Show newer
arXiv - CSCL

Aligning Language Models with Offline Reinforcement Learning from Human Feedback. (arXiv:2308.12050v1 [cs.CL]) 

arxiv.org/abs/2308.12050

0
arXiv - CSCL

CgT-GAN: CLIP-guided Text GAN for Image Captioning. (arXiv:2308.12045v1 [cs.CV]) 

arxiv.org/abs/2308.12045

0
arXiv - CSCL

IncreLoRA: Incremental Parameter Allocation Method for Parameter-Efficient Fine-tuning. (arXiv:2308.12043v1 [cs.CL]) 

arxiv.org/abs/2308.12043

0
arXiv - CSCL

Hybrid Retrieval and Multi-stage Text Ranking Solution at TREC 2022 Deep Learning Track. (arXiv:2308.12039v1 [cs.IR]) 

arxiv.org/abs/2308.12039

0
arXiv - CSCL

Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages. (arXiv:2308.12038v1 [cs.CL]) 

arxiv.org/abs/2308.12038

0
arXiv - CSCL

PREFER: Prompt Ensemble Learning via Feedback-Reflect-Refine. (arXiv:2308.12033v1 [cs.CL]) 

arxiv.org/abs/2308.12033

0
arXiv - CSCL

From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning. (arXiv:2308.12032v1 [cs.CL]) 

arxiv.org/abs/2308.12032

0
arXiv - CSCL

Prompt-Based Length Controlled Generation with Reinforcement Learning. (arXiv:2308.12030v1 [cs.CL]) 

arxiv.org/abs/2308.12030

0
arXiv - CSCL

Knowledge-injected Prompt Learning for Chinese Biomedical Entity Normalization. (arXiv:2308.12025v1 [cs.CL]) 

arxiv.org/abs/2308.12025

0
arXiv - CSCL

Reranking Passages with Coarse-to-Fine Neural Retriever using List-Context Information. (arXiv:2308.12022v1 [cs.CL]) 

arxiv.org/abs/2308.12022

0
arXiv - CSCL

From Instructions to Intrinsic Human Values -- A Survey of Alignment Goals for Big Models. (arXiv:2308.12014v1 [cs.AI]) 

arxiv.org/abs/2308.12014

0
arXiv - CSCL

Graecia capta ferum victorem cepit. Detecting Latin Allusions to Ancient Greek Literature. (arXiv:2308.12008v1 [cs.CL]) 

arxiv.org/abs/2308.12008

0
arXiv - CSCL

Topical-Chat: Towards Knowledge-Grounded Open-Domain Conversations. (arXiv:2308.11995v1 [cs.CL]) 

arxiv.org/abs/2308.11995

0
arXiv - CSCL

EVE: Efficient Vision-Language Pre-training with Masked Prediction and Modality-Aware MoE. (arXiv:2308.11971v1 [cs.CV]) 

arxiv.org/abs/2308.11971

0
arXiv - CSCL

Audio Generation with Multiple Conditional Diffusion Model. (arXiv:2308.11940v1 [cs.SD]) 

arxiv.org/abs/2308.11940

0
arXiv - CSCL

Audio Difference Captioning Utilizing Similarity-Discrepancy Disentanglement. (arXiv:2308.11923v1 [eess.AS]) 

arxiv.org/abs/2308.11923

0
arXiv - CSCL

Bridging the Gap: Deciphering Tabular Data Using Large Language Model. (arXiv:2308.11891v1 [cs.CL]) 

arxiv.org/abs/2308.11891

0
arXiv - CSCL

Cabrita: closing the gap for foreign languages. (arXiv:2308.11878v1 [cs.CL]) 

arxiv.org/abs/2308.11878

0
arXiv - CSCL

Exploring the Effectiveness of GPT Models in Test-Taking: A Case Study of the Driver's License Knowledge Test. (arXiv:2308.11827v1 [cs.CL]) 

arxiv.org/abs/2308.11827

0
arXiv - CSCL

Towards an On-device Agent for Text Rewriting. (arXiv:2308.11807v1 [cs.CL]) 

arxiv.org/abs/2308.11807

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