Show newer
arXiv - CSCL

HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination & Visual Illusion in Large Vision-Language Models. (arXiv:2310.14566v2 [cs.CV] UPDATED) 

arxiv.org/abs/2310.14566

0
arXiv - CSCL

Chameleon: a heterogeneous and disaggregated accelerator system for retrieval-augmented language models. (arXiv:2310.09949v3 [cs.LG] UPDATED) 

arxiv.org/abs/2310.09949

0
arXiv - CSCL

An Attribution Method for Siamese Encoders. (arXiv:2310.05703v3 [cs.CL] UPDATED) 

arxiv.org/abs/2310.05703

0
arXiv - CSCL

Loose lips sink ships: Mitigating Length Bias in Reinforcement Learning from Human Feedback. (arXiv:2310.05199v5 [cs.CL] UPDATED) 

arxiv.org/abs/2310.05199

0
arXiv - CSCL

Navigating Cultural Chasms: Exploring and Unlocking the Cultural POV of Text-To-Image Models. (arXiv:2310.01929v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.01929

0
arXiv - CSCL

DeepSpeed-VisualChat: Multi-Round Multi-Image Interleave Chat via Multi-Modal Causal Attention. (arXiv:2309.14327v3 [cs.CV] UPDATED) 

arxiv.org/abs/2309.14327

0
arXiv - CSCL

Arabic Sentiment Analysis with Noisy Deep Explainable Model. (arXiv:2309.13731v2 [cs.CL] UPDATED) 

arxiv.org/abs/2309.13731

0
arXiv - CSCL

On Separate Normalization in Self-supervised Transformers. (arXiv:2309.12931v2 [cs.CL] UPDATED) 

arxiv.org/abs/2309.12931

0
arXiv - CSCL

Explainability for Large Language Models: A Survey. (arXiv:2309.01029v3 [cs.CL] UPDATED) 

arxiv.org/abs/2309.01029

0
arXiv - CSCL

Towards Understanding In-Context Learning with Contrastive Demonstrations and Saliency Maps. (arXiv:2307.05052v2 [cs.CL] UPDATED) 

arxiv.org/abs/2307.05052

0
arXiv - CSCL

Does Conceptual Representation Require Embodiment? Insights From Large Language Models. (arXiv:2305.19103v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.19103

0
arXiv - CSCL

MuLER: Detailed and Scalable Reference-based Evaluation. (arXiv:2305.14991v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14991

0
arXiv - CSCL

Adapting Sentence Transformers for the Aviation Domain. (arXiv:2305.09556v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.09556

0
arXiv - CSCL

SUR-adapter: Enhancing Text-to-Image Pre-trained Diffusion Models with Large Language Models. (arXiv:2305.05189v4 [cs.CL] UPDATED) 

arxiv.org/abs/2305.05189

0
arXiv - CSCL

Exploring Human-Like Translation Strategy with Large Language Models. (arXiv:2305.04118v3 [cs.CL] UPDATED) 

arxiv.org/abs/2305.04118

0
arXiv - CSCL

Diffusion Glancing Transformer for Parallel Sequence to Sequence Learning. (arXiv:2212.10240v2 [cs.CL] UPDATED) 

arxiv.org/abs/2212.10240

0
arXiv - CSCL

Multi-turn Response Selection using Dialogue Dependency Relations. (arXiv:2010.01502v2 [cs.CL] UPDATED) 

arxiv.org/abs/2010.01502

0
arXiv - CSCL

Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planning. (arXiv:2311.17842v1 [cs.RO]) 

arxiv.org/abs/2311.17842

0
arXiv - CSCL

Higher-Order DisCoCat (Peirce-Lambek-Montague semantics). (arXiv:2311.17813v1 [cs.CL]) 

arxiv.org/abs/2311.17813

0
arXiv - CSCL

DSS: Synthesizing long Digital Ink using Data augmentation, Style encoding and Split generation. (arXiv:2311.17786v1 [cs.HC]) 

arxiv.org/abs/2311.17786

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