Show newer
arXiv - CSCL

Beyond Gradient and Priors in Privacy Attacks: Leveraging Pooler Layer Inputs of Language Models in Federated Learning. (arXiv:2312.05720v2 [cs.LG] UPDATED) 

arxiv.org/abs/2312.05720

0
arXiv - CSCL

Fovea Transformer: Efficient Long-Context Modeling with Structured Fine-to-Coarse Attention. (arXiv:2311.07102v2 [cs.CL] UPDATED) 

arxiv.org/abs/2311.07102

0
arXiv - CSCL

ALYMPICS: Language Agents Meet Game Theory -- Exploring Strategic Decision-Making with AI Agents. (arXiv:2311.03220v3 [cs.CL] UPDATED) 

arxiv.org/abs/2311.03220

0
arXiv - CSCL

CausalCite: A Causal Formulation of Paper Citations. (arXiv:2311.02790v2 [cs.CL] UPDATED) 

arxiv.org/abs/2311.02790

0
arXiv - CSCL

An Embedded Diachronic Sense Change Model with a Case Study from Ancient Greek. (arXiv:2311.00541v2 [cs.CL] UPDATED) 

arxiv.org/abs/2311.00541

0
arXiv - CSCL

Towards Robust Pruning: An Adaptive Knowledge-Retention Pruning Strategy for Language Models. (arXiv:2310.13191v3 [cs.CL] UPDATED) 

arxiv.org/abs/2310.13191

0
arXiv - CSCL

Breaking through Deterministic Barriers: Randomized Pruning Mask Generation and Selection. (arXiv:2310.13183v2 [cs.CV] UPDATED) 

arxiv.org/abs/2310.13183

0
arXiv - CSCL

Task Selection and Assignment for Multi-modal Multi-task Dialogue Act Classification with Non-stationary Multi-armed Bandits. (arXiv:2309.09832v2 [cs.CL] UPDATED) 

arxiv.org/abs/2309.09832

0
arXiv - CSCL

CORAL: Expert-Curated medical Oncology Reports to Advance Language Model Inference. (arXiv:2308.03853v3 [cs.CL] UPDATED) 

arxiv.org/abs/2308.03853

0
arXiv - CSCL

Automated Distractor and Feedback Generation for Math Multiple-choice Questions via In-context Learning. (arXiv:2308.03234v2 [cs.CL] UPDATED) 

arxiv.org/abs/2308.03234

0
arXiv - CSCL

Fine-Tuning Language Models with Just Forward Passes. (arXiv:2305.17333v3 [cs.LG] UPDATED) 

arxiv.org/abs/2305.17333

0
arXiv - CSCL

Heterogeneous Value Alignment Evaluation for Large Language Models. (arXiv:2305.17147v3 [cs.CL] UPDATED) 

arxiv.org/abs/2305.17147

0
arXiv - CSCL

Persian Typographical Error Type Detection Using Deep Neural Networks on Algorithmically-Generated Misspellings. (arXiv:2305.11731v4 [cs.CL] UPDATED) 

arxiv.org/abs/2305.11731

0
arXiv - CSCL

A Taxonomy of Foundation Model based Systems through the Lens of Software Architecture. (arXiv:2305.05352v5 [cs.SE] UPDATED) 

arxiv.org/abs/2305.05352

0
arXiv - CSCL

Linear Spaces of Meanings: Compositional Structures in Vision-Language Models. (arXiv:2302.14383v3 [cs.LG] UPDATED) 

arxiv.org/abs/2302.14383

0
arXiv - CSCL

TOFU: A Task of Fictitious Unlearning for LLMs. (arXiv:2401.06121v1 [cs.LG]) 

arxiv.org/abs/2401.06121

0
arXiv - CSCL

Extreme Compression of Large Language Models via Additive Quantization. (arXiv:2401.06118v1 [cs.LG]) 

arxiv.org/abs/2401.06118

0
arXiv - CSCL

Axis Tour: Word Tour Determines the Order of Axes in ICA-transformed Embeddings. (arXiv:2401.06112v1 [cs.CL]) 

arxiv.org/abs/2401.06112

0
arXiv - CSCL

PALP: Prompt Aligned Personalization of Text-to-Image Models. (arXiv:2401.06105v1 [cs.CV]) 

arxiv.org/abs/2401.06105

0
arXiv - CSCL

Transformers are Multi-State RNNs. (arXiv:2401.06104v1 [cs.CL]) 

arxiv.org/abs/2401.06104

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