Подписаться
Luke Vilnis
Luke Vilnis
Research Scientist, Google DeepMind
Подтвержден адрес электронной почты в домене google.com - Главная страница
Название
Процитировано
Процитировано
Год
Generating sentences from a continuous space
SR Bowman, L Vilnis, O Vinyals, AM Dai, R Jozefowicz, S Bengio
Conference on Computational Natural Language Learning (CoNLL), 2016
29552016
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
G Team, P Georgiev, VI Lei, R Burnell, L Bai, A Gulati, G Tanzer, ...
arXiv preprint arXiv:2403.05530, 2024
13052024
Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning
R Das, S Dhuliawala, M Zaheer, L Vilnis, I Durugkar, A Krishnamurthy, ...
International Conference on Learning Representations (ICLR), 2018
6822018
Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases with Reinforcement Learning
R Das, S Dhuliawala, M Zaheer, L Vilnis, I Durugkar, A Krishnamurthy, ...
NIPS Workshop on Automated Knowledge Base Construction (AKBC), 2017
682*2017
Word Representations via Gaussian Embedding
L Vilnis, A McCallum
International Conference on Learning Representations (ICLR), 2015
6512015
Adding gradient noise improves learning for very deep networks
A Neelakantan, L Vilnis, QV Le, I Sutskever, L Kaiser, K Kurach, J Martens
International Conference on Learning Representations Workshop (ICLR WS), 2016
6352016
Probabilistic Embedding of Knowledge Graphs with Box Lattice Measures
L Vilnis, X Li, S Murty, A McCallum
Annual Meeting of the Association for Computational Linguistics (ACL), 2018
1582018
Hierarchical Losses and New Resources for Fine-grained Entity Typing and Linking
S Murty, P Verga, L Vilnis, I Radovanovic, A McCallum
116*
Smoothing the geometry of probabilistic box embeddings
X Li, L Vilnis, D Zhang, M Boratko, A McCallum
International conference on learning representations, 2018
1042018
Unsupervised Hypernym Detection by Distributional Inclusion Vector Embedding
HS Chang, ZY Wang, L Vilnis, A McCallum
North American Chapter of the Association for Computational Linguistics (NAACL), 2018
76*2018
Codegemma: Open code models based on gemma
CG Team, H Zhao, J Hui, J Howland, N Nguyen, S Zuo, A Hu, ...
arXiv preprint arXiv:2406.11409, 2024
712024
Improving local identifiability in probabilistic box embeddings
S Dasgupta, M Boratko, D Zhang, L Vilnis, X Li, A McCallum
Advances in Neural Information Processing Systems 33, 182-192, 2020
682020
Dynamic knowledge-base alignment for coreference resolution
J Zheng, L Vilnis, S Singh, JD Choi, A McCallum
Conference on Computational Natural Language Learning (CoNLL), 2013
342013
Bethe Projections for Non-Local Inference
L Vilnis, D Belanger, D Sheldon, A McCallum
Uncertainty in Artificial Intelligence (UAI), 2015
312015
Adding gradient noise improves learning for very deep networks. arXiv 2015
A Neelakantan, L Vilnis, QV Le, I Sutskever, L Kaiser, K Kurach, J Martens
arXiv preprint arXiv:1511.06807, 2020
302020
Representing joint hierarchies with box embeddings
D Patel, S Sankar
Automated Knowledge Base Construction, 2020
272020
Finer Grained Entity Typing with TypeNet
S Murty, P Verga, L Vilnis, A McCallum
NIPS Workshop on Automated Knowledge Base Construction (AKBC), 2017
242017
Learning Dynamic Feature Selection for Fast Sequential Prediction
E Strubell, L Vilnis, K Silverstein, A McCallum
Annual Meeting of the Association for Computational Linguistics (ACL), 2015
202015
Improved Representation Learning for Predicting Commonsense Ontologies
X Li, L Vilnis, A McCallum
ICML Workshop on Deep Structured Prediction (ICML WS), 2017
152017
Capacity and bias of learned geometric embeddings for directed graphs
M Boratko, D Zhang, N Monath, L Vilnis, KL Clarkson, A McCallum
Advances in Neural Information Processing Systems 34, 16423-16436, 2021
142021
В данный момент система не может выполнить эту операцию. Повторите попытку позднее.
Статьи 1–20