiv - CSCL

Term Rewriting Based On Set Automaton Matching. (arXiv:2202.08687v3 [cs.CL] UPDATED) 

arxiv.org/abs/2202.08687

0
arXiv - CSCL

Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark. (arXiv:2304.03279v1 [cs.LG]) 

arxiv.org/abs/2304.03279

0
arXiv - CSCL

Instruction Tuning with GPT-4. (arXiv:2304.03277v1 [cs.CL]) 

arxiv.org/abs/2304.03277

0
arXiv - CSCL

Large language models effectively leverage document-level context for literary translation, but critical errors persist. (arXiv:2304.03245v1 [cs.CL]) 

arxiv.org/abs/2304.03245

0
arXiv - CSCL

FedBot: Enhancing Privacy in Chatbots with Federated Learning. (arXiv:2304.03228v1 [cs.CL]) 

arxiv.org/abs/2304.03228

0
arXiv - CSCL

On the Pareto Front of Multilingual Neural Machine Translation. (arXiv:2304.03216v1 [cs.CL]) 

arxiv.org/abs/2304.03216

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