Show newer
arXiv - CSCL

SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs. (arXiv:2306.17842v2 [cs.CV] UPDATED) 

arxiv.org/abs/2306.17842

0
arXiv - CSCL

Statler: State-Maintaining Language Models for Embodied Reasoning. (arXiv:2306.17840v2 [cs.RO] UPDATED) 

arxiv.org/abs/2306.17840

0
arXiv - CSCL

Progressive Multi-task Learning Framework for Chinese Text Error Correction. (arXiv:2306.17447v2 [cs.CL] UPDATED) 

arxiv.org/abs/2306.17447

0
arXiv - CSCL

LMBot: Distilling Graph Knowledge into Language Model for Graph-less Deployment in Twitter Bot Detection. (arXiv:2306.17408v2 [cs.AI] UPDATED) 

arxiv.org/abs/2306.17408

0
arXiv - CSCL

weighted CapsuleNet networks for Persian multi-domain sentiment analysis. (arXiv:2306.17068v2 [cs.CL] UPDATED) 

arxiv.org/abs/2306.17068

0
arXiv - CSCL

Probabilistic Linguistic Knowledge and Token-level Text Augmentation. (arXiv:2306.16644v2 [cs.CL] UPDATED) 

arxiv.org/abs/2306.16644

0
arXiv - CSCL

SparseOptimizer: Sparsify Language Models through Moreau-Yosida Regularization and Accelerate via Compiler Co-design. (arXiv:2306.15656v2 [cs.LG] UPDATED) 

arxiv.org/abs/2306.15656

0
arXiv - CSCL

MindDial: Belief Dynamics Tracking with Theory-of-Mind Modeling for Situated Neural Dialogue Generation. (arXiv:2306.15253v3 [cs.CL] UPDATED) 

arxiv.org/abs/2306.15253

0
arXiv - CSCL

On the Reliability of Watermarks for Large Language Models. (arXiv:2306.04634v3 [cs.LG] UPDATED) 

arxiv.org/abs/2306.04634

0
arXiv - CSCL

LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion. (arXiv:2306.02561v3 [cs.CL] UPDATED) 

arxiv.org/abs/2306.02561

0
arXiv - CSCL

Measuring the Robustness of Natural Language Processing Models to Domain Shifts. (arXiv:2306.00168v2 [cs.CL] UPDATED) 

arxiv.org/abs/2306.00168

0
arXiv - CSCL

W-procer: Weighted Prototypical Contrastive Learning for Medical Few-Shot Named Entity Recognition. (arXiv:2305.18624v3 [cs.CL] UPDATED) 

arxiv.org/abs/2305.18624

0
arXiv - CSCL

Practical PCG Through Large Language Models. (arXiv:2305.18243v3 [cs.CL] UPDATED) 

arxiv.org/abs/2305.18243

0
arXiv - CSCL

Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer. (arXiv:2305.16380v3 [cs.CL] UPDATED) 

arxiv.org/abs/2305.16380

0
arXiv - CSCL

MERGE: Fast Private Text Generation. (arXiv:2305.15769v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.15769

0
arXiv - CSCL

Zero-shot Approach to Overcome Perturbation Sensitivity of Prompts. (arXiv:2305.15689v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.15689

0
arXiv - CSCL

Is ChatGPT Fair for Recommendation? Evaluating Fairness in Large Language Model Recommendation. (arXiv:2305.07609v2 [cs.IR] UPDATED) 

arxiv.org/abs/2305.07609

0
arXiv - CSCL

How to Index Item IDs for Recommendation Foundation Models. (arXiv:2305.06569v3 [cs.IR] UPDATED) 

arxiv.org/abs/2305.06569

0
arXiv - CSCL

Analysis of Climate Campaigns on Social Media using Bayesian Model Averaging. (arXiv:2305.06174v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.06174

0
arXiv - CSCL

Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Models. (arXiv:2304.07619v3 [q-fin.ST] UPDATED) 

arxiv.org/abs/2304.07619

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