Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDMostafa Dehghani 0001
Person information
- affiliation: Google
- affiliation: University of Amsterdam, The Netherlands
- affiliation: University of Tehran, Iran
Other persons with the same name
- Mostafa Dehghani 0002
![[0000-0001-5019-725X]](https://dblp.org/img/orcid-mark.12x12.png "0000-0001-5019-725X")
— University of Kashan, Iran
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
[j12]David Rau, Mostafa Dehghani, Jaap Kamps:
Revisiting Bag of Words Document Representations for Efficient Ranking with Transformers. ACM Trans. Inf. Syst. 42(5): 114:1-114:27 (2024)- [c62]Ali Vardasbi, Maarten de Rijke, Fernando Diaz, Mostafa Dehghani:
The Impact of Group Membership Bias on the Quality and Fairness of Exposure in Ranking. SIGIR 2024: 1514-1524 - [i62]Ibrahim Alabdulmohsin, Vinh Q. Tran, Mostafa Dehghani:
Fractal Patterns May Unravel the Intelligence in Next-Token Prediction. CoRR abs/2402.01825 (2024) - [i61]Andreas Bär, Neil Houlsby, Mostafa Dehghani, Manoj Kumar:
Frozen Feature Augmentation for Few-Shot Image Classification. CoRR abs/2403.10519 (2024) - 2023
- [j11]Yi Tay, Mostafa Dehghani, Dara Bahri, Donald Metzler:
Efficient Transformers: A Survey. ACM Comput. Surv. 55(6): 109:1-109:28 (2023) - [j10]Manoj Kumar, Mostafa Dehghani, Neil Houlsby:
Dual PatchNorm. Trans. Mach. Learn. Res. 2023 (2023) - [j9]Valerii Likhosherstov, Anurag Arnab, Krzysztof Marcin Choromanski, Mario Lucic, Yi Tay, Mostafa Dehghani:
PolyViT: Co-training Vision Transformers on Images, Videos and Audio. Trans. Mach. Learn. Res. 2023 (2023) - [c61]Yi Tay, Jason Wei, Hyung Won Chung, Vinh Q. Tran, David R. So, Siamak Shakeri, Xavier Garcia, Huaixiu Steven Zheng, Jinfeng Rao, Aakanksha Chowdhery, Denny Zhou, Donald Metzler, Slav Petrov, Neil Houlsby, Quoc V. Le, Mostafa Dehghani:
Transcending Scaling Laws with 0.1% Extra Compute. EMNLP 2023: 1471-1486 - [c60]Sanket Vaibhav Mehta, Jai Gupta, Yi Tay, Mostafa Dehghani, Vinh Q. Tran, Jinfeng Rao, Marc Najork, Emma Strubell, Donald Metzler:
DSI++: Updating Transformer Memory with New Documents. EMNLP 2023: 8198-8213 - [c59]Yi Tay, Mostafa Dehghani, Samira Abnar, Hyung Won Chung, William Fedus, Jinfeng Rao, Sharan Narang, Vinh Q. Tran, Dani Yogatama, Donald Metzler:
Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling? EMNLP (Findings) 2023: 12342-12364 - [c58]Lisa Alazraki, Lluís Castrejón, Mostafa Dehghani, Fantine Huot, Jasper R. R. Uijlings, Thomas Mensink:
How (not) to ensemble LVLMs for VQA. ICBINB 2023: 1-20 - [c57]Aran Komatsuzaki, Joan Puigcerver, James Lee-Thorp, Carlos Riquelme Ruiz, Basil Mustafa, Joshua Ainslie, Yi Tay, Mostafa Dehghani, Neil Houlsby:
Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints. ICLR 2023 - [c56]Sajad Movahedi, Melika Adabinejad, Ayyoob Imani, Arezou Keshavarz, Mostafa Dehghani, Azadeh Shakery, Babak Nadjar Araabi:
$\Lambda$-DARTS: Mitigating Performance Collapse by Harmonizing Operation Selection among Cells. ICLR 2023 - [c55]Mani Shemiranifar, Mostafa Dehghani:
L2 Norm Guided Adaptive Computation. Tiny Papers @ ICLR 2023 - [c54]Yi Tay, Mostafa Dehghani, Vinh Q. Tran, Xavier Garcia, Jason Wei, Xuezhi Wang, Hyung Won Chung, Dara Bahri, Tal Schuster, Huaixiu Steven Zheng, Denny Zhou, Neil Houlsby, Donald Metzler:
UL2: Unifying Language Learning Paradigms. ICLR 2023 - [c53]Mostafa Dehghani, Josip Djolonga, Basil Mustafa, Piotr Padlewski, Jonathan Heek, Justin Gilmer, Andreas Peter Steiner, Mathilde Caron, Robert Geirhos, Ibrahim Alabdulmohsin, Rodolphe Jenatton, Lucas Beyer, Michael Tschannen, Anurag Arnab, Xiao Wang, Carlos Riquelme Ruiz, Matthias Minderer, Joan Puigcerver, Utku Evci, Manoj Kumar, Sjoerd van Steenkiste, Gamaleldin Fathy Elsayed, Aravindh Mahendran, Fisher Yu, Avital Oliver, Fantine Huot, Jasmijn Bastings, Mark Collier, Alexey A. Gritsenko, Vighnesh Birodkar, Cristina Nader Vasconcelos, Yi Tay, Thomas Mensink, Alexander Kolesnikov, Filip Pavetic, Dustin Tran, Thomas Kipf, Mario Lucic, Xiaohua Zhai, Daniel Keysers, Jeremiah J. Harmsen, Neil Houlsby:
Scaling Vision Transformers to 22 Billion Parameters. ICML 2023: 7480-7512 - [c52]Fuzhao Xue, Valerii Likhosherstov, Anurag Arnab, Neil Houlsby, Mostafa Dehghani, Yang You:
Adaptive Computation with Elastic Input Sequence. ICML 2023: 38971-38988 - [c51]Mostafa Dehghani, Basil Mustafa, Josip Djolonga, Jonathan Heek, Matthias Minderer, Mathilde Caron, Andreas Steiner, Joan Puigcerver, Robert Geirhos, Ibrahim M. Alabdulmohsin, Avital Oliver, Piotr Padlewski, Alexey A. Gritsenko, Mario Lucic, Neil Houlsby:
Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution. NeurIPS 2023 - [i60]Fuzhao Xue, Valerii Likhosherstov, Anurag Arnab, Neil Houlsby, Mostafa Dehghani, Yang You:
Adaptive Computation with Elastic Input Sequence. CoRR abs/2301.13195 (2023) - [i59]Manoj Kumar, Mostafa Dehghani, Neil Houlsby:
Dual PatchNorm. CoRR abs/2302.01327 (2023) - [i58]Mostafa Dehghani, Josip Djolonga, Basil Mustafa, Piotr Padlewski, Jonathan Heek, Justin Gilmer, Andreas Steiner, Mathilde Caron, Robert Geirhos, Ibrahim Alabdulmohsin, Rodolphe Jenatton, Lucas Beyer, Michael Tschannen, Anurag Arnab, Xiao Wang, Carlos Riquelme, Matthias Minderer, Joan Puigcerver, Utku Evci, Manoj Kumar, Sjoerd van Steenkiste, Gamaleldin F. Elsayed, Aravindh Mahendran, Fisher Yu, Avital Oliver, Fantine Huot, Jasmijn Bastings, Mark Patrick Collier, Alexey A. Gritsenko, Vighnesh Birodkar, Cristina Nader Vasconcelos, Yi Tay, Thomas Mensink, Alexander Kolesnikov, Filip Pavetic, Dustin Tran, Thomas Kipf, Mario Lucic, Xiaohua Zhai, Daniel Keysers, Jeremiah Harmsen, Neil Houlsby:
Scaling Vision Transformers to 22 Billion Parameters. CoRR abs/2302.05442 (2023) - [i57]Alexey A. Gritsenko, Xuehan Xiong, Josip Djolonga, Mostafa Dehghani, Chen Sun, Mario Lucic, Cordelia Schmid, Anurag Arnab:
End-to-End Spatio-Temporal Action Localisation with Video Transformers. CoRR abs/2304.12160 (2023) - [i56]Rohan Anil, Andrew M. Dai, Orhan Firat, Melvin Johnson, Dmitry Lepikhin, Alexandre Passos, Siamak Shakeri, Emanuel Taropa, Paige Bailey, Zhifeng Chen, Eric Chu, Jonathan H. Clark, Laurent El Shafey, Yanping Huang, Kathy Meier-Hellstern, Gaurav Mishra, Erica Moreira, Mark Omernick, Kevin Robinson, Sebastian Ruder, Yi Tay, Kefan Xiao, Yuanzhong Xu, Yujing Zhang, Gustavo Hernández Ábrego, Junwhan Ahn, Jacob Austin, Paul Barham, Jan A. Botha, James Bradbury, Siddhartha Brahma, Kevin Brooks, Michele Catasta, Yong Cheng, Colin Cherry, Christopher A. Choquette-Choo, Aakanksha Chowdhery, Clément Crepy, Shachi Dave, Mostafa Dehghani, Sunipa Dev, Jacob Devlin, Mark Díaz, Nan Du, Ethan Dyer, Vladimir Feinberg, Fangxiaoyu Feng, Vlad Fienber, Markus Freitag, Xavier Garcia, Sebastian Gehrmann, Lucas Gonzalez, et al.:
PaLM 2 Technical Report. CoRR abs/2305.10403 (2023) - [i55]Xi Chen, Josip Djolonga, Piotr Padlewski, Basil Mustafa, Soravit Changpinyo, Jialin Wu, Carlos Riquelme Ruiz, Sebastian Goodman, Xiao Wang, Yi Tay, Siamak Shakeri, Mostafa Dehghani, Daniel Salz, Mario Lucic, Michael Tschannen, Arsha Nagrani, Hexiang Hu, Mandar Joshi, Bo Pang, Ceslee Montgomery, Paulina Pietrzyk, Marvin Ritter, A. J. Piergiovanni, Matthias Minderer, Filip Pavetic, Austin Waters, Gang Li, Ibrahim Alabdulmohsin, Lucas Beyer, Julien Amelot, Kenton Lee, Andreas Peter Steiner, Yang Li, Daniel Keysers, Anurag Arnab, Yuanzhong Xu, Keran Rong, Alexander Kolesnikov, Mojtaba Seyedhosseini, Anelia Angelova, Xiaohua Zhai, Neil Houlsby, Radu Soricut:
PaLI-X: On Scaling up a Multilingual Vision and Language Model. CoRR abs/2305.18565 (2023) - [i54]Mostafa Dehghani, Basil Mustafa, Josip Djolonga, Jonathan Heek, Matthias Minderer, Mathilde Caron, Andreas Steiner, Joan Puigcerver, Robert Geirhos, Ibrahim Alabdulmohsin, Avital Oliver, Piotr Padlewski, Alexey A. Gritsenko, Mario Lucic, Neil Houlsby:
Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution. CoRR abs/2307.06304 (2023) - [i53]Ali Vardasbi, Maarten de Rijke, Fernando Diaz, Mostafa Dehghani:
Group Membership Bias. CoRR abs/2308.02887 (2023) - [i52]Lisa Alazraki, Lluís Castrejón, Mostafa Dehghani, Fantine Huot, Jasper R. R. Uijlings, Thomas Mensink:
How (not) to ensemble LVLMs for VQA. CoRR abs/2310.06641 (2023) - [i51]Chenxi Whitehouse, Fantine Huot, Jasmijn Bastings, Mostafa Dehghani, Chu-Cheng Lin, Mirella Lapata:
Parameter-Efficient Multilingual Summarisation: An Empirical Study. CoRR abs/2311.08572 (2023) - 2022
- [c50]Ali Vardasbi, Maarten de Rijke, Mostafa Dehghani:
Intersection of Parallels as an Early Stopping Criterion. CIKM 2022: 1965-1974 - [c49]Mostafa Dehghani, Alexey A. Gritsenko, Anurag Arnab, Matthias Minderer, Yi Tay:
SCENIC: A JAX Library for Computer Vision Research and Beyond. CVPR 2022: 21361-21366 - [c48]Matthias Minderer, Alexey A. Gritsenko, Austin Stone, Maxim Neumann, Dirk Weissenborn, Alexey Dosovitskiy, Aravindh Mahendran, Anurag Arnab, Mostafa Dehghani, Zhuoran Shen, Xiao Wang, Xiaohua Zhai, Thomas Kipf, Neil Houlsby:
Simple Open-Vocabulary Object Detection. ECCV (10) 2022: 728-755 - [c47]Mostafa Dehghani, Yi Tay, Anurag Arnab, Lucas Beyer, Ashish Vaswani:
The Efficiency Misnomer. ICLR 2022 - [c46]Samira Abnar, Mostafa Dehghani, Behnam Neyshabur, Hanie Sedghi:
Exploring the Limits of Large Scale Pre-training. ICLR 2022 - [c45]Chengzhi Mao, Lu Jiang, Mostafa Dehghani, Carl Vondrick, Rahul Sukthankar, Irfan Essa:
Discrete Representations Strengthen Vision Transformer Robustness. ICLR 2022 - [c44]Yi Tay, Mostafa Dehghani, Jinfeng Rao, William Fedus, Samira Abnar, Hyung Won Chung, Sharan Narang, Dani Yogatama, Ashish Vaswani, Donald Metzler:
Scale Efficiently: Insights from Pretraining and Finetuning Transformers. ICLR 2022 - [c43]Tal Schuster, Adam Fisch, Jai Gupta, Mostafa Dehghani, Dara Bahri, Vinh Tran, Yi Tay, Donald Metzler:
Confident Adaptive Language Modeling. NeurIPS 2022 - [c42]Yi Tay, Vinh Tran, Mostafa Dehghani, Jianmo Ni, Dara Bahri, Harsh Mehta, Zhen Qin, Kai Hui, Zhe Zhao, Jai Prakash Gupta, Tal Schuster, William W. Cohen, Donald Metzler:
Transformer Memory as a Differentiable Search Index. NeurIPS 2022 - [c41]Hamed Zamani, Fernando Diaz, Mostafa Dehghani, Donald Metzler, Michael Bendersky:
Retrieval-Enhanced Machine Learning. SIGIR 2022: 2875-2886 - [i50]Yi Tay, Vinh Q. Tran, Mostafa Dehghani, Jianmo Ni, Dara Bahri, Harsh Mehta, Zhen Qin, Kai Hui, Zhe Zhao, Jai Prakash Gupta, Tal Schuster, William W. Cohen, Donald Metzler:
Transformer Memory as a Differentiable Search Index. CoRR abs/2202.06991 (2022) - [i49]Hamed Zamani, Fernando Diaz, Mostafa Dehghani, Donald Metzler, Michael Bendersky:
Retrieval-Enhanced Machine Learning. CoRR abs/2205.01230 (2022) - [i48]Yi Tay, Mostafa Dehghani, Vinh Q. Tran, Xavier Garcia, Dara Bahri, Tal Schuster, Huaixiu Steven Zheng, Neil Houlsby, Donald Metzler:
Unifying Language Learning Paradigms. CoRR abs/2205.05131 (2022) - [i47]Matthias Minderer, Alexey A. Gritsenko, Austin Stone, Maxim Neumann, Dirk Weissenborn, Alexey Dosovitskiy, Aravindh Mahendran, Anurag Arnab, Mostafa Dehghani, Zhuoran Shen, Xiao Wang, Xiaohua Zhai, Thomas Kipf, Neil Houlsby:
Simple Open-Vocabulary Object Detection with Vision Transformers. CoRR abs/2205.06230 (2022) - [i46]Anurag Arnab, Xuehan Xiong, Alexey A. Gritsenko, Rob Romijnders, Josip Djolonga, Mostafa Dehghani, Chen Sun, Mario Lucic, Cordelia Schmid:
Beyond Transfer Learning: Co-finetuning for Action Localisation. CoRR abs/2207.03807 (2022) - [i45]Tal Schuster, Adam Fisch, Jai Prakash Gupta, Mostafa Dehghani, Dara Bahri, Vinh Q. Tran, Yi Tay, Donald Metzler:
Confident Adaptive Language Modeling. CoRR abs/2207.07061 (2022) - [i44]Yi Tay, Mostafa Dehghani, Samira Abnar, Hyung Won Chung, William Fedus, Jinfeng Rao, Sharan Narang, Vinh Q. Tran, Dani Yogatama, Donald Metzler:
Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling? CoRR abs/2207.10551 (2022) - [i43]Ali Vardasbi, Maarten de Rijke, Mostafa Dehghani:
Intersection of Parallels as an Early Stopping Criterion. CoRR abs/2208.09529 (2022) - [i42]Sajad Movahedi, Melika Adabinejad, Ayyoob Imani, Arezou Keshavarz, Mostafa Dehghani, Azadeh Shakery, Babak Nadjar Araabi:
Λ-DARTS: Mitigating Performance Collapse by Harmonizing Operation Selection among Cells. CoRR abs/2210.07998 (2022) - [i41]Yi Tay, Jason Wei, Hyung Won Chung, Vinh Q. Tran, David R. So, Siamak Shakeri, Xavier Garcia, Huaixiu Steven Zheng, Jinfeng Rao, Aakanksha Chowdhery, Denny Zhou, Donald Metzler, Slav Petrov, Neil Houlsby, Quoc V. Le, Mostafa Dehghani:
Transcending Scaling Laws with 0.1% Extra Compute. CoRR abs/2210.11399 (2022) - [i40]Hyung Won Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, William Fedus, Eric Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, Albert Webson, Shixiang Shane Gu, Zhuyun Dai, Mirac Suzgun, Xinyun Chen, Aakanksha Chowdhery, Sharan Narang, Gaurav Mishra, Adams Yu, Vincent Y. Zhao, Yanping Huang, Andrew M. Dai, Hongkun Yu, Slav Petrov, Ed H. Chi, Jeff Dean, Jacob Devlin, Adam Roberts, Denny Zhou, Quoc V. Le, Jason Wei:
Scaling Instruction-Finetuned Language Models. CoRR abs/2210.11416 (2022) - [i39]Zahra Shamsi, Drew Bryant, Jacob Wilson, Xiaoyu Qu, Avinava Dubey, Konik Kothari, Mostafa Dehghani, Mariya Chavarha, Valerii Likhosherstov, Brian Williams, Michael Frumkin, Fred Appelbaum, Krzysztof Choromanski, Ali Bashir, Min Fang:
Automated Deep Aberration Detection from Chromosome Karyotype Images. CoRR abs/2211.14312 (2022) - [i38]Aran Komatsuzaki, Joan Puigcerver, James Lee-Thorp, Carlos Riquelme Ruiz, Basil Mustafa, Joshua Ainslie, Yi Tay, Mostafa Dehghani, Neil Houlsby:
Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints. CoRR abs/2212.05055 (2022) - [i37]Sanket Vaibhav Mehta, Jai Prakash Gupta, Yi Tay, Mostafa Dehghani, Vinh Q. Tran, Jinfeng Rao, Marc Najork, Emma Strubell, Donald Metzler:
DSI++: Updating Transformer Memory with New Documents. CoRR abs/2212.09744 (2022) - 2021
- [j8]Hosein Azarbonyad, Mostafa Dehghani, Maarten Marx, Jaap Kamps:
Learning to rank for multi-label text classification: Combining different sources of information. Nat. Lang. Eng. 27(1): 89-111 (2021) - [c40]Rabeeh Karimi Mahabadi, Sebastian Ruder, Mostafa Dehghani, James Henderson:
Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks. ACL/IJCNLP (1) 2021: 565-576 - [c39]Yi Tay, Mostafa Dehghani, Jai Prakash Gupta, Vamsi Aribandi, Dara Bahri, Zhen Qin, Donald Metzler:
Are Pretrained Convolutions Better than Pretrained Transformers? ACL/IJCNLP (1) 2021: 4349-4359 - [c38]Anurag Arnab, Mostafa Dehghani, Georg Heigold, Chen Sun, Mario Lucic, Cordelia Schmid:
ViViT: A Video Vision Transformer. ICCV 2021: 6816-6826 - [c37]Rianne van den Berg, Alexey A. Gritsenko, Mostafa Dehghani, Casper Kaae Sønderby, Tim Salimans:
IDF++: Analyzing and Improving Integer Discrete Flows for Lossless Compression. ICLR 2021 - [c36]Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby:
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR 2021 - [c35]Yi Tay, Mostafa Dehghani, Samira Abnar, Yikang Shen, Dara Bahri, Philip Pham, Jinfeng Rao, Liu Yang, Sebastian Ruder, Donald Metzler:
Long Range Arena : A Benchmark for Efficient Transformers. ICLR 2021 - [c34]Yi Tay, Mostafa Dehghani, Vamsi Aribandi, Jai Prakash Gupta, Philip Pham, Zhen Qin, Dara Bahri, Da-Cheng Juan, Donald Metzler:
OmniNet: Omnidirectional Representations from Transformers. ICML 2021: 10193-10202 - [c33]Michael S. Ryoo, A. J. Piergiovanni, Anurag Arnab, Mostafa Dehghani, Anelia Angelova:
TokenLearner: Adaptive Space-Time Tokenization for Videos. NeurIPS 2021: 12786-12797 - [i36]Yi Tay, Mostafa Dehghani, Vamsi Aribandi, Jai Prakash Gupta, Philip Pham, Zhen Qin, Dara Bahri, Da-Cheng Juan, Donald Metzler:
OmniNet: Omnidirectional Representations from Transformers. CoRR abs/2103.01075 (2021) - [i35]Anurag Arnab, Mostafa Dehghani, Georg Heigold, Chen Sun, Mario Lucic, Cordelia Schmid:
ViViT: A Video Vision Transformer. CoRR abs/2103.15691 (2021) - [i34]Yi Tay, Mostafa Dehghani, Jai Prakash Gupta, Dara Bahri, Vamsi Aribandi, Zhen Qin, Donald Metzler:
Are Pre-trained Convolutions Better than Pre-trained Transformers? CoRR abs/2105.03322 (2021) - [i33]Rabeeh Karimi Mahabadi, Sebastian Ruder, Mostafa Dehghani, James Henderson:
Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks. CoRR abs/2106.04489 (2021) - [i32]Samira Abnar, Rianne van den Berg, Golnaz Ghiasi, Mostafa Dehghani, Nal Kalchbrenner, Hanie Sedghi:
Gradual Domain Adaptation in the Wild: When Intermediate Distributions are Absent. CoRR abs/2106.06080 (2021) - [i31]Michael S. Ryoo, A. J. Piergiovanni, Anurag Arnab, Mostafa Dehghani, Anelia Angelova:
TokenLearner: What Can 8 Learned Tokens Do for Images and Videos? CoRR abs/2106.11297 (2021) - [i30]Mostafa Dehghani, Yi Tay, Alexey A. Gritsenko, Zhe Zhao, Neil Houlsby, Fernando Diaz, Donald Metzler, Oriol Vinyals:
The Benchmark Lottery. CoRR abs/2107.07002 (2021) - [i29]Yi Tay, Mostafa Dehghani, Jinfeng Rao, William Fedus, Samira Abnar, Hyung Won Chung, Sharan Narang, Dani Yogatama, Ashish Vaswani, Donald Metzler:
Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers. CoRR abs/2109.10686 (2021) - [i28]Samira Abnar, Mostafa Dehghani, Behnam Neyshabur, Hanie Sedghi:
Exploring the Limits of Large Scale Pre-training. CoRR abs/2110.02095 (2021) - [i27]Mostafa Dehghani, Alexey A. Gritsenko, Anurag Arnab, Matthias Minderer, Yi Tay:
SCENIC: A JAX Library for Computer Vision Research and Beyond. CoRR abs/2110.11403 (2021) - [i26]Mostafa Dehghani, Anurag Arnab, Lucas Beyer, Ashish Vaswani, Yi Tay:
The Efficiency Misnomer. CoRR abs/2110.12894 (2021) - [i25]Chengzhi Mao, Lu Jiang, Mostafa Dehghani, Carl Vondrick, Rahul Sukthankar, Irfan Essa:
Discrete Representations Strengthen Vision Transformer Robustness. CoRR abs/2111.10493 (2021) - [i24]Valerii Likhosherstov, Anurag Arnab, Krzysztof Choromanski, Mario Lucic, Yi Tay, Adrian Weller, Mostafa Dehghani:
PolyViT: Co-training Vision Transformers on Images, Videos and Audio. CoRR abs/2111.12993 (2021) - [i23]Yang Li, Gang Li, Xin Zhou, Mostafa Dehghani, Alexey A. Gritsenko:
VUT: Versatile UI Transformer for Multi-Modal Multi-Task User Interface Modeling. CoRR abs/2112.05692 (2021) - 2020
- [i22]Casper Kaae Sønderby, Lasse Espeholt, Jonathan Heek, Mostafa Dehghani, Avital Oliver, Tim Salimans, Shreya Agrawal, Jason Hickey, Nal Kalchbrenner:
MetNet: A Neural Weather Model for Precipitation Forecasting. CoRR abs/2003.12140 (2020) - [i21]Samira Abnar, Mostafa Dehghani, Willem H. Zuidema:
Transferring Inductive Biases through Knowledge Distillation. CoRR abs/2006.00555 (2020) - [i20]Rianne van den Berg, Alexey A. Gritsenko, Mostafa Dehghani, Casper Kaae Sønderby, Tim Salimans:
IDF++: Analyzing and Improving Integer Discrete Flows for Lossless Compression. CoRR abs/2006.12459 (2020) - [i19]Yi Tay, Mostafa Dehghani, Dara Bahri, Donald Metzler:
Efficient Transformers: A Survey. CoRR abs/2009.06732 (2020) - [i18]Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby:
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. CoRR abs/2010.11929 (2020) - [i17]Yi Tay, Mostafa Dehghani, Samira Abnar, Yikang Shen, Dara Bahri, Philip Pham, Jinfeng Rao, Liu Yang, Sebastian Ruder, Donald Metzler:
Long Range Arena: A Benchmark for Efficient Transformers. CoRR abs/2011.04006 (2020)
2010 – 2019
- 2019
- [j7]Hosein Azarbonyad, Mostafa Dehghani, Tom Kenter, Maarten Marx, Jaap Kamps, Maarten de Rijke:
HiTR: Hierarchical Topic Model Re-Estimation for Measuring Topical Diversity of Documents. IEEE Trans. Knowl. Data Eng. 31(11): 2124-2137 (2019) - [c32]Mostafa Dehghani, Hosein Azarbonyad, Jaap Kamps, Maarten de Rijke:
Learning to Transform, Combine, and Reason in Open-Domain Question Answering. BNAIC/BENELEARN 2019 - [c31]Mostafa Dehghani, Stephan Gouws, Oriol Vinyals, Jakob Uszkoreit, Lukasz Kaiser:
Universal Transformers. ICLR (Poster) 2019 - [c30]Mostafa Dehghani, Hosein Azarbonyad, Jaap Kamps, Maarten de Rijke:
Learning to Transform, Combine, and Reason in Open-Domain Question Answering. WSDM 2019: 681-689 - 2018
- [j6]Nafiseh Torkzadeh Mahani, Mostafa Dehghani, Maryam S. Mirian, Azadeh Shakery, Khalil Taheri:
Expert finding by the Dempster-Shafer theory for evidence combination. Expert Syst. J. Knowl. Eng. 35(1) (2018) - [c29]Hamed Zamani, Mostafa Dehghani, W. Bruce Croft, Erik G. Learned-Miller, Jaap Kamps:
From Neural Re-Ranking to Neural Ranking: Learning a Sparse Representation for Inverted Indexing. CIKM 2018: 497-506 - [c28]Mostafa Dehghani, Arash Mehrjou, Stephan Gouws, Jaap Kamps, Bernhard Schölkopf:
Fidelity-Weighted Learning. ICLR (Poster) 2018 - [c27]Hamed Zamani, Mostafa Dehghani, Fernando Diaz, Hang Li, Nick Craswell:
SIGIR 2018 Workshop on Learning from Limited or Noisy Data for Information Retrieval. SIGIR 2018: 1439-1440 - [c26]Tom Kenter, Alexey Borisov, Christophe Van Gysel, Mostafa Dehghani, Maarten de Rijke, Bhaskar Mitra:
Neural Networks for Information Retrieval. WSDM 2018: 779-780 - [i16]Tom Kenter, Alexey Borisov, Christophe Van Gysel, Mostafa Dehghani, Maarten de Rijke, Bhaskar Mitra:
Neural Networks for Information Retrieval. CoRR abs/1801.02178 (2018) - [i15]Mostafa Dehghani, Jaap Kamps:
Learning to Rank from Samples of Variable Quality. CoRR abs/1806.08694 (2018) - [i14]Mostafa Dehghani, Stephan Gouws, Oriol Vinyals, Jakob Uszkoreit, Lukasz Kaiser:
Universal Transformers. CoRR abs/1807.03819 (2018) - [i13]Hosein Azarbonyad, Mostafa Dehghani, Tom Kenter, Maarten Marx, Jaap Kamps, Maarten de Rijke:
HiTR: Hierarchical Topic Model Re-estimation for Measuring Topical Diversity of Documents. CoRR abs/1810.05436 (2018) - 2017
- [j5]Mostafa Dehghani:
Toward Document Understanding for Information Retrieval. SIGIR Forum 51(3): 27-31 (2017) - [c25]Mostafa Dehghani, Glorianna Jagfeld, Hosein Azarbonyad, Alex Olieman, Jaap Kamps, Maarten Marx:
Telling How to Narrow it Down: Browsing Path Recommendation for Exploratory Search. CHIIR 2017: 369-372 - [c24]Hosein Azarbonyad, Mostafa Dehghani, Kaspar Beelen, Alexandra Arkut, Maarten Marx, Jaap Kamps:
Words are Malleable: Computing Semantic Shifts in Political and Media Discourse. CIKM 2017: 1509-1518 - [c23]Mostafa Dehghani, Sascha Rothe, Enrique Alfonseca, Pascal Fleury:
Learning to Attend, Copy, and Generate for Session-Based Query Suggestion. CIKM 2017: 1747-1756 - [c22]Hosein Azarbonyad, Mostafa Dehghani, Tom Kenter, Maarten Marx, Jaap Kamps, Maarten de Rijke:
Hierarchical Re-estimation of Topic Models for Measuring Topical Diversity. ECIR 2017: 68-81 - [c21]Mostafa Dehghani, Glorianna Jagfeld, Hosein Azarbonyad, Alex Olieman, Jaap Kamps, Maarten Marx:
On Search Powered Navigation. ICTIR 2017: 317-320 - [c20]Mostafa Dehghani, Hamed Zamani, Aliaksei Severyn, Jaap Kamps, W. Bruce Croft:
Neural Ranking Models with Weak Supervision. SIGIR 2017: 65-74 - [c19]Tom Kenter, Alexey Borisov, Christophe Van Gysel, Mostafa Dehghani, Maarten de Rijke, Bhaskar Mitra:
Neural Networks for Information Retrieval. SIGIR 2017: 1403-1406 - [i12]Hosein Azarbonyad, Mostafa Dehghani, Tom Kenter, Maarten Marx, Jaap Kamps, Maarten de Rijke:
Hierarchical Re-estimation of Topic Models for Measuring Topical Diversity. CoRR abs/1701.04273 (2017) - [i11]Mostafa Dehghani, Hamed Zamani, Aliaksei Severyn, Jaap Kamps, W. Bruce Croft:
Neural Ranking Models with Weak Supervision. CoRR abs/1704.08803 (2017) - [i10]Tom Kenter, Alexey Borisov, Christophe Van Gysel, Mostafa Dehghani, Maarten de Rijke, Bhaskar Mitra:
Neural Networks for Information Retrieval. CoRR abs/1707.04242 (2017) - [i9]Mostafa Dehghani, Hosein Azarbonyad, Jaap Kamps, Maarten de Rijke:
Share your Model instead of your Data: Privacy Preserving Mimic Learning for Ranking. CoRR abs/1707.07605 (2017) - [i8]Mostafa Dehghani, Sascha Rothe, Enrique Alfonseca, Pascal Fleury:
Learning to Attend, Copy, and Generate for Session-Based Query Suggestion. CoRR abs/1708.03418 (2017) - [i7]Mostafa Dehghani, Glorianna Jagfeld, Hosein Azarbonyad, Alex Olieman, Jaap Kamps, Maarten Marx:
On Search Powered Navigation. CoRR abs/1711.00310 (2017) - [i6]Mostafa Dehghani, Aliaksei Severyn, Sascha Rothe, Jaap Kamps:
Avoiding Your Teacher's Mistakes: Training Neural Networks with Controlled Weak Supervision. CoRR abs/1711.00313 (2017) - [i5]Mostafa Dehghani, Arash Mehrjou, Stephan Gouws, Jaap Kamps, Bernhard Schölkopf:
Fidelity-Weighted Learning. CoRR abs/1711.02799 (2017) - [i4]Hosein Azarbonyad, Mostafa Dehghani, Kaspar Beelen, Alexandra Arkut, Maarten Marx, Jaap Kamps:
Words are Malleable: Computing Semantic Shifts in Political and Media Discourse. CoRR abs/1711.05603 (2017) - [i3]Mostafa Dehghani, Aliaksei Severyn, Sascha Rothe, Jaap Kamps:
Learning to Learn from Weak Supervision by Full Supervision. CoRR abs/1711.11383 (2017) - 2016
- [j4]Mostafa Dehghani, Azadeh Shakery, Maryam S. Mirian:
Alecsa: Attentive Learning for Email Categorization using Structural Aspects. Knowl. Based Syst. 98: 44-54 (2016) - [j3]Razieh Rahimi, Azadeh Shakery, Javid Dadashkarimi, Mozhdeh Ariannezhad, Mostafa Dehghani, Hossein Nasr Esfahani:
Building a multi-domain comparable corpus using a learning to rank method. Nat. Lang. Eng. 22(4): 627-653 (2016) - [c18]