Follow
Amit Alfassy
Amit Alfassy
Research Scientist at IBM Research, CS PhD from Technion
Verified email at campus.technion.ac.il
Title
Cited by
Cited by
Year
Bloom: A 176b-parameter open-access multilingual language model
T Le Scao, A Fan, C Akiki, E Pavlick, S Ilić, D Hesslow, R Castagné, ...
16262023
Laso: Label-set operations networks for multi-label few-shot learning
A Alfassy, L Karlinsky, A Aides, J Shtok, S Harary, R Feris, R Giryes, ...
Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2019
1472019
Dense and aligned captions (dac) promote compositional reasoning in vl models
S Doveh, A Arbelle, S Harary, R Herzig, D Kim, P Cascante-Bonilla, ...
Advances in Neural Information Processing Systems 36, 76137-76150, 2023
402023
Unsupervised domain generalization by learning a bridge across domains
S Harary, E Schwartz, A Arbelle, P Staar, S Abu-Hussein, E Amrani, ...
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022
392022
Starnet: towards weakly supervised few-shot object detection
L Karlinsky, J Shtok, A Alfassy, M Lichtenstein, S Harary, E Schwartz, ...
Proceedings of the AAAI Conference on Artificial Intelligence 35 (2), 1743-1753, 2021
28*2021
Detector-Free Weakly Supervised Grounding by Separation
A Arbelle, S Doveh, A Alfassy, J Shtok, G Lev, E Schwartz, H Kuehne, ...
Proceedings of the International Conference on Computer Vision 2021, ICCV 2021., 2021
262021
BLOOM: A 176b-parameter open-access multilingual language model. CoRR, abs/2211.05100, 2022. doi: 10.48550
T Le Scao, A Fan, C Akiki, E Pavlick, S Ilic, D Hesslow, R Castagné, ...
arXiv preprint arXiv.2211.05100 10, 0
22
FETA: Towards Specializing Foundational Models for Expert Task Applications
A Alfassy, A Arbelle, O Halimi, S Harary, R Herzig, E Schwartz, R Panda, ...
Advances in Neural Information Processing Systems 35, 29873-29888, 2022
152022
Towards multimodal in-context learning for vision & language models
S Doveh, S Perek, MJ Mirza, W Lin, A Alfassy, A Arbelle, S Ullman, ...
arXiv preprint arXiv:2403.12736, 2024
112024
Method and system for producing digital image features
A Aides, A Alfassy, L Karlinsky, J Shtok
US Patent 11,176,417, 2021
62021
Training multi-modal models on documents using multiple instance learning
A Alfassy, A Arbelle, L Karlinsky
US Patent App. 18/306,071, 2024
2024
Augmenting In-Context-Learning in LLMs via Automatic Data Labeling and Refinement
J Shtok, A Alfassy, FA Dahood, E Schwartz, S Doveh, A Arbelle
arXiv preprint arXiv:2410.10348, 2024
2024
Training visual language grounding models using separation loss
A Arbelle, L Karlinsky, S Doveh, J Shtok, A Alfassy
US Patent App. 17/412,528, 2023
2023
The system can't perform the operation now. Try again later.
Articles 1–13