Scaling Laws for Pre-training Agents and World Models
Tim Pearce, Tabish Rashid, Dave Bignell, Raluca Stevenson, Sam Devlin, Katja Hofmann
November 2024
Publications
Publications by Year
-
Domain mismatch and data augmentation in speech emotion recognition
Dimitra Emmanouilidou, Hannes Gamper, Midia Yousefi
SMM24, Interspeech Workshop on Speech, Music and Mind 2024 | September 2024
Learning Safety Constraints from Demonstrations with Unknown Rewards
David Lindner, Xin Chen, Sebastian Tschiatschek, Katja Hofmann, Andreas Krause
International Conference on Artificial Intelligence and Statistics | April 2024
Toward Human-AI Alignment in Large-Scale Multi-Player Games
Sugandha Sharma, Guy Davidson, Khimya Khetarpal, Anssi Kanervisto, Udit Arora, Katja Hofmann, Ida Momennejad
arXiv:2402.03575 | February 2024
Published by Microsoft
-
Orca-2: Teaching Small Language Models How to Reason
Arindam Mitra, Luciano Del Corro, Shweti Mahajan, Andres Codas, Clarisse Simoes Ribeiro, Sahaj Agrawal, Xuxi Chen, Anastasia Razdaibiedina, Erik Jones, Kriti Aggarwal, Hamid Palangi, Guoqing Zheng, Corby Rosset, Hamed Khanpour, Ahmed Awadallah
November 2023
Comparing the Efficacy of Fine-Tuning and Meta-Learning for Few-Shot Policy Imitation
Massimiliano Patacchiola, Mingfei Sun, Katja Hofmann, Richard E Turner
Conference on Lifelong Learning Agents | November 2023
Multi-View Learning for Speech Emotion Recognition
Daniel Tompkins, Dimitra Emmanouilidou, Soham Deshmukh, Benjamin Elizalde
International Conference on Acoustics, Speech and Signal Processing | June 2023
Orca: Progressive Learning from Complex Explanation Traces of GPT-4
Subhabrata (Subho) Mukherjee, Arindam Mitra, Ganesh Jawahar, Sahaj Agarwal, Hamid Palangi, Ahmed Awadallah
arXiv: Computation and Language | June 2023
ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models
Binfeng Xu, Zhiyuan Peng, Bowen Lei, Subhabrata (Subho) Mukherjee, Yuchen Liu, Dongkuan Xu
arXiv: Computation and Language | May 2023
A Systematic Study of Knowledge Distillation for Natural Language Generation with Pseudo-Target Training
Nitay Calderon, Subhabrata (Subho) Mukherjee, Roi Reichart, Amir Kantor
ACL 2023 | May 2023
AutoMoE: Neural Architecture Search for Efficient Sparsely Activated Transformers
Ganesh Jawahar, Subhabrata (Subho) Mukherjee, Xiaodong Liu, Young Jin Kim, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan, Ahmed Awadallah, Sébastien Bubeck, Jianfeng Gao
ACL | May 2023
Investigations in Audio Captioning: Addressing Vocabulary Imbalance and Evaluating Suitability of Language-Centric Performance Metrics
Sandeep Kothinti, Dimitra Emmanouilidou
European Signal Processing Conference (EUSIPCO) | May 2023
What do Compressed Large Language Models Forget? Robustness Challenges in Model Compression
Mengnan Du, Subhabrata (Subho) Mukherjee, Yu Cheng, Milad Shokouhi, Xia Hu, Ahmed Awadallah
EACL | April 2023
Accelerating Dataset Distillation via Model Augmentation
Lei Zhang, Jie Zhang, Bowen Lei, Subhabrata (Subho) Mukherjee, Xiang Pan, Bo Zhao, Caiwen Ding, Yao Li, Dongkuan Xu
2023 Computer Vision and Pattern Recognition | March 2023
Highlight paper (2.5%)
ADMoE: Anomaly Detection with Mixture-of-Experts from Noisy Labels
Yue Zhao, Guoqing Zheng, Subhabrata (Subho) Mukherjee, Robert McCann, Ahmed Awadallah
AAAI | January 2023
-
AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning
Yaqing Wang, Sahaj Agarwal, Subhabrata (Subho) Mukherjee, Xiaodong Liu, Jing Gao, Ahmed Awadallah, Jianfeng Gao
EMNLP | December 2022
Boosting Natural Language Generation from Instructions with Meta-Learning
Budhaditya Deb, Guoqing Zheng, Ahmed Awadallah
EMNLP | December 2022
Imagining future digital assistants at work: A study of task management needs
Yonchanok Khaokaew, Indigo Holcombe-James, Mohammad Saiedur Rahaman, Jonathan Liono, Johanne R. Trippas, Damiano Spina, Peter Bailey, Nicholas J. Belkin, Paul Bennett, Yongli Ren, Mark Sanderson, Falk Scholer, Ryen W. White, Flora D. Salim
International Journal of Human-Computer Studies | December 2022, Vol 168
Periodic motion-based visual stimulus
Andrew D. Wilson, Ivan Tashev, Hannes Gamper, Ed Cutrell, David Johnston, Dimitra Emmanouilidou
MSR-TR-2022-37 | November 2022
Published by Microsoft
US-20220365599-A1
Heterogeneous Ensemble Knowledge Transfer for Training Large Models in Federated Learning
Yae Jee Cho, Andre Manoel, Gauri Joshi, Robert Sim, Dimitrios Dimitriadis
IJCAI-ECAI’22 | August 2022
Toxic Speech and Speech Emotions: Investigations of Audio-based Modeling and Intercorrelations
Wei-Cheng Lin, Dimitra Emmanouilidou
European Signal Processing Conference (EUSIPCO) | August 2022
UserIdentifier: Implicit User Representations for Simple and Effective Personalized Sentiment Analysis
Fatemehsadat Mireshghallah, Vaishnavi Shrivastava, Milad Shokouhi, Taylor Berg-Kirkpatrick, Robert Sim, Dimitrios Dimitriadis
2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL’22) | July 2022
Privacy Leakage in Text Classification: A Data Extraction Approach
Adel Elmahdy, Huseyin Inan, Robert Sim
June 2022
Knowledge Infused Decoding
Ruibo Liu, Guoqing Zheng, Shashank Gupta, Radhika Gaonkar, Chongyang Gao, Soroush Vosoughi, Milad Shokouhi, Ahmed Awadallah
ICLR 2022 | April 2022
LiST: Lite Prompted Self-training Makes Parameter-efficient Few-shot Learners
Yaqing Wang, Subhabrata (Subho) Mukherjee, Xiaodong Liu, Jing Gao, Ahmed Awadallah, Jianfeng Gao
NAACL 2022 | April 2022
Sparsely Activated Mixture-of-Experts are Robust Multi-Task Learners
Shashank Gupta, Subhabrata (Subho) Mukherjee, Krishan Subudhi, Eduardo Gonzalez, Damien Jose, Ahmed Awadallah, Jianfeng Gao
ArXiv | April 2022
FLUTE: A Scalable, Extensible Framework for High-Performance Federated Learning Simulations
Dimitrios Dimitriadis, Mirian Hipolito Garcia, Daniel Madrigal, Andre Manoel, Robert Sim
March 2022
Population-scale dietary interests during the COVID-19 pandemic.
Kristina Gligoric, Arnaud Chiolero, Emre Kiciman, Ryen W. White, Robert West
Nature Communications | February 2022, Vol 13(1073)
-
CLUES: Few-Shot Learning Evaluation in Natural Language Understanding
Subhabrata (Subho) Mukherjee, Xiaodong Liu, Guoqing Zheng, Saghar Hosseini, Hao Cheng, Greg Yang, Chris Meek, Ahmed Awadallah, Jianfeng Gao
NeurIPS 2021 | December 2021
Fairness via Representation Neutralization
Mengnan Du, Subhabrata (Subho) Mukherjee, Guanchu Wang, Ruixiang Tang, Ahmed Awadallah, Xia Hu
NeurIPS 2021 | December 2021
A Review of Speaker Diarization: Recent Advances with Deep Learning
Tae Jin Park, Naoyuki Kanda, Dimitrios Dimitriadis, Kyu J. Han, Shinji Watanabe, Shrikanth Narayanan
Computer Speech & Language | November 2021, Vol 72
Say `YES’ to Positivity: Detecting Toxic Language in Workplace Communications
Meghana Moorthy Bhat, Saghar Hosseini, Ahmed Awadallah, Paul Bennett, Weisheng Li
EMNLP 2021 | November 2021
Self-training with Few-shot Rationalization: Teacher Explanations Aid Student in Few-shot NLU
Meghana Moorthy Bhat, Alessandro Sordoni, Subhabrata (Subho) Mukherjee
EMNLP 2021 | November 2021
Tackling Dynamics in Federated Incremental Learning with Variational Embedding Rehearsal
Tae Jin Park, Kenichi Kumatani, Dimitrios Dimitriadis
October 2021
Meta Self-training for Few-shot Neural Sequence Labeling
Yaqing Wang, Subhabrata (Subho) Mukherjee, Haoda Chu, Yuancheng Tu, Ming Wu, Jing Gao, Ahmed Awadallah
SIGKDD 2021 (Research Track) | August 2021
One-Shot Voice Conversion with Speaker-Agnostic StarGAN
Sefik Emre Eskimez, Dimitrios Dimitriadis, Kenichi Kumatani, Robert Gmyr
INTERSPEECH 2022 | August 2021
Ensemble Combination between Different Time Segmentations
Jeremy Wong, Dimitrios Dimitriadis, Kenichi Kumatani, Yashesh Gaur, George Polovets, Partha Parthasarathy, Eric Sun, Jinyu Li, Yifan Gong
2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) | June 2021
NL-EDIT: Correcting Semantic Parse Errors through Natural Language Interaction
Ahmed Elgohary, Chris Meek, Matthew Richardson, Adam Fourney, Gonzalo Ramos, Ahmed Awadallah
NAACL 2021 | June 2021
Structure-Grounded Pretraining for Text-to-SQL
Xiang Deng, Ahmed Awadallah, Chris Meek, Alex Polozov, Huan Sun, Matthew Richardson
NAACL 2021 | June 2021
XtremeDistilTransformers: Task Transfer for Task-agnostic Distillation
Subhabrata (Subho) Mukherjee, Ahmed Awadallah, Jianfeng Gao
ArXiv | June 2021
arXiv:2106.04563
MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning
Mengzhou Xia, Guoqing Zheng, Subhabrata (Subho) Mukherjee, Milad Shokouhi, Graham Neubig, Ahmed Awadallah
NAACL 2021 | May 2021
Self-training with Weak Supervision
Giannis Karamanolakis, Subhabrata (Subho) Mukherjee, Guoqing Zheng, Ahmed Awadallah
NAACL 2021 | May 2021
SCoRe: Pre-Training for Context Representation in Conversational Semantic Parsing
Tao Yu, Rui Zhang, Alex Polozov, Chris Meek, Ahmed Awadallah
ICLR | May 2021
QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization
Ming Zhong, Da Yin, Tao Yu, Ahmad Zaidi, Mutethia Mutuma, Rahul Jha, Ahmed Awadallah, Asli Celikyilmaz, Yang Liu, Xipeng Qiu, Dragomir R. Radev
NAACL | April 2021
-
A Federated Approach in Training Acoustic Models
Dimitrios Dimitriadis, Kenichi Kumatani, Robert Gmyr, Yashesh Gaur, Sefik Emre Eskimez
INTERSPEECH 2020 | October 2020
GAN-based Data Generation for Speech Emotion Recognition
Sefik Emre Eskimez, Dimitrios Dimitriadis, Robert Gmyr, Kenichi Kumatani
INTERSPEECH 2020 | October 2020
Sequence-level self-learning with multi-task learning framework
Kenichi Kumatani, Dimitrios Dimitriadis, Yashesh Gaur, Robert Gmyr, Sefik Emre Eskimez, Jinyu Li, Michael Zeng
October 2020
Intelligent Task Recognition: Towards Enabling Productivity Assistance in Daily Life
Jonathan Liono, Mohammad Saiedur Rahaman, Flora D Salim, Yongli Ren, Damiano Spina, Falk Scholer, Johanne R Trippas, Mark Sanderson, Ryen W. White, Paul Bennett
2020 International Conference on Multimedia Retrieval | June 2020
Publications by Research Area
-
Scaling Laws for Pre-training Agents and World Models
Tim Pearce, Tabish Rashid, Dave Bignell, Raluca Stevenson, Sam Devlin, Katja Hofmann
November 2024
Learning Safety Constraints from Demonstrations with Unknown Rewards
David Lindner, Xin Chen, Sebastian Tschiatschek, Katja Hofmann, Andreas Krause
International Conference on Artificial Intelligence and Statistics | April 2024
Toward Human-AI Alignment in Large-Scale Multi-Player Games
Sugandha Sharma, Guy Davidson, Khimya Khetarpal, Anssi Kanervisto, Udit Arora, Katja Hofmann, Ida Momennejad
arXiv:2402.03575 | February 2024
Published by Microsoft
Orca-2: Teaching Small Language Models How to Reason
Arindam Mitra, Luciano Del Corro, Shweti Mahajan, Andres Codas, Clarisse Simoes Ribeiro, Sahaj Agrawal, Xuxi Chen, Anastasia Razdaibiedina, Erik Jones, Kriti Aggarwal, Hamid Palangi, Guoqing Zheng, Corby Rosset, Hamed Khanpour, Ahmed Awadallah
November 2023
Comparing the Efficacy of Fine-Tuning and Meta-Learning for Few-Shot Policy Imitation
Massimiliano Patacchiola, Mingfei Sun, Katja Hofmann, Richard E Turner
Conference on Lifelong Learning Agents | November 2023
Orca: Progressive Learning from Complex Explanation Traces of GPT-4
Subhabrata (Subho) Mukherjee, Arindam Mitra, Ganesh Jawahar, Sahaj Agarwal, Hamid Palangi, Ahmed Awadallah
arXiv: Computation and Language | June 2023
ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models
Binfeng Xu, Zhiyuan Peng, Bowen Lei, Subhabrata (Subho) Mukherjee, Yuchen Liu, Dongkuan Xu
arXiv: Computation and Language | May 2023
A Systematic Study of Knowledge Distillation for Natural Language Generation with Pseudo-Target Training
Nitay Calderon, Subhabrata (Subho) Mukherjee, Roi Reichart, Amir Kantor
ACL 2023 | May 2023
AutoMoE: Neural Architecture Search for Efficient Sparsely Activated Transformers
Ganesh Jawahar, Subhabrata (Subho) Mukherjee, Xiaodong Liu, Young Jin Kim, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan, Ahmed Awadallah, Sébastien Bubeck, Jianfeng Gao
ACL | May 2023
Accelerating Dataset Distillation via Model Augmentation
Lei Zhang, Jie Zhang, Bowen Lei, Subhabrata (Subho) Mukherjee, Xiang Pan, Bo Zhao, Caiwen Ding, Yao Li, Dongkuan Xu
2023 Computer Vision and Pattern Recognition | March 2023
Highlight paper (2.5%)
ADMoE: Anomaly Detection with Mixture-of-Experts from Noisy Labels
Yue Zhao, Guoqing Zheng, Subhabrata (Subho) Mukherjee, Robert McCann, Ahmed Awadallah
AAAI | January 2023
AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning
Yaqing Wang, Sahaj Agarwal, Subhabrata (Subho) Mukherjee, Xiaodong Liu, Jing Gao, Ahmed Awadallah, Jianfeng Gao
EMNLP | December 2022
Boosting Natural Language Generation from Instructions with Meta-Learning
Budhaditya Deb, Guoqing Zheng, Ahmed Awadallah
EMNLP | December 2022
Imagining future digital assistants at work: A study of task management needs
Yonchanok Khaokaew, Indigo Holcombe-James, Mohammad Saiedur Rahaman, Jonathan Liono, Johanne R. Trippas, Damiano Spina, Peter Bailey, Nicholas J. Belkin, Paul Bennett, Yongli Ren, Mark Sanderson, Falk Scholer, Ryen W. White, Flora D. Salim
International Journal of Human-Computer Studies | December 2022, Vol 168
Heterogeneous Ensemble Knowledge Transfer for Training Large Models in Federated Learning
Yae Jee Cho, Andre Manoel, Gauri Joshi, Robert Sim, Dimitrios Dimitriadis
IJCAI-ECAI’22 | August 2022
UserIdentifier: Implicit User Representations for Simple and Effective Personalized Sentiment Analysis
Fatemehsadat Mireshghallah, Vaishnavi Shrivastava, Milad Shokouhi, Taylor Berg-Kirkpatrick, Robert Sim, Dimitrios Dimitriadis
2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL’22) | July 2022
Sparsely Activated Mixture-of-Experts are Robust Multi-Task Learners
Shashank Gupta, Subhabrata (Subho) Mukherjee, Krishan Subudhi, Eduardo Gonzalez, Damien Jose, Ahmed Awadallah, Jianfeng Gao
ArXiv | April 2022
Knowledge Infused Decoding
Ruibo Liu, Guoqing Zheng, Shashank Gupta, Radhika Gaonkar, Chongyang Gao, Soroush Vosoughi, Milad Shokouhi, Ahmed Awadallah
ICLR 2022 | April 2022
LiST: Lite Prompted Self-training Makes Parameter-efficient Few-shot Learners
Yaqing Wang, Subhabrata (Subho) Mukherjee, Xiaodong Liu, Jing Gao, Ahmed Awadallah, Jianfeng Gao
NAACL 2022 | April 2022
FLUTE: A Scalable, Extensible Framework for High-Performance Federated Learning Simulations
Dimitrios Dimitriadis, Mirian Hipolito Garcia, Daniel Madrigal, Andre Manoel, Robert Sim
March 2022
Population-scale dietary interests during the COVID-19 pandemic.
Kristina Gligoric, Arnaud Chiolero, Emre Kiciman, Ryen W. White, Robert West
Nature Communications | February 2022, Vol 13(1073)
CLUES: Few-Shot Learning Evaluation in Natural Language Understanding
Subhabrata (Subho) Mukherjee, Xiaodong Liu, Guoqing Zheng, Saghar Hosseini, Hao Cheng, Greg Yang, Chris Meek, Ahmed Awadallah, Jianfeng Gao
NeurIPS 2021 | December 2021
Fairness via Representation Neutralization
Mengnan Du, Subhabrata (Subho) Mukherjee, Guanchu Wang, Ruixiang Tang, Ahmed Awadallah, Xia Hu
NeurIPS 2021 | December 2021
A Review of Speaker Diarization: Recent Advances with Deep Learning
Tae Jin Park, Naoyuki Kanda, Dimitrios Dimitriadis, Kyu J. Han, Shinji Watanabe, Shrikanth Narayanan
Computer Speech & Language | November 2021, Vol 72
Tackling Dynamics in Federated Incremental Learning with Variational Embedding Rehearsal
Tae Jin Park, Kenichi Kumatani, Dimitrios Dimitriadis
October 2021
Meta Self-training for Few-shot Neural Sequence Labeling
Yaqing Wang, Subhabrata (Subho) Mukherjee, Haoda Chu, Yuancheng Tu, Ming Wu, Jing Gao, Ahmed Awadallah
SIGKDD 2021 (Research Track) | August 2021
One-Shot Voice Conversion with Speaker-Agnostic StarGAN
Sefik Emre Eskimez, Dimitrios Dimitriadis, Kenichi Kumatani, Robert Gmyr
INTERSPEECH 2022 | August 2021
Ensemble Combination between Different Time Segmentations
Jeremy Wong, Dimitrios Dimitriadis, Kenichi Kumatani, Yashesh Gaur, George Polovets, Partha Parthasarathy, Eric Sun, Jinyu Li, Yifan Gong
2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) | June 2021
NL-EDIT: Correcting Semantic Parse Errors through Natural Language Interaction
Ahmed Elgohary, Chris Meek, Matthew Richardson, Adam Fourney, Gonzalo Ramos, Ahmed Awadallah
NAACL 2021 | June 2021
Structure-Grounded Pretraining for Text-to-SQL
Xiang Deng, Ahmed Awadallah, Chris Meek, Alex Polozov, Huan Sun, Matthew Richardson
NAACL 2021 | June 2021
MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning
Mengzhou Xia, Guoqing Zheng, Subhabrata (Subho) Mukherjee, Milad Shokouhi, Graham Neubig, Ahmed Awadallah
NAACL 2021 | May 2021
SCoRe: Pre-Training for Context Representation in Conversational Semantic Parsing
Tao Yu, Rui Zhang, Alex Polozov, Chris Meek, Ahmed Awadallah
ICLR | May 2021
QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization
Ming Zhong, Da Yin, Tao Yu, Ahmad Zaidi, Mutethia Mutuma, Rahul Jha, Ahmed Awadallah, Asli Celikyilmaz, Yang Liu, Xipeng Qiu, Dragomir R. Radev
NAACL | April 2021
Sequence-level self-learning with multi-task learning framework
Kenichi Kumatani, Dimitrios Dimitriadis, Yashesh Gaur, Robert Gmyr, Sefik Emre Eskimez, Jinyu Li, Michael Zeng
October 2020
GAN-based Data Generation for Speech Emotion Recognition
Sefik Emre Eskimez, Dimitrios Dimitriadis, Robert Gmyr, Kenichi Kumatani
INTERSPEECH 2020 | October 2020
A Federated Approach in Training Acoustic Models
Dimitrios Dimitriadis, Kenichi Kumatani, Robert Gmyr, Yashesh Gaur, Sefik Emre Eskimez
INTERSPEECH 2020 | October 2020
-
Domain mismatch and data augmentation in speech emotion recognition
Dimitra Emmanouilidou, Hannes Gamper, Midia Yousefi
SMM24, Interspeech Workshop on Speech, Music and Mind 2024 | September 2024
Multi-View Learning for Speech Emotion Recognition
Daniel Tompkins, Dimitra Emmanouilidou, Soham Deshmukh, Benjamin Elizalde
International Conference on Acoustics, Speech and Signal Processing | June 2023
Investigations in Audio Captioning: Addressing Vocabulary Imbalance and Evaluating Suitability of Language-Centric Performance Metrics
Sandeep Kothinti, Dimitra Emmanouilidou
European Signal Processing Conference (EUSIPCO) | May 2023
Toxic Speech and Speech Emotions: Investigations of Audio-based Modeling and Intercorrelations
Wei-Cheng Lin, Dimitra Emmanouilidou
European Signal Processing Conference (EUSIPCO) | August 2022
A Review of Speaker Diarization: Recent Advances with Deep Learning
Tae Jin Park, Naoyuki Kanda, Dimitrios Dimitriadis, Kyu J. Han, Shinji Watanabe, Shrikanth Narayanan
Computer Speech & Language | November 2021, Vol 72
Ensemble Combination between Different Time Segmentations
Jeremy Wong, Dimitrios Dimitriadis, Kenichi Kumatani, Yashesh Gaur, George Polovets, Partha Parthasarathy, Eric Sun, Jinyu Li, Yifan Gong
2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) | June 2021
-
Orca-2: Teaching Small Language Models How to Reason
Arindam Mitra, Luciano Del Corro, Shweti Mahajan, Andres Codas, Clarisse Simoes Ribeiro, Sahaj Agrawal, Xuxi Chen, Anastasia Razdaibiedina, Erik Jones, Kriti Aggarwal, Hamid Palangi, Guoqing Zheng, Corby Rosset, Hamed Khanpour, Ahmed Awadallah
November 2023
Orca: Progressive Learning from Complex Explanation Traces of GPT-4
Subhabrata (Subho) Mukherjee, Arindam Mitra, Ganesh Jawahar, Sahaj Agarwal, Hamid Palangi, Ahmed Awadallah
arXiv: Computation and Language | June 2023
ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models
Binfeng Xu, Zhiyuan Peng, Bowen Lei, Subhabrata (Subho) Mukherjee, Yuchen Liu, Dongkuan Xu
arXiv: Computation and Language | May 2023
A Systematic Study of Knowledge Distillation for Natural Language Generation with Pseudo-Target Training
Nitay Calderon, Subhabrata (Subho) Mukherjee, Roi Reichart, Amir Kantor
ACL 2023 | May 2023
AutoMoE: Neural Architecture Search for Efficient Sparsely Activated Transformers
Ganesh Jawahar, Subhabrata (Subho) Mukherjee, Xiaodong Liu, Young Jin Kim, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan, Ahmed Awadallah, Sébastien Bubeck, Jianfeng Gao
ACL | May 2023
What do Compressed Large Language Models Forget? Robustness Challenges in Model Compression
Mengnan Du, Subhabrata (Subho) Mukherjee, Yu Cheng, Milad Shokouhi, Xia Hu, Ahmed Awadallah
EACL | April 2023
ADMoE: Anomaly Detection with Mixture-of-Experts from Noisy Labels
Yue Zhao, Guoqing Zheng, Subhabrata (Subho) Mukherjee, Robert McCann, Ahmed Awadallah
AAAI | January 2023
AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning
Yaqing Wang, Sahaj Agarwal, Subhabrata (Subho) Mukherjee, Xiaodong Liu, Jing Gao, Ahmed Awadallah, Jianfeng Gao
EMNLP | December 2022
UserIdentifier: Implicit User Representations for Simple and Effective Personalized Sentiment Analysis
Fatemehsadat Mireshghallah, Vaishnavi Shrivastava, Milad Shokouhi, Taylor Berg-Kirkpatrick, Robert Sim, Dimitrios Dimitriadis
2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL’22) | July 2022
Sparsely Activated Mixture-of-Experts are Robust Multi-Task Learners
Shashank Gupta, Subhabrata (Subho) Mukherjee, Krishan Subudhi, Eduardo Gonzalez, Damien Jose, Ahmed Awadallah, Jianfeng Gao
ArXiv | April 2022
Knowledge Infused Decoding
Ruibo Liu, Guoqing Zheng, Shashank Gupta, Radhika Gaonkar, Chongyang Gao, Soroush Vosoughi, Milad Shokouhi, Ahmed Awadallah
ICLR 2022 | April 2022
LiST: Lite Prompted Self-training Makes Parameter-efficient Few-shot Learners
Yaqing Wang, Subhabrata (Subho) Mukherjee, Xiaodong Liu, Jing Gao, Ahmed Awadallah, Jianfeng Gao
NAACL 2022 | April 2022
CLUES: Few-Shot Learning Evaluation in Natural Language Understanding
Subhabrata (Subho) Mukherjee, Xiaodong Liu, Guoqing Zheng, Saghar Hosseini, Hao Cheng, Greg Yang, Chris Meek, Ahmed Awadallah, Jianfeng Gao
NeurIPS 2021 | December 2021
A Review of Speaker Diarization: Recent Advances with Deep Learning
Tae Jin Park, Naoyuki Kanda, Dimitrios Dimitriadis, Kyu J. Han, Shinji Watanabe, Shrikanth Narayanan
Computer Speech & Language | November 2021, Vol 72
Say `YES’ to Positivity: Detecting Toxic Language in Workplace Communications
Meghana Moorthy Bhat, Saghar Hosseini, Ahmed Awadallah, Paul Bennett, Weisheng Li
EMNLP 2021 | November 2021
Self-training with Few-shot Rationalization: Teacher Explanations Aid Student in Few-shot NLU
Meghana Moorthy Bhat, Alessandro Sordoni, Subhabrata (Subho) Mukherjee
EMNLP 2021 | November 2021
Meta Self-training for Few-shot Neural Sequence Labeling
Yaqing Wang, Subhabrata (Subho) Mukherjee, Haoda Chu, Yuancheng Tu, Ming Wu, Jing Gao, Ahmed Awadallah
SIGKDD 2021 (Research Track) | August 2021
Ensemble Combination between Different Time Segmentations
Jeremy Wong, Dimitrios Dimitriadis, Kenichi Kumatani, Yashesh Gaur, George Polovets, Partha Parthasarathy, Eric Sun, Jinyu Li, Yifan Gong
2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) | June 2021
XtremeDistilTransformers: Task Transfer for Task-agnostic Distillation
Subhabrata (Subho) Mukherjee, Ahmed Awadallah, Jianfeng Gao
ArXiv | June 2021
arXiv:2106.04563
NL-EDIT: Correcting Semantic Parse Errors through Natural Language Interaction
Ahmed Elgohary, Chris Meek, Matthew Richardson, Adam Fourney, Gonzalo Ramos, Ahmed Awadallah
NAACL 2021 | June 2021
Structure-Grounded Pretraining for Text-to-SQL
Xiang Deng, Ahmed Awadallah, Chris Meek, Alex Polozov, Huan Sun, Matthew Richardson
NAACL 2021 | June 2021
Self-training with Weak Supervision
Giannis Karamanolakis, Subhabrata (Subho) Mukherjee, Guoqing Zheng, Ahmed Awadallah
NAACL 2021 | May 2021
MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning
Mengzhou Xia, Guoqing Zheng, Subhabrata (Subho) Mukherjee, Milad Shokouhi, Graham Neubig, Ahmed Awadallah
NAACL 2021 | May 2021
SCoRe: Pre-Training for Context Representation in Conversational Semantic Parsing
Tao Yu, Rui Zhang, Alex Polozov, Chris Meek, Ahmed Awadallah
ICLR | May 2021
QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization
Ming Zhong, Da Yin, Tao Yu, Ahmad Zaidi, Mutethia Mutuma, Rahul Jha, Ahmed Awadallah, Asli Celikyilmaz, Yang Liu, Xipeng Qiu, Dragomir R. Radev
NAACL | April 2021
-
Accelerating Dataset Distillation via Model Augmentation
Lei Zhang, Jie Zhang, Bowen Lei, Subhabrata (Subho) Mukherjee, Xiang Pan, Bo Zhao, Caiwen Ding, Yao Li, Dongkuan Xu
2023 Computer Vision and Pattern Recognition | March 2023
Highlight paper (2.5%)
-
Periodic motion-based visual stimulus
Andrew D. Wilson, Ivan Tashev, Hannes Gamper, Ed Cutrell, David Johnston, Dimitra Emmanouilidou
MSR-TR-2022-37 | November 2022
Published by Microsoft
US-20220365599-A1
Heterogeneous Ensemble Knowledge Transfer for Training Large Models in Federated Learning
Yae Jee Cho, Andre Manoel, Gauri Joshi, Robert Sim, Dimitrios Dimitriadis
IJCAI-ECAI’22 | August 2022
Tackling Dynamics in Federated Incremental Learning with Variational Embedding Rehearsal
Tae Jin Park, Kenichi Kumatani, Dimitrios Dimitriadis
October 2021
Sequence-level self-learning with multi-task learning framework
Kenichi Kumatani, Dimitrios Dimitriadis, Yashesh Gaur, Robert Gmyr, Sefik Emre Eskimez, Jinyu Li, Michael Zeng
October 2020
-
Imagining future digital assistants at work: A study of task management needs
Yonchanok Khaokaew, Indigo Holcombe-James, Mohammad Saiedur Rahaman, Jonathan Liono, Johanne R. Trippas, Damiano Spina, Peter Bailey, Nicholas J. Belkin, Paul Bennett, Yongli Ren, Mark Sanderson, Falk Scholer, Ryen W. White, Flora D. Salim
International Journal of Human-Computer Studies | December 2022, Vol 168
Periodic motion-based visual stimulus
Andrew D. Wilson, Ivan Tashev, Hannes Gamper, Ed Cutrell, David Johnston, Dimitra Emmanouilidou
MSR-TR-2022-37 | November 2022
Published by Microsoft
US-20220365599-A1
Ensemble Combination between Different Time Segmentations
Jeremy Wong, Dimitrios Dimitriadis, Kenichi Kumatani, Yashesh Gaur, George Polovets, Partha Parthasarathy, Eric Sun, Jinyu Li, Yifan Gong
2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) | June 2021
Sequence-level self-learning with multi-task learning framework
Kenichi Kumatani, Dimitrios Dimitriadis, Yashesh Gaur, Robert Gmyr, Sefik Emre Eskimez, Jinyu Li, Michael Zeng
October 2020
GAN-based Data Generation for Speech Emotion Recognition
Sefik Emre Eskimez, Dimitrios Dimitriadis, Robert Gmyr, Kenichi Kumatani
INTERSPEECH 2020 | October 2020
A Federated Approach in Training Acoustic Models
Dimitrios Dimitriadis, Kenichi Kumatani, Robert Gmyr, Yashesh Gaur, Sefik Emre Eskimez
INTERSPEECH 2020 | October 2020
-
Population-scale dietary interests during the COVID-19 pandemic.
Kristina Gligoric, Arnaud Chiolero, Emre Kiciman, Ryen W. White, Robert West
Nature Communications | February 2022, Vol 13(1073)
Meta Self-training for Few-shot Neural Sequence Labeling
Yaqing Wang, Subhabrata (Subho) Mukherjee, Haoda Chu, Yuancheng Tu, Ming Wu, Jing Gao, Ahmed Awadallah
SIGKDD 2021 (Research Track) | August 2021
Intelligent Task Recognition: Towards Enabling Productivity Assistance in Daily Life
Jonathan Liono, Mohammad Saiedur Rahaman, Flora D Salim, Yongli Ren, Damiano Spina, Falk Scholer, Johanne R Trippas, Mark Sanderson, Ryen W. White, Paul Bennett
2020 International Conference on Multimedia Retrieval | June 2020
-
Privacy Leakage in Text Classification: A Data Extraction Approach
Adel Elmahdy, Huseyin Inan, Robert Sim
June 2022
FLUTE: A Scalable, Extensible Framework for High-Performance Federated Learning Simulations
Dimitrios Dimitriadis, Mirian Hipolito Garcia, Daniel Madrigal, Andre Manoel, Robert Sim
March 2022
-
Population-scale dietary interests during the COVID-19 pandemic.
Kristina Gligoric, Arnaud Chiolero, Emre Kiciman, Ryen W. White, Robert West
Nature Communications | February 2022, Vol 13(1073)
-
A Federated Approach in Training Acoustic Models
Dimitrios Dimitriadis, Kenichi Kumatani, Robert Gmyr, Yashesh Gaur, Sefik Emre Eskimez
INTERSPEECH 2020 | October 2020
Publications by Type
-
Domain mismatch and data augmentation in speech emotion recognition
Dimitra Emmanouilidou, Hannes Gamper, Midia Yousefi
SMM24, Interspeech Workshop on Speech, Music and Mind 2024 | September 2024
Learning Safety Constraints from Demonstrations with Unknown Rewards
David Lindner, Xin Chen, Sebastian Tschiatschek, Katja Hofmann, Andreas Krause
International Conference on Artificial Intelligence and Statistics | April 2024
Comparing the Efficacy of Fine-Tuning and Meta-Learning for Few-Shot Policy Imitation
Massimiliano Patacchiola, Mingfei Sun, Katja Hofmann, Richard E Turner
Conference on Lifelong Learning Agents | November 2023
Multi-View Learning for Speech Emotion Recognition
Daniel Tompkins, Dimitra Emmanouilidou, Soham Deshmukh, Benjamin Elizalde
International Conference on Acoustics, Speech and Signal Processing | June 2023
A Systematic Study of Knowledge Distillation for Natural Language Generation with Pseudo-Target Training
Nitay Calderon, Subhabrata (Subho) Mukherjee, Roi Reichart, Amir Kantor
ACL 2023 | May 2023
Investigations in Audio Captioning: Addressing Vocabulary Imbalance and Evaluating Suitability of Language-Centric Performance Metrics
Sandeep Kothinti, Dimitra Emmanouilidou
European Signal Processing Conference (EUSIPCO) | May 2023
AutoMoE: Neural Architecture Search for Efficient Sparsely Activated Transformers
Ganesh Jawahar, Subhabrata (Subho) Mukherjee, Xiaodong Liu, Young Jin Kim, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan, Ahmed Awadallah, Sébastien Bubeck, Jianfeng Gao
ACL | May 2023
What do Compressed Large Language Models Forget? Robustness Challenges in Model Compression
Mengnan Du, Subhabrata (Subho) Mukherjee, Yu Cheng, Milad Shokouhi, Xia Hu, Ahmed Awadallah
EACL | April 2023
Accelerating Dataset Distillation via Model Augmentation
Lei Zhang, Jie Zhang, Bowen Lei, Subhabrata (Subho) Mukherjee, Xiang Pan, Bo Zhao, Caiwen Ding, Yao Li, Dongkuan Xu
2023 Computer Vision and Pattern Recognition | March 2023
Highlight paper (2.5%)
ADMoE: Anomaly Detection with Mixture-of-Experts from Noisy Labels
Yue Zhao, Guoqing Zheng, Subhabrata (Subho) Mukherjee, Robert McCann, Ahmed Awadallah
AAAI | January 2023
Boosting Natural Language Generation from Instructions with Meta-Learning
Budhaditya Deb, Guoqing Zheng, Ahmed Awadallah
EMNLP | December 2022
Toxic Speech and Speech Emotions: Investigations of Audio-based Modeling and Intercorrelations
Wei-Cheng Lin, Dimitra Emmanouilidou
European Signal Processing Conference (EUSIPCO) | August 2022
Heterogeneous Ensemble Knowledge Transfer for Training Large Models in Federated Learning
Yae Jee Cho, Andre Manoel, Gauri Joshi, Robert Sim, Dimitrios Dimitriadis
IJCAI-ECAI’22 | August 2022
UserIdentifier: Implicit User Representations for Simple and Effective Personalized Sentiment Analysis
Fatemehsadat Mireshghallah, Vaishnavi Shrivastava, Milad Shokouhi, Taylor Berg-Kirkpatrick, Robert Sim, Dimitrios Dimitriadis
2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL’22) | July 2022
Knowledge Infused Decoding
Ruibo Liu, Guoqing Zheng, Shashank Gupta, Radhika Gaonkar, Chongyang Gao, Soroush Vosoughi, Milad Shokouhi, Ahmed Awadallah
ICLR 2022 | April 2022
CLUES: Few-Shot Learning Evaluation in Natural Language Understanding
Subhabrata (Subho) Mukherjee, Xiaodong Liu, Guoqing Zheng, Saghar Hosseini, Hao Cheng, Greg Yang, Chris Meek, Ahmed Awadallah, Jianfeng Gao
NeurIPS 2021 | December 2021
Fairness via Representation Neutralization
Mengnan Du, Subhabrata (Subho) Mukherjee, Guanchu Wang, Ruixiang Tang, Ahmed Awadallah, Xia Hu
NeurIPS 2021 | December 2021
Say `YES’ to Positivity: Detecting Toxic Language in Workplace Communications
Meghana Moorthy Bhat, Saghar Hosseini, Ahmed Awadallah, Paul Bennett, Weisheng Li
EMNLP 2021 | November 2021
Self-training with Few-shot Rationalization: Teacher Explanations Aid Student in Few-shot NLU
Meghana Moorthy Bhat, Alessandro Sordoni, Subhabrata (Subho) Mukherjee
EMNLP 2021 | November 2021
Meta Self-training for Few-shot Neural Sequence Labeling
Yaqing Wang, Subhabrata (Subho) Mukherjee, Haoda Chu, Yuancheng Tu, Ming Wu, Jing Gao, Ahmed Awadallah
SIGKDD 2021 (Research Track) | August 2021
One-Shot Voice Conversion with Speaker-Agnostic StarGAN
Sefik Emre Eskimez, Dimitrios Dimitriadis, Kenichi Kumatani, Robert Gmyr
INTERSPEECH 2022 | August 2021
Ensemble Combination between Different Time Segmentations
Jeremy Wong, Dimitrios Dimitriadis, Kenichi Kumatani, Yashesh Gaur, George Polovets, Partha Parthasarathy, Eric Sun, Jinyu Li, Yifan Gong
2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) | June 2021
NL-EDIT: Correcting Semantic Parse Errors through Natural Language Interaction
Ahmed Elgohary, Chris Meek, Matthew Richardson, Adam Fourney, Gonzalo Ramos, Ahmed Awadallah
NAACL 2021 | June 2021
Structure-Grounded Pretraining for Text-to-SQL
Xiang Deng, Ahmed Awadallah, Chris Meek, Alex Polozov, Huan Sun, Matthew Richardson
NAACL 2021 | June 2021
Self-training with Weak Supervision
Giannis Karamanolakis, Subhabrata (Subho) Mukherjee, Guoqing Zheng, Ahmed Awadallah
NAACL 2021 | May 2021
MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning
Mengzhou Xia, Guoqing Zheng, Subhabrata (Subho) Mukherjee, Milad Shokouhi, Graham Neubig, Ahmed Awadallah
NAACL 2021 | May 2021
SCoRe: Pre-Training for Context Representation in Conversational Semantic Parsing
Tao Yu, Rui Zhang, Alex Polozov, Chris Meek, Ahmed Awadallah
ICLR | May 2021
QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization
Ming Zhong, Da Yin, Tao Yu, Ahmad Zaidi, Mutethia Mutuma, Rahul Jha, Ahmed Awadallah, Asli Celikyilmaz, Yang Liu, Xipeng Qiu, Dragomir R. Radev
NAACL | April 2021
GAN-based Data Generation for Speech Emotion Recognition
Sefik Emre Eskimez, Dimitrios Dimitriadis, Robert Gmyr, Kenichi Kumatani
INTERSPEECH 2020 | October 2020
A Federated Approach in Training Acoustic Models
Dimitrios Dimitriadis, Kenichi Kumatani, Robert Gmyr, Yashesh Gaur, Sefik Emre Eskimez
INTERSPEECH 2020 | October 2020
Intelligent Task Recognition: Towards Enabling Productivity Assistance in Daily Life
Jonathan Liono, Mohammad Saiedur Rahaman, Flora D Salim, Yongli Ren, Damiano Spina, Falk Scholer, Johanne R Trippas, Mark Sanderson, Ryen W. White, Paul Bennett
2020 International Conference on Multimedia Retrieval | June 2020
-
Scaling Laws for Pre-training Agents and World Models
Tim Pearce, Tabish Rashid, Dave Bignell, Raluca Stevenson, Sam Devlin, Katja Hofmann
November 2024
Sequence-level self-learning with multi-task learning framework
Kenichi Kumatani, Dimitrios Dimitriadis, Yashesh Gaur, Robert Gmyr, Sefik Emre Eskimez, Jinyu Li, Michael Zeng
October 2020
-
Toward Human-AI Alignment in Large-Scale Multi-Player Games
Sugandha Sharma, Guy Davidson, Khimya Khetarpal, Anssi Kanervisto, Udit Arora, Katja Hofmann, Ida Momennejad
arXiv:2402.03575 | February 2024
Published by Microsoft
Periodic motion-based visual stimulus
Andrew D. Wilson, Ivan Tashev, Hannes Gamper, Ed Cutrell, David Johnston, Dimitra Emmanouilidou
MSR-TR-2022-37 | November 2022
Published by Microsoft
US-20220365599-A1
-
Orca-2: Teaching Small Language Models How to Reason
Arindam Mitra, Luciano Del Corro, Shweti Mahajan, Andres Codas, Clarisse Simoes Ribeiro, Sahaj Agrawal, Xuxi Chen, Anastasia Razdaibiedina, Erik Jones, Kriti Aggarwal, Hamid Palangi, Guoqing Zheng, Corby Rosset, Hamed Khanpour, Ahmed Awadallah
November 2023
Privacy Leakage in Text Classification: A Data Extraction Approach
Adel Elmahdy, Huseyin Inan, Robert Sim
June 2022
FLUTE: A Scalable, Extensible Framework for High-Performance Federated Learning Simulations
Dimitrios Dimitriadis, Mirian Hipolito Garcia, Daniel Madrigal, Andre Manoel, Robert Sim
March 2022
Tackling Dynamics in Federated Incremental Learning with Variational Embedding Rehearsal
Tae Jin Park, Kenichi Kumatani, Dimitrios Dimitriadis
October 2021
-
Orca: Progressive Learning from Complex Explanation Traces of GPT-4
Subhabrata (Subho) Mukherjee, Arindam Mitra, Ganesh Jawahar, Sahaj Agarwal, Hamid Palangi, Ahmed Awadallah
arXiv: Computation and Language | June 2023
ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models
Binfeng Xu, Zhiyuan Peng, Bowen Lei, Subhabrata (Subho) Mukherjee, Yuchen Liu, Dongkuan Xu
arXiv: Computation and Language | May 2023
AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning
Yaqing Wang, Sahaj Agarwal, Subhabrata (Subho) Mukherjee, Xiaodong Liu, Jing Gao, Ahmed Awadallah, Jianfeng Gao
EMNLP | December 2022
Imagining future digital assistants at work: A study of task management needs
Yonchanok Khaokaew, Indigo Holcombe-James, Mohammad Saiedur Rahaman, Jonathan Liono, Johanne R. Trippas, Damiano Spina, Peter Bailey, Nicholas J. Belkin, Paul Bennett, Yongli Ren, Mark Sanderson, Falk Scholer, Ryen W. White, Flora D. Salim
International Journal of Human-Computer Studies | December 2022, Vol 168
Sparsely Activated Mixture-of-Experts are Robust Multi-Task Learners
Shashank Gupta, Subhabrata (Subho) Mukherjee, Krishan Subudhi, Eduardo Gonzalez, Damien Jose, Ahmed Awadallah, Jianfeng Gao
ArXiv | April 2022
LiST: Lite Prompted Self-training Makes Parameter-efficient Few-shot Learners
Yaqing Wang, Subhabrata (Subho) Mukherjee, Xiaodong Liu, Jing Gao, Ahmed Awadallah, Jianfeng Gao
NAACL 2022 | April 2022
Population-scale dietary interests during the COVID-19 pandemic.
Kristina Gligoric, Arnaud Chiolero, Emre Kiciman, Ryen W. White, Robert West
Nature Communications | February 2022, Vol 13(1073)
A Review of Speaker Diarization: Recent Advances with Deep Learning
Tae Jin Park, Naoyuki Kanda, Dimitrios Dimitriadis, Kyu J. Han, Shinji Watanabe, Shrikanth Narayanan
Computer Speech & Language | November 2021, Vol 72
XtremeDistilTransformers: Task Transfer for Task-agnostic Distillation
Subhabrata (Subho) Mukherjee, Ahmed Awadallah, Jianfeng Gao
ArXiv | June 2021
arXiv:2106.04563