Mostafa Dehghani

142 papers A* 32A 10B 3Misc 3Journal 75Unranked 19

Year	Rank	Type	Title / Venue / Authors
2024	A*	`conf`	End-to-End Spatio-Temporal Action Localisation with Video Transformers. CVPR Alexey A. Gritsenko, Xuehan Xiong, Josip Djolonga, Mostafa Dehghani, Chen Sun, Mario Lucic, Cordelia Schmid, Anurag Arnab
2024	A*	`conf`	Fractal Patterns May Illuminate the Success of Next-Token Prediction. NeurIPS Ibrahim M. Alabdulmohsin, Vinh Q. Tran, Mostafa Dehghani
2024	J	`jnl`	Fractal Patterns May Unravel the Intelligence in Next-Token Prediction. CoRR Ibrahim Alabdulmohsin, Vinh Q. Tran, Mostafa Dehghani
2024	A*	`conf`	Frozen Feature Augmentation for Few-Shot Image Classification. CVPR Andreas Bär, Neil Houlsby, Mostafa Dehghani, Manoj Kumar
2024	J	`jnl`	Frozen Feature Augmentation for Few-Shot Image Classification. CoRR Andreas Bär, Neil Houlsby, Mostafa Dehghani, Manoj Kumar
2024	—	`conf`	Low-Rank Adaptation for Multilingual Summarization: An Empirical Study. NAACL-HLT (Findings) Chenxi Whitehouse, Fantine Huot, Jasmijn Bastings, Mostafa Dehghani, Chu-Cheng Lin, Mirella Lapata
2024	A*	`conf`	On Scaling Up a Multilingual Vision and Language Model. CVPR 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
2024	J	`jnl`	Revisiting Bag of Words Document Representations for Efficient Ranking with Transformers. ACM Trans. Inf. Syst. David Rau, Mostafa Dehghani, Jaap Kamps
2024	J	`jnl`	Scaling Instruction-Finetuned Language Models. J. Mach. Learn. Res. Hyung Won Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, William Fedus, Yunxuan Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, Albert Webson, Shixiang Shane Gu, Zhuyun Dai, Mirac Suzgun, Xinyun Chen, Aakanksha Chowdhery, Alex Castro-Ros, Marie Pellat, Kevin Robinson, Dasha Valter, 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
2024	A*	`conf`	The Impact of Group Membership Bias on the Quality and Fairness of Exposure in Ranking. SIGIR Ali Vardasbi, Maarten de Rijke, Fernando Diaz, Mostafa Dehghani
2023	A*	`conf`	$\Lambda$-DARTS: Mitigating Performance Collapse by Harmonizing Operation Selection among Cells. ICLR Sajad Movahedi, Melika Adabinejad, Ayyoob Imani, Arezou Keshavarz, Mostafa Dehghani, Azadeh Shakery, Babak Nadjar Araabi
2023	A*	`conf`	Adaptive Computation with Elastic Input Sequence. ICML Fuzhao Xue, Valerii Likhosherstov, Anurag Arnab, Neil Houlsby, Mostafa Dehghani, Yang You
2023	J	`jnl`	Adaptive Computation with Elastic Input Sequence. CoRR Fuzhao Xue, Valerii Likhosherstov, Anurag Arnab, Neil Houlsby, Mostafa Dehghani, Yang You
2023	A*	`conf`	DSI++: Updating Transformer Memory with New Documents. EMNLP Sanket Vaibhav Mehta, Jai Gupta, Yi Tay, Mostafa Dehghani, Vinh Q. Tran, Jinfeng Rao, Marc Najork, Emma Strubell, Donald Metzler
2023	J	`jnl`	Dual PatchNorm. CoRR Manoj Kumar, Mostafa Dehghani, Neil Houlsby
2023	J	`jnl`	Dual PatchNorm. Trans. Mach. Learn. Res. Manoj Kumar, Mostafa Dehghani, Neil Houlsby
2023	J	`jnl`	Efficient Transformers: A Survey. ACM Comput. Surv. Yi Tay, Mostafa Dehghani, Dara Bahri, Donald Metzler
2023	J	`jnl`	End-to-End Spatio-Temporal Action Localisation with Video Transformers. CoRR Alexey A. Gritsenko, Xuehan Xiong, Josip Djolonga, Mostafa Dehghani, Chen Sun, Mario Lucic, Cordelia Schmid, Anurag Arnab
2023	J	`jnl`	Group Membership Bias. CoRR Ali Vardasbi, Maarten de Rijke, Fernando Diaz, Mostafa Dehghani
2023	—	`conf`	How (not) to ensemble LVLMs for VQA. ICBINB Lisa Alazraki, Lluís Castrejón, Mostafa Dehghani, Fantine Huot, Jasper R. R. Uijlings, Thomas Mensink
2023	J	`jnl`	How (not) to ensemble LVLMs for VQA. CoRR Lisa Alazraki, Lluís Castrejón, Mostafa Dehghani, Fantine Huot, Jasper R. R. Uijlings, Thomas Mensink
2023	—	`conf`	L2 Norm Guided Adaptive Computation. Tiny Papers @ ICLR Mani Shemiranifar, Mostafa Dehghani
2023	J	`jnl`	PaLI-X: On Scaling up a Multilingual Vision and Language Model. CoRR 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
2023	J	`jnl`	PaLM 2 Technical Report. CoRR 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.
2023	J	`jnl`	Parameter-Efficient Multilingual Summarisation: An Empirical Study. CoRR Chenxi Whitehouse, Fantine Huot, Jasmijn Bastings, Mostafa Dehghani, Chu-Cheng Lin, Mirella Lapata
2023	A*	`conf`	Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution. NeurIPS 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
2023	J	`jnl`	Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution. CoRR 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
2023	J	`jnl`	PolyViT: Co-training Vision Transformers on Images, Videos and Audio. Trans. Mach. Learn. Res. Valerii Likhosherstov, Anurag Arnab, Krzysztof Marcin Choromanski, Mario Lucic, Yi Tay, Mostafa Dehghani
2023	—	`conf`	Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling? EMNLP (Findings) Yi Tay, Mostafa Dehghani, Samira Abnar, Hyung Won Chung, William Fedus, Jinfeng Rao, Sharan Narang, Vinh Q. Tran, Dani Yogatama, Donald Metzler
2023	A*	`conf`	Scaling Vision Transformers to 22 Billion Parameters. ICML 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
2023	J	`jnl`	Scaling Vision Transformers to 22 Billion Parameters. CoRR 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
2023	A*	`conf`	Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints. ICLR Aran Komatsuzaki, Joan Puigcerver, James Lee-Thorp, Carlos Riquelme Ruiz, Basil Mustafa, Joshua Ainslie, Yi Tay, Mostafa Dehghani, Neil Houlsby
2023	A*	`conf`	Transcending Scaling Laws with 0.1% Extra Compute. EMNLP 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
2023	A*	`conf`	UL2: Unifying Language Learning Paradigms. ICLR 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
2022	J	`jnl`	Automated Deep Aberration Detection from Chromosome Karyotype Images. CoRR 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
2022	J	`jnl`	Beyond Transfer Learning: Co-finetuning for Action Localisation. CoRR Anurag Arnab, Xuehan Xiong, Alexey A. Gritsenko, Rob Romijnders, Josip Djolonga, Mostafa Dehghani, Chen Sun, Mario Lucic, Cordelia Schmid
2022	A*	`conf`	Confident Adaptive Language Modeling. NeurIPS Tal Schuster, Adam Fisch, Jai Gupta, Mostafa Dehghani, Dara Bahri, Vinh Tran, Yi Tay, Donald Metzler
2022	J	`jnl`	Confident Adaptive Language Modeling. CoRR Tal Schuster, Adam Fisch, Jai Prakash Gupta, Mostafa Dehghani, Dara Bahri, Vinh Q. Tran, Yi Tay, Donald Metzler
2022	J	`jnl`	DSI++: Updating Transformer Memory with New Documents. CoRR Sanket Vaibhav Mehta, Jai Prakash Gupta, Yi Tay, Mostafa Dehghani, Vinh Q. Tran, Jinfeng Rao, Marc Najork, Emma Strubell, Donald Metzler
2022	A*	`conf`	Discrete Representations Strengthen Vision Transformer Robustness. ICLR Chengzhi Mao, Lu Jiang, Mostafa Dehghani, Carl Vondrick, Rahul Sukthankar, Irfan Essa
2022	A*	`conf`	Exploring the Limits of Large Scale Pre-training. ICLR Samira Abnar, Mostafa Dehghani, Behnam Neyshabur, Hanie Sedghi
2022	A	`conf`	Intersection of Parallels as an Early Stopping Criterion. CIKM Ali Vardasbi, Maarten de Rijke, Mostafa Dehghani
2022	J	`jnl`	Intersection of Parallels as an Early Stopping Criterion. CoRR Ali Vardasbi, Maarten de Rijke, Mostafa Dehghani
2022	A*	`conf`	Retrieval-Enhanced Machine Learning. SIGIR Hamed Zamani, Fernando Diaz, Mostafa Dehghani, Donald Metzler, Michael Bendersky
2022	J	`jnl`	Retrieval-Enhanced Machine Learning. CoRR Hamed Zamani, Fernando Diaz, Mostafa Dehghani, Donald Metzler, Michael Bendersky
2022	A*	`conf`	SCENIC: A JAX Library for Computer Vision Research and Beyond. CVPR Mostafa Dehghani, Alexey A. Gritsenko, Anurag Arnab, Matthias Minderer, Yi Tay
2022	A*	`conf`	Scale Efficiently: Insights from Pretraining and Finetuning Transformers. ICLR Yi Tay, Mostafa Dehghani, Jinfeng Rao, William Fedus, Samira Abnar, Hyung Won Chung, Sharan Narang, Dani Yogatama, Ashish Vaswani, Donald Metzler
2022	J	`jnl`	Scaling Instruction-Finetuned Language Models. CoRR 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
2022	J	`jnl`	Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling? CoRR Yi Tay, Mostafa Dehghani, Samira Abnar, Hyung Won Chung, William Fedus, Jinfeng Rao, Sharan Narang, Vinh Q. Tran, Dani Yogatama, Donald Metzler
2022	J	`jnl`	Simple Open-Vocabulary Object Detection with Vision Transformers. CoRR 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
2022	—	`conf`	Simple Open-Vocabulary Object Detection. ECCV (10) 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
2022	J	`jnl`	Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints. CoRR Aran Komatsuzaki, Joan Puigcerver, James Lee-Thorp, Carlos Riquelme Ruiz, Basil Mustafa, Joshua Ainslie, Yi Tay, Mostafa Dehghani, Neil Houlsby
2022	A*	`conf`	The Efficiency Misnomer. ICLR Mostafa Dehghani, Yi Tay, Anurag Arnab, Lucas Beyer, Ashish Vaswani
2022	J	`jnl`	Transcending Scaling Laws with 0.1% Extra Compute. CoRR 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
2022	A*	`conf`	Transformer Memory as a Differentiable Search Index. NeurIPS 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
2022	J	`jnl`	Transformer Memory as a Differentiable Search Index. CoRR 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
2022	J	`jnl`	Unifying Language Learning Paradigms. CoRR Yi Tay, Mostafa Dehghani, Vinh Q. Tran, Xavier Garcia, Dara Bahri, Tal Schuster, Huaixiu Steven Zheng, Neil Houlsby, Donald Metzler
2022	J	`jnl`	Λ-DARTS: Mitigating Performance Collapse by Harmonizing Operation Selection among Cells. CoRR Sajad Movahedi, Melika Adabinejad, Ayyoob Imani, Arezou Keshavarz, Mostafa Dehghani, Azadeh Shakery, Babak Nadjar Araabi
2021	A*	`conf`	An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby
2021	J	`jnl`	Are Pre-trained Convolutions Better than Pre-trained Transformers? CoRR Yi Tay, Mostafa Dehghani, Jai Prakash Gupta, Dara Bahri, Vamsi Aribandi, Zhen Qin, Donald Metzler
2021	—	`conf`	Are Pretrained Convolutions Better than Pretrained Transformers? ACL/IJCNLP (1) Yi Tay, Mostafa Dehghani, Jai Prakash Gupta, Vamsi Aribandi, Dara Bahri, Zhen Qin, Donald Metzler
2021	J	`jnl`	Discrete Representations Strengthen Vision Transformer Robustness. CoRR Chengzhi Mao, Lu Jiang, Mostafa Dehghani, Carl Vondrick, Rahul Sukthankar, Irfan Essa
2021	J	`jnl`	Exploring the Limits of Large Scale Pre-training. CoRR Samira Abnar, Mostafa Dehghani, Behnam Neyshabur, Hanie Sedghi
2021	J	`jnl`	Gradual Domain Adaptation in the Wild: When Intermediate Distributions are Absent. CoRR Samira Abnar, Rianne van den Berg, Golnaz Ghiasi, Mostafa Dehghani, Nal Kalchbrenner, Hanie Sedghi
2021	A*	`conf`	IDF++: Analyzing and Improving Integer Discrete Flows for Lossless Compression. ICLR Rianne van den Berg, Alexey A. Gritsenko, Mostafa Dehghani, Casper Kaae Sønderby, Tim Salimans
2021	J	`jnl`	Learning to rank for multi-label text classification: Combining different sources of information. Nat. Lang. Eng. Hosein Azarbonyad, Mostafa Dehghani, Maarten Marx, Jaap Kamps
2021	A*	`conf`	Long Range Arena : A Benchmark for Efficient Transformers. ICLR Yi Tay, Mostafa Dehghani, Samira Abnar, Yikang Shen, Dara Bahri, Philip Pham, Jinfeng Rao, Liu Yang, Sebastian Ruder, Donald Metzler
2021	A*	`conf`	OmniNet: Omnidirectional Representations from Transformers. ICML Yi Tay, Mostafa Dehghani, Vamsi Aribandi, Jai Prakash Gupta, Philip Pham, Zhen Qin, Dara Bahri, Da-Cheng Juan, Donald Metzler
2021	J	`jnl`	OmniNet: Omnidirectional Representations from Transformers. CoRR Yi Tay, Mostafa Dehghani, Vamsi Aribandi, Jai Prakash Gupta, Philip Pham, Zhen Qin, Dara Bahri, Da-Cheng Juan, Donald Metzler
2021	—	`conf`	Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks. ACL/IJCNLP (1) Rabeeh Karimi Mahabadi, Sebastian Ruder, Mostafa Dehghani, James Henderson
2021	J	`jnl`	Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks. CoRR Rabeeh Karimi Mahabadi, Sebastian Ruder, Mostafa Dehghani, James Henderson
2021	J	`jnl`	PolyViT: Co-training Vision Transformers on Images, Videos and Audio. CoRR Valerii Likhosherstov, Anurag Arnab, Krzysztof Choromanski, Mario Lucic, Yi Tay, Adrian Weller, Mostafa Dehghani
2021	J	`jnl`	SCENIC: A JAX Library for Computer Vision Research and Beyond. CoRR Mostafa Dehghani, Alexey A. Gritsenko, Anurag Arnab, Matthias Minderer, Yi Tay
2021	J	`jnl`	Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers. CoRR Yi Tay, Mostafa Dehghani, Jinfeng Rao, William Fedus, Samira Abnar, Hyung Won Chung, Sharan Narang, Dani Yogatama, Ashish Vaswani, Donald Metzler
2021	J	`jnl`	The Benchmark Lottery. CoRR Mostafa Dehghani, Yi Tay, Alexey A. Gritsenko, Zhe Zhao, Neil Houlsby, Fernando Diaz, Donald Metzler, Oriol Vinyals
2021	J	`jnl`	The Efficiency Misnomer. CoRR Mostafa Dehghani, Anurag Arnab, Lucas Beyer, Ashish Vaswani, Yi Tay
2021	A*	`conf`	TokenLearner: Adaptive Space-Time Tokenization for Videos. NeurIPS Michael S. Ryoo, A. J. Piergiovanni, Anurag Arnab, Mostafa Dehghani, Anelia Angelova
2021	J	`jnl`	TokenLearner: What Can 8 Learned Tokens Do for Images and Videos? CoRR Michael S. Ryoo, A. J. Piergiovanni, Anurag Arnab, Mostafa Dehghani, Anelia Angelova
2021	J	`jnl`	VUT: Versatile UI Transformer for Multi-Modal Multi-Task User Interface Modeling. CoRR Yang Li, Gang Li, Xin Zhou, Mostafa Dehghani, Alexey A. Gritsenko
2021	A*	`conf`	ViViT: A Video Vision Transformer. ICCV Anurag Arnab, Mostafa Dehghani, Georg Heigold, Chen Sun, Mario Lucic, Cordelia Schmid
2021	J	`jnl`	ViViT: A Video Vision Transformer. CoRR Anurag Arnab, Mostafa Dehghani, Georg Heigold, Chen Sun, Mario Lucic, Cordelia Schmid
2020	J	`jnl`	An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. CoRR Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby
2020	J	`jnl`	Efficient Transformers: A Survey. CoRR Yi Tay, Mostafa Dehghani, Dara Bahri, Donald Metzler
2020	J	`jnl`	IDF++: Analyzing and Improving Integer Discrete Flows for Lossless Compression. CoRR Rianne van den Berg, Alexey A. Gritsenko, Mostafa Dehghani, Casper Kaae Sønderby, Tim Salimans
2020	J	`jnl`	Long Range Arena: A Benchmark for Efficient Transformers. CoRR Yi Tay, Mostafa Dehghani, Samira Abnar, Yikang Shen, Dara Bahri, Philip Pham, Jinfeng Rao, Liu Yang, Sebastian Ruder, Donald Metzler
2020	J	`jnl`	MetNet: A Neural Weather Model for Precipitation Forecasting. CoRR Casper Kaae Sønderby, Lasse Espeholt, Jonathan Heek, Mostafa Dehghani, Avital Oliver, Tim Salimans, Shreya Agrawal, Jason Hickey, Nal Kalchbrenner
2020	J	`jnl`	Transferring Inductive Biases through Knowledge Distillation. CoRR Samira Abnar, Mostafa Dehghani, Willem H. Zuidema
2019	J	`jnl`	HiTR: Hierarchical Topic Model Re-Estimation for Measuring Topical Diversity of Documents. IEEE Trans. Knowl. Data Eng. Hosein Azarbonyad, Mostafa Dehghani, Tom Kenter, Maarten Marx, Jaap Kamps, Maarten de Rijke
2019	—	`conf`	Learning to Transform, Combine, and Reason in Open-Domain Question Answering. BNAIC/BENELEARN Mostafa Dehghani, Hosein Azarbonyad, Jaap Kamps, Maarten de Rijke
2019	A	`conf`	Learning to Transform, Combine, and Reason in Open-Domain Question Answering. WSDM Mostafa Dehghani, Hosein Azarbonyad, Jaap Kamps, Maarten de Rijke
2019	—	`conf`	Universal Transformers. ICLR (Poster) Mostafa Dehghani, Stephan Gouws, Oriol Vinyals, Jakob Uszkoreit, Lukasz Kaiser
2018	J	`jnl`	Expert finding by the Dempster-Shafer theory for evidence combination. Expert Syst. J. Knowl. Eng. Nafiseh Torkzadeh Mahani, Mostafa Dehghani, Maryam S. Mirian, Azadeh Shakery, Khalil Taheri
2018	—	`conf`	Fidelity-Weighted Learning. ICLR (Poster) Mostafa Dehghani, Arash Mehrjou, Stephan Gouws, Jaap Kamps, Bernhard Schölkopf
2018	A	`conf`	From Neural Re-Ranking to Neural Ranking: Learning a Sparse Representation for Inverted Indexing. CIKM Hamed Zamani, Mostafa Dehghani, W. Bruce Croft, Erik G. Learned-Miller, Jaap Kamps
2018	J	`jnl`	HiTR: Hierarchical Topic Model Re-estimation for Measuring Topical Diversity of Documents. CoRR Hosein Azarbonyad, Mostafa Dehghani, Tom Kenter, Maarten Marx, Jaap Kamps, Maarten de Rijke
2018	J	`jnl`	Learning to Rank from Samples of Variable Quality. CoRR Mostafa Dehghani, Jaap Kamps
2018	A	`conf`	Neural Networks for Information Retrieval. WSDM Tom Kenter, Alexey Borisov, Christophe Van Gysel, Mostafa Dehghani, Maarten de Rijke, Bhaskar Mitra
2018	J	`jnl`	Neural Networks for Information Retrieval. CoRR Tom Kenter, Alexey Borisov, Christophe Van Gysel, Mostafa Dehghani, Maarten de Rijke, Bhaskar Mitra
2018	A*	`conf`	SIGIR 2018 Workshop on Learning from Limited or Noisy Data for Information Retrieval. SIGIR Hamed Zamani, Mostafa Dehghani, Fernando Diaz, Hang Li, Nick Craswell
2018	J	`jnl`	Universal Transformers. CoRR Mostafa Dehghani, Stephan Gouws, Oriol Vinyals, Jakob Uszkoreit, Lukasz Kaiser
2017	J	`jnl`	Avoiding Your Teacher's Mistakes: Training Neural Networks with Controlled Weak Supervision. CoRR Mostafa Dehghani, Aliaksei Severyn, Sascha Rothe, Jaap Kamps
2017	J	`jnl`	Fidelity-Weighted Learning. CoRR Mostafa Dehghani, Arash Mehrjou, Stephan Gouws, Jaap Kamps, Bernhard Schölkopf
2017	A	`conf`	Hierarchical Re-estimation of Topic Models for Measuring Topical Diversity. ECIR Hosein Azarbonyad, Mostafa Dehghani, Tom Kenter, Maarten Marx, Jaap Kamps, Maarten de Rijke
2017	J	`jnl`	Hierarchical Re-estimation of Topic Models for Measuring Topical Diversity. CoRR Hosein Azarbonyad, Mostafa Dehghani, Tom Kenter, Maarten Marx, Jaap Kamps, Maarten de Rijke
2017	A	`conf`	Learning to Attend, Copy, and Generate for Session-Based Query Suggestion. CIKM Mostafa Dehghani, Sascha Rothe, Enrique Alfonseca, Pascal Fleury
2017	J	`jnl`	Learning to Attend, Copy, and Generate for Session-Based Query Suggestion. CoRR Mostafa Dehghani, Sascha Rothe, Enrique Alfonseca, Pascal Fleury
2017	J	`jnl`	Learning to Learn from Weak Supervision by Full Supervision. CoRR Mostafa Dehghani, Aliaksei Severyn, Sascha Rothe, Jaap Kamps
2017	A*	`conf`	Neural Networks for Information Retrieval. SIGIR Tom Kenter, Alexey Borisov, Christophe Van Gysel, Mostafa Dehghani, Maarten de Rijke, Bhaskar Mitra
2017	J	`jnl`	Neural Networks for Information Retrieval. CoRR Tom Kenter, Alexey Borisov, Christophe Van Gysel, Mostafa Dehghani, Maarten de Rijke, Bhaskar Mitra
2017	A*	`conf`	Neural Ranking Models with Weak Supervision. SIGIR Mostafa Dehghani, Hamed Zamani, Aliaksei Severyn, Jaap Kamps, W. Bruce Croft
2017	J	`jnl`	Neural Ranking Models with Weak Supervision. CoRR Mostafa Dehghani, Hamed Zamani, Aliaksei Severyn, Jaap Kamps, W. Bruce Croft
2017	Misc	`conf`	On Search Powered Navigation. ICTIR Mostafa Dehghani, Glorianna Jagfeld, Hosein Azarbonyad, Alex Olieman, Jaap Kamps, Maarten Marx
2017	J	`jnl`	On Search Powered Navigation. CoRR Mostafa Dehghani, Glorianna Jagfeld, Hosein Azarbonyad, Alex Olieman, Jaap Kamps, Maarten Marx
2017	J	`jnl`	Share your Model instead of your Data: Privacy Preserving Mimic Learning for Ranking. CoRR Mostafa Dehghani, Hosein Azarbonyad, Jaap Kamps, Maarten de Rijke
2017	B	`conf`	Telling How to Narrow it Down: Browsing Path Recommendation for Exploratory Search. CHIIR Mostafa Dehghani, Glorianna Jagfeld, Hosein Azarbonyad, Alex Olieman, Jaap Kamps, Maarten Marx
2017	J	`jnl`	Toward Document Understanding for Information Retrieval. SIGIR Forum Mostafa Dehghani
2017	A	`conf`	Words are Malleable: Computing Semantic Shifts in Political and Media Discourse. CIKM Hosein Azarbonyad, Mostafa Dehghani, Kaspar Beelen, Alexandra Arkut, Maarten Marx, Jaap Kamps
2017	J	`jnl`	Words are Malleable: Computing Semantic Shifts in Political and Media Discourse. CoRR Hosein Azarbonyad, Mostafa Dehghani, Kaspar Beelen, Alexandra Arkut, Maarten Marx, Jaap Kamps
2016	J	`jnl`	Alecsa: Attentive Learning for Email Categorization using Structural Aspects. Knowl. Based Syst. Mostafa Dehghani, Azadeh Shakery, Maryam S. Mirian
2016	J	`jnl`	Building a multi-domain comparable corpus using a learning to rank method. Nat. Lang. Eng. Razieh Rahimi, Azadeh Shakery, Javid Dadashkarimi, Mozhdeh Ariannezhad, Mostafa Dehghani, Hossein Nasr Esfahani
2016	—	`conf`	Distributional Semantics for Medical Information Extraction. CLEF (Working Notes) Lautaro Quiroz, Lydia Mennes, Mostafa Dehghani, Evangelos Kanoulas
2016	B	`conf`	Generalized Group Profiling for Content Customization. CHIIR Mostafa Dehghani, Hosein Azarbonyad, Jaap Kamps, Maarten Marx
2016	J	`jnl`	Generalized Group Profiling for Content Customization. CoRR Mostafa Dehghani, Hosein Azarbonyad, Jaap Kamps, Maarten Marx
2016	A	`conf`	Luhn Revisited: Significant Words Language Models. CIKM Mostafa Dehghani, Hosein Azarbonyad, Jaap Kamps, Djoerd Hiemstra, Maarten Marx
2016	Misc	`conf`	On Horizontal and Vertical Separation in Hierarchical Text Classification. ICTIR Mostafa Dehghani, Hosein Azarbonyad, Jaap Kamps, Maarten Marx
2016	J	`jnl`	On Horizontal and Vertical Separation in Hierarchical Text Classification. CoRR Mostafa Dehghani, Hosein Azarbonyad, Jaap Kamps, Maarten Marx
2016	—	`conf`	Significant Words Language Models for Contextual Suggestion. TREC Mostafa Dehghani, Jaap Kamps, Hosein Azarbonyad, Maarten Marx
2016	A*	`conf`	Significant Words Representations of Entities. SIGIR Mostafa Dehghani
2016	A	`conf`	The Healing Power of Poison: Helpful Non-relevant Documents in Feedback. CIKM Mostafa Dehghani, Samira Abnar, Jaap Kamps
2016	—	`conf`	Two-Way Parsimonious Classification Models for Evolving Hierarchies. CLEF Mostafa Dehghani, Hosein Azarbonyad, Jaap Kamps, Maarten Marx
2015	—	`conf`	Are Topically Diverse Documents Also Interesting? CLEF Hosein Azarbonyad, Ferron Saan, Mostafa Dehghani, Maarten Marx, Jaap Kamps
2015	—	`conf`	Meta Text Aligner: Text Alignment Based on Predicted Plagiarism Relation. CLEF Samira Abnar, Mostafa Dehghani, Azadeh Shakery
2015	—	`conf`	Parsimonious User and Group Profiling in Venue Recommendation. TREC Seyyed Hadi Hashemi, Mostafa Dehghani, Jaap Kamps
2015	Misc	`conf`	Revisiting Optimal Rank Aggregation: A Dynamic Programming Approach. ICTIR Shayan A. Tabrizi, Javid Dadashkarimi, Mostafa Dehghani, Hassan Nasr Esfahani, Azadeh Shakery
2015	A	`conf`	Sources of Evidence for Automatic Indexing of Political Texts. ECIR Mostafa Dehghani, Hosein Azarbonyad, Maarten Marx, Jaap Kamps
2015	A*	`conf`	Time-Aware Authorship Attribution for Short Text Streams. SIGIR Hosein Azarbonyad, Mostafa Dehghani, Maarten Marx, Jaap Kamps
2014	—	`conf`	Authorship Identification Using Dynamic Selection of Features from Probabilistic Feature Set. CLEF Hamed Zamani, Hossein Nasr Esfahani, Pariya Babaie, Samira Abnar, Mostafa Dehghani, Azadeh Shakery
2014	—	`conf`	Entity linking by focusing DBpedia candidate entities. ERD@SIGIR Alex Olieman, Hosein Azarbonyad, Mostafa Dehghani, Jaap Kamps, Maarten Marx
2014	—	`conf`	Expanded N-Grams for Semantic Text Alignment Notebook for PAN at CLEF 2014. CLEF (Working Notes) Samira Abnar, Mostafa Dehghani, Hamed Zamani, Azadeh Shakery
2013	J	`jnl`	A Supervised Approach for Reconstructing Thread Structure in Comments on Blogs and Online News Agencies (El enfoque supervisado para reconstrucción de la estructura de hilos en comentarios en blogs y agencias de noticias en línea). Computación y Sistemas Ali Balali, Heshaam Faili, Masoud Asadpour, Mostafa Dehghani
2013	J	`jnl`	A learning approach for email conversation thread reconstruction. J. Inf. Sci. Mostafa Dehghani, Azadeh Shakery, Masoud Asadpour, Arash Koushkestani
2012	B	`conf`	An Evolutionary-Based Method for Reconstructing Conversation Threads in Email Corpora. ASONAM Mostafa Dehghani, Masoud Asadpour, Azadeh Shakery