Somshubra Majumdar

53 papers A* 2A 5B 2C 1Misc 4Journal 34Unranked 5

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Learning Generative Selection for Best-of-N. CoRR Shubham Toshniwal, Aleksander Ficek, Siddhartha Jain, Wei Du, Vahid Noroozi, Sadegh Mahdavi, Somshubra Majumdar, Igor Gitman
2025	J	`jnl`	From Output to Evaluation: Does Raw Instruction-Tuned Code LLMs Output Suffice for Fill-in-the-Middle Code Generation? CoRR Wasi Uddin Ahmad, Somshubra Majumdar, Boris Ginsburg
2025	—	`conf`	Genetic Instruct: Scaling up Synthetic Generation of Coding Instructions for Large Language Models. ACL (6) Somshubra Majumdar, Vahid Noroozi, Mehrzad Samadi, Sean Narenthiran, Aleksander Ficek, Wasi Uddin Ahmad, Jocelyn Huang, Jagadeesh Balam, Boris Ginsburg
2025	J	`jnl`	Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluation. CoRR Vaibhav Srivastav, Steven Zheng, Eric Bezzam, Eustache Le Bihan, Nithin Rao Koluguri, Piotr Zelasko, Somshubra Majumdar, Adel Moumen, Sanchit Gandhi
2025	J	`jnl`	OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs. CoRR Wasi Uddin Ahmad, Aleksander Ficek, Mehrzad Samadi, Jocelyn Huang, Vahid Noroozi, Somshubra Majumdar, Boris Ginsburg
2025	J	`jnl`	OpenCodeReasoning-II: A Simple Test Time Scaling Approach via Self-Critique. CoRR Wasi Uddin Ahmad, Somshubra Majumdar, Aleksander Ficek, Sean Narenthiran, Mehrzad Samadi, Jocelyn Huang, Siddhartha Jain, Vahid Noroozi, Boris Ginsburg
2025	J	`jnl`	OpenCodeReasoning: Advancing Data Distillation for Competitive Coding. CoRR Wasi Uddin Ahmad, Sean Narenthiran, Somshubra Majumdar, Aleksander Ficek, Siddhartha Jain, Jocelyn Huang, Vahid Noroozi, Boris Ginsburg
2025	J	`jnl`	SWAN-GPT: An Efficient and Scalable Approach for Long-Context Language Modeling. CoRR Krishna C. Puvvada, Faisal Ladhak, Santiago Akle Serrano, Cheng-Ping Hsieh, Shantanu Acharya, Somshubra Majumdar, Fei Jia, Samuel Kriman, Simeng Sun, Dima Rekesh, Boris Ginsburg
2025	A*	`conf`	SWAN: An Efficient and Scalable Approach for Long-Context Language Modeling. EMNLP Krishna C. Puvvada, Faisal Ladhak, Santiago Akle Serano, Cheng-Ping Hsieh, Shantanu Acharya, Somshubra Majumdar, Fei Jia, Samuel Kriman, Simeng Sun, Dima Rekesh, Boris Ginsburg
2025	J	`jnl`	Scaling Test-Time Compute to Achieve IOI Gold Medal with Open-Weight Models. CoRR Mehrzad Samadi, Aleksander Ficek, Sean Narenthiran, Siddhartha Jain, Wasi Uddin Ahmad, Somshubra Majumdar, Vahid Noroozi, Boris Ginsburg
2025	J	`jnl`	Scoring Verifiers: Evaluating Synthetic Verification in Code and Reasoning. CoRR Aleksander Ficek, Somshubra Majumdar, Vahid Noroozi, Boris Ginsburg
2024	J	`jnl`	Genetic Instruct: Scaling up Synthetic Generation of Coding Instructions for Large Language Models. CoRR Somshubra Majumdar, Vahid Noroozi, Sean Narenthiran, Aleksander Ficek, Jagadeesh Balam, Boris Ginsburg
2024	A	`conf`	Instruction Data Generation and Unsupervised Adaptation for Speech Language Models. INTERSPEECH Vahid Noroozi, Zhehuai Chen, Somshubra Majumdar, Steve Huang, Jagadeesh Balam, Boris Ginsburg
2024	J	`jnl`	Instruction Data Generation and Unsupervised Adaptation for Speech Language Models. CoRR Vahid Noroozi, Zhehuai Chen, Somshubra Majumdar, Steve Huang, Jagadeesh Balam, Boris Ginsburg
2024	Misc	`conf`	Investigating End-to-End ASR Architectures for Long Form Audio Transcription. ICASSP Nithin Rao Koluguri, Samuel Kriman, Georgy Zelenfroind, Somshubra Majumdar, Dima Rekesh, Vahid Noroozi, Jagadeesh Balam, Boris Ginsburg
2024	A	`conf`	Less is More: Accurate Speech Recognition & Translation without Web-Scale Data. INTERSPEECH Krishna C. Puvvada, Piotr Zelasko, He Huang, Oleksii Hrinchuk, Nithin Rao Koluguri, Kunal Dhawan, Somshubra Majumdar, Elena Rastorgueva, Zhehuai Chen, Vitaly Lavrukhin, Jagadeesh Balam, Boris Ginsburg
2024	J	`jnl`	Less is More: Accurate Speech Recognition & Translation without Web-Scale Data. CoRR Krishna C. Puvvada, Piotr Zelasko, He Huang, Oleksii Hrinchuk, Nithin Rao Koluguri, Kunal Dhawan, Somshubra Majumdar, Elena Rastorgueva, Zhehuai Chen, Vitaly Lavrukhin, Jagadeesh Balam, Boris Ginsburg
2024	—	`conf`	Resource-Efficient Adaptation of Speech Foundation Models for Multi-Speaker ASR. SLT Weiqing Wang, Kunal Dhawan, Taejin Park, Krishna C. Puvvada, Ivan Medennikov, Somshubra Majumdar, He Huang, Jagadeesh Balam, Boris Ginsburg
2024	J	`jnl`	Resource-Efficient Adaptation of Speech Foundation Models for Multi-Speaker ASR. CoRR Weiqing Wang, Kunal Dhawan, Taejin Park, Krishna C. Puvvada, Ivan Medennikov, Somshubra Majumdar, He Huang, Jagadeesh Balam, Boris Ginsburg
2024	Misc	`conf`	Stateful Conformer with Cache-Based Inference for Streaming Automatic Speech Recognition. ICASSP Vahid Noroozi, Somshubra Majumdar, Ankur Kumar, Jagadeesh Balam, Boris Ginsburg
2023	A*	`conf`	Efficient Sequence Transduction by Jointly Predicting Tokens and Durations. ICML Hainan Xu, Fei Jia, Somshubra Majumdar, He Huang, Shinji Watanabe, Boris Ginsburg
2023	J	`jnl`	Efficient Sequence Transduction by Jointly Predicting Tokens and Durations. CoRR Hainan Xu, Fei Jia, Somshubra Majumdar, He Huang, Shinji Watanabe, Boris Ginsburg
2023	C	`conf`	Fast Conformer With Linearly Scalable Attention For Efficient Speech Recognition. ASRU Dima Rekesh, Nithin Rao Koluguri, Samuel Kriman, Somshubra Majumdar, Vahid Noroozi, He Huang, Oleksii Hrinchuk, Krishna C. Puvvada, Ankur Kumar, Jagadeesh Balam, Boris Ginsburg
2023	J	`jnl`	Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition. CoRR Dima Rekesh, Samuel Kriman, Somshubra Majumdar, Vahid Noroozi, He Huang, Oleksii Hrinchuk, Ankur Kumar, Boris Ginsburg
2023	J	`jnl`	Investigating End-to-End ASR Architectures for Long Form Audio Transcription. CoRR Nithin Rao Koluguri, Samuel Kriman, Georgy Zelenfroind, Somshubra Majumdar, Dima Rekesh, Vahid Noroozi, Jagadeesh Balam, Boris Ginsburg
2023	Misc	`conf`	Multi-Blank Transducers for Speech Recognition. ICASSP Hainan Xu, Fei Jia, Somshubra Majumdar, Shinji Watanabe, Boris Ginsburg
2023	J	`jnl`	Stateful Conformer with Cache-based Inference for Streaming Automatic Speech Recognition. CoRR Vahid Noroozi, Somshubra Majumdar, Ankur Kumar, Jagadeesh Balam, Boris Ginsburg
2022	A	`conf`	CTC Variations Through New WFST Topologies. INTERSPEECH Aleksandr Laptev, Somshubra Majumdar, Boris Ginsburg
2022	—	`conf`	Damage Control During Domain Adaptation for Transducer Based Automatic Speech Recognition. SLT Somshubra Majumdar, Shantanu Acharya, Vitaly Lavrukhin, Boris Ginsburg
2022	J	`jnl`	Damage Control During Domain Adaptation for Transducer Based Automatic Speech Recognition. CoRR Somshubra Majumdar, Shantanu Acharya, Vitaly Lavrukhin, Boris Ginsburg
2022	J	`jnl`	Multi-blank Transducers for Speech Recognition. CoRR Hainan Xu, Fei Jia, Somshubra Majumdar, Shinji Watanabe, Boris Ginsburg
2022	—	`conf`	NVIDIA NeMo Offline Speech Translation Systems for IWSLT 2022. IWSLT@ACL Oleksii Hrinchuk, Vahid Noroozi, Ashwinkumar Ganesan, Sarah Campbell, Sandeep Subramanian, Somshubra Majumdar, Oleksii Kuchaiev
2021	J	`jnl`	Adversarial Attacks on Time Series. IEEE Trans. Pattern Anal. Mach. Intell. Fazle Karim, Somshubra Majumdar, Houshang Darabi
2021	J	`jnl`	CTC Variations Through New WFST Topologies. CoRR Aleksandr Laptev, Somshubra Majumdar, Boris Ginsburg
2021	J	`jnl`	CarneliNet: Neural Mixture Model for Automatic Speech Recognition. CoRR Aleksei Kalinov, Somshubra Majumdar, Jagadeesh Balam, Boris Ginsburg
2021	Misc	`conf`	MarbleNet: Deep 1D Time-Channel Separable Convolutional Neural Network for Voice Activity Detection. ICASSP Fei Jia, Somshubra Majumdar, Boris Ginsburg
2021	A	`conf`	SPGISpeech: 5, 000 Hours of Transcribed Financial Audio for Fully Formatted End-to-End Speech Recognition. Interspeech Patrick K. O'Neill, Vitaly Lavrukhin, Somshubra Majumdar, Vahid Noroozi, Yuekai Zhang, Oleksii Kuchaiev, Jagadeesh Balam, Yuliya Dovzhenko, Keenan Freyberg, Michael D. Shulman, Boris Ginsburg, Shinji Watanabe, Georg Kucsko
2021	J	`jnl`	SPGISpeech: 5, 000 hours of transcribed financial audio for fully formatted end-to-end speech recognition. CoRR Patrick K. O'Neill, Vitaly Lavrukhin, Somshubra Majumdar, Vahid Noroozi, Yuekai Zhang, Oleksii Kuchaiev, Jagadeesh Balam, Yuliya Dovzhenko, Keenan Freyberg, Michael D. Shulman, Boris Ginsburg, Shinji Watanabe, Georg Kucsko
2020	J	`jnl`	MarbleNet: Deep 1D Time-Channel Separable Convolutional Neural Network for Voice Activity Detection. CoRR Fei Jia, Somshubra Majumdar, Boris Ginsburg
2020	A	`conf`	MatchboxNet: 1D Time-Channel Separable Convolutional Neural Network Architecture for Speech Commands Recognition. INTERSPEECH Somshubra Majumdar, Boris Ginsburg
2019	J	`jnl`	Adversarial Attacks on Time Series. CoRR Fazle Karim, Somshubra Majumdar, Houshang Darabi
2019	J	`jnl`	Insights Into LSTM Fully Convolutional Networks for Time Series Classification. IEEE Access Fazle Karim, Somshubra Majumdar, Houshang Darabi
2019	J	`jnl`	Insights into LSTM Fully Convolutional Networks for Time Series Classification. CoRR Fazle Karim, Somshubra Majumdar, Houshang Darabi
2019	J	`jnl`	Multivariate LSTM-FCNs for time series classification. Neural Networks Fazle Karim, Somshubra Majumdar, Houshang Darabi, Samuel Harford
2018	J	`jnl`	A Comprehensive Comparison between Neural Style Transfer and Universal Style Transfer. CoRR Somshubra Majumdar, Amlaan Bhoi, Ganesh Jagadeesan
2018	B	`conf`	Exudate segmentation using fully convolutional neural networks and inception modules. Image Processing Piotr Chudzik, Somshubra Majumdar, Francesco Calivá, Bashir Al-Diri, Andrew Hunter
2018	J	`jnl`	LSTM Fully Convolutional Networks for Time Series Classification. IEEE Access Fazle Karim, Somshubra Majumdar, Houshang Darabi, Shun Chen
2018	B	`conf`	Microaneurysm detection using deep learning and interleaved freezing. Image Processing Piotr Chudzik, Somshubra Majumdar, Francesco Calivá, Bashir Al-Diri, Andrew Hunter
2018	J	`jnl`	Microaneurysm detection using fully convolutional neural networks. Comput. Methods Programs Biomed. Piotr Chudzik, Somshubra Majumdar, Francesco Calivá, Bashir Al-Diri, Andrew Hunter
2018	J	`jnl`	Multivariate LSTM-FCNs for Time Series Classification. CoRR Fazle Karim, Somshubra Majumdar, Houshang Darabi, Samuel Harford
2018	—	`conf`	Pathological Voice Classification Using Mel-Cepstrum Vectors and Support Vector Machine. IEEE BigData Maryam Pishgar, Fazle Karim, Somshubra Majumdar, Houshang Darabi
2018	J	`jnl`	Pathological Voice Classification Using Mel-Cepstrum Vectors and Support Vector Machine. CoRR Maryam Pishgar, Fazle Karim, Somshubra Majumdar, Houshang Darabi
2017	J	`jnl`	LSTM Fully Convolutional Networks for Time Series Classification. CoRR Fazle Karim, Somshubra Majumdar, Houshang Darabi, Shun Chen