Ivan Kobyzev
Ivan Kobyzev
ML Researcher, Huawei Noah's Ark
Verified email at
Cited by
Cited by
Normalizing flows: An introduction and review of current methods
I Kobyzev, SJD Prince, MA Brubaker
IEEE transactions on pattern analysis and machine intelligence 43 (11), 3964 …, 2020
Representation Learning for Dynamic Graphs: A Survey
SM Kazemi, R Goel, K Jain, I Kobyzev, A Sethi, P Forsyth, P Poupart
Journal of Machine Learning Research 21 (70), 1-73, 2020
Dylora: Parameter efficient tuning of pre-trained models using dynamic search-free low-rank adaptation
M Valipour, M Rezagholizadeh, I Kobyzev, A Ghodsi
arXiv preprint arXiv:2210.07558, 2022
Krona: Parameter efficient tuning with kronecker adapter
A Edalati, M Tahaei, I Kobyzev, VP Nia, JJ Clark, M Rezagholizadeh
arXiv preprint arXiv:2212.10650, 2022
Tails of Lipschitz triangular flows
P Jaini, I Kobyzev, Y Yu, M Brubaker
International Conference on Machine Learning, 4673-4681, 2020
A short study on compressing decoder-based language models
T Li, YE Mesbahi, I Kobyzev, A Rashid, A Mahmud, N Anchuri, ...
arXiv preprint arXiv:2110.08460, 2021
Polarized-VAE: Proximity based disentangled representation learning for text generation
V Balasubramanian, I Kobyzev, H Bahuleyan, I Shapiro, O Vechtomova
arXiv preprint arXiv:2004.10809, 2020
Generating emotionally aligned responses in dialogues using affect control theory
N Asghar, I Kobyzev, J Hoey, P Poupart, MB Sheikh
arXiv preprint arXiv:2003.03645, 2020
A categorical approach to cyclic cohomology of quasi-Hopf algebras and Hopf algebroids
I Kobyzev, I Shapiro
Applied Categorical Structures 27, 85-109, 2019
Improving generalization of pre-trained language models via stochastic weight averaging
P Lu, I Kobyzev, M Rezagholizadeh, A Rashid, A Ghodsi, P Langlais
arXiv preprint arXiv:2212.05956, 2022
Equivariant Discrete Normalizing Flows
AJ Bose, I Kobyzev
CoRR, 2021
Anti-Yetter-Drinfeld modules for quasi-Hopf algebras
I Kobyzev, I Shapiro
Symmetry, Integrability and Geometry: Methods and Applications (SIGMA) 14 (098), 2018
Continuation kd: Improved knowledge distillation through the lens of continuation optimization
A Jafari, I Kobyzev, M Rezagholizadeh, P Poupart, A Ghodsi
arXiv preprint arXiv:2212.05998, 2022
A semi-holographic hyperdimensional representation system for hardware-friendly cognitive computing
A Serb, I Kobyzev, J Wang, T Prodromakis
Philosophical Transactions of the Royal Society A 378 (2164), 20190162, 2020
Do we need Label Regularization to Fine-tune Pre-trained Language Models?
I Kobyzev, A Jafari, M Rezagholizadeh, T Li, A Do-Omri, P Lu, P Poupart, ...
arXiv preprint arXiv:2205.12428, 2022
G-theory of root stacks and equivariant K-theory
A Dhillon, I Kobyzev
Annals of K-Theory 4 (2), 151-183, 2019
Attribute controlled dialogue prompting
R Liu, A Rashid, I Kobyzev, M Rezagholizadeh, P Poupart
arXiv preprint arXiv:2307.05228, 2023
Resonance RoPE: Improving Context Length Generalization of Large Language Models
S Wang, I Kobyzev, P Lu, M Rezagholizadeh, B Liu
arXiv preprint arXiv:2403.00071, 2024
Hyperparameter optimization for Large Language Model instruction-tuning
C Tribes, S Benarroch-Lelong, P Lu, I Kobyzev
arXiv preprint arXiv:2312.00949, 2023
Learning functions on multiple sets using multi-set transformers
KA Selby, A Rashid, I Kobyzev, M Rezagholizadeh, P Poupart
Uncertainty in Artificial Intelligence, 1760-1770, 2022
The system can't perform the operation now. Try again later.
Articles 1–20