Follow
Ilia Kulikov
Title
Cited by
Cited by
Year
Neural text generation with unlikelihood training
S Welleck, I Kulikov, S Roller, E Dinan, K Cho, J Weston
arXiv preprint arXiv:1908.04319, 2019
4942019
Don't say that! making inconsistent dialogue unlikely with unlikelihood training
M Li, S Roller, I Kulikov, S Welleck, YL Boureau, K Cho, J Weston
arXiv preprint arXiv:1911.03860, 2019
1812019
Importance of search and evaluation strategies in neural dialogue modeling
I Kulikov, AH Miller, K Cho, J Weston
arXiv preprint arXiv:1811.00907, 2018
115*2018
RETURNN: The RWTH extensible training framework for universal recurrent neural networks
P Doetsch, A Zeyer, P Voigtlaender, I Kulikov, R Schlüter, H Ney
2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017
812017
Consistency of a recurrent language model with respect to incomplete decoding
S Welleck, I Kulikov, J Kim, RY Pang, K Cho
arXiv preprint arXiv:2002.02492, 2020
632020
The RWTH/UPB/FORTH system combination for the 4th CHiME challenge evaluation
T Menne
Deutsche Nationalbibliothek, 2016
522016
Optimization of memory operations in generalized search trees of PostgreSQL
A Borodin, S Mirvoda, I Kulikov, S Porshnev
Beyond Databases, Architectures and Structures. Towards Efficient Solutions …, 2017
462017
SeamlessM4T-Massively Multilingual & Multimodal Machine Translation
L Barrault, YA Chung, MC Meglioli, D Dale, N Dong, PA Duquenne, ...
arXiv preprint arXiv:2308.11596, 2023
412023
Unity: Two-pass direct speech-to-speech translation with discrete units
H Inaguma, S Popuri, I Kulikov, PJ Chen, C Wang, YA Chung, Y Tang, ...
arXiv preprint arXiv:2212.08055, 2022
312022
Seamless: Multilingual Expressive and Streaming Speech Translation
L Barrault, YA Chung, MC Meglioli, D Dale, N Dong, M Duppenthaler, ...
arXiv preprint arXiv:2312.05187, 2023
172023
Simple and effective unsupervised speech translation
C Wang, H Inaguma, PJ Chen, I Kulikov, Y Tang, WN Hsu, M Auli, J Pino
arXiv preprint arXiv:2210.10191, 2022
142022
Vehicle communication strategies for simulated highway driving
C Resnick, I Kulikov, K Cho, J Weston
arXiv preprint arXiv:1804.07178, 2018
14*2018
Improving speech-to-speech translation through unlabeled text
XP Nguyen, S Popuri, C Wang, Y Tang, I Kulikov, H Gong
ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023
82023
Uncertainty determines the adequacy of the mode and the tractability of decoding in sequence-to-sequence models
F Stahlberg, I Kulikov, S Kumar
arXiv preprint arXiv:2204.00471, 2022
62022
Characterizing and addressing the issue of oversmoothing in neural autoregressive sequence modeling
I Kulikov, M Eremeev, K Cho
arXiv preprint arXiv:2112.08914, 2021
62021
Multi-resolution HuBERT: Multi-resolution Speech Self-Supervised Learning with Masked Unit Prediction
J Shi, H Inaguma, X Ma, I Kulikov, A Sun
arXiv preprint arXiv:2310.02720, 2023
52023
Multi-turn beam search for neural dialogue modeling
I Kulikov, J Lee, K Cho
arXiv preprint arXiv:1906.00141, 2019
42019
Mode recovery in neural autoregressive sequence modeling
I Kulikov, S Welleck, K Cho
arXiv preprint arXiv:2106.05459, 2021
32021
Faster sequence training
A Zeyer, I Kulikov, R Schlüter, H Ney
2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017
22017
MSLM-S2ST: A Multitask Speech Language Model for Textless Speech-to-Speech Translation with Speaker Style Preservation
Y Peng, I Kulikov, Y Yang, S Popuri, H Lu, C Wang, H Gong
arXiv preprint arXiv:2403.12408, 2024
12024
The system can't perform the operation now. Try again later.
Articles 1–20