Ting-Han Fan

Alexander Rudnicky

Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Short Papers, 2024

Attention Alignment and Flexible Positional Embeddings Improve Transformer Length Extrapolation.

[BibT_eX]

[DOI]

Alexander Rudnicky

Proceedings of the Findings of the Association for Computational Linguistics: NAACL 2024, 2024

2023

Transformer Working Memory Enables Regular Language Reasoning And Natural Language Length Extrapolation.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, 2023

Dissecting Transformer Length Extrapolation via the Lens of Receptive Field Analysis.

[BibT_eX]

[DOI]

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023

Latent Positional Information is in the Self-Attention Variance of Transformer Language Models Without Positional Embeddings.

[BibT_eX]

[DOI]

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 2023

2022

Receptive Field Alignment Enables Transformer Length Extrapolation.

[BibT_eX]

[DOI]

Alexander I. Rudnicky

CoRR, 2022

KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

PowerGym: A Reinforcement Learning Environment for Volt-Var Control in Power Distribution Systems.

[BibT_eX]

[DOI]

Xian Yeow Lee

Yubo Wang

Proceedings of the Learning for Dynamics and Control Conference, 2022

Training Discrete Deep Generative Models via Gapped Straight-Through Estimator.

[BibT_eX]

[DOI]

Alexander I. Rudnicky

Proceedings of the International Conference on Machine Learning, 2022

Safety Control for Prime Focus Spectrograph.

[BibT_eX]

[DOI]

Athindran Ramesh Kumar

Proceedings of the 56th Annual Conference on Information Sciences and Systems, 2022

Soft Actor-Critic With Integer Actions.

[BibT_eX]

[DOI]

Yubo Wang

Proceedings of the American Control Conference, 2022

2021

Explaining Off-Policy Actor-Critic From A Bias-Variance Perspective.

[BibT_eX]

[DOI]

CoRR, 2021

A Contraction Approach to Model-based Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2019

Model Imitation for Model-Based Reinforcement Learning.

[BibT_eX]

[DOI]

CoRR, 2019

2018

Rumor Source Detection: A Probabilistic Perspective.

[BibT_eX]

[DOI]

I-Hsiang Wang

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

2017

A New Social Network Model of Online Forums.

[BibT_eX]

[DOI]