Urmish Thakker

46 papers A* 2Journal 33Unranked 11

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Cross-Family Speculative Prefill: Training-Free Long-Context Compression with Small Draft Models. CoRR Shubhangi Upasani, Ravi Shanker Raju, Bo Li, Mengmeng Ji, John Long, Chen Wu, Urmish Thakker, Guangtao Wang
2026	J	`jnl`	Test-Time Adaptation via Many-Shot Prompting: Benefits, Limits, and Pitfalls. CoRR Shubhangi Upasani, Chen Wu, Jay Rainton, Bo Li, Urmish Thakker, Changran Hu, Qizheng Zhang
2026	J	`jnl`	The Limits of Long-Context Reasoning in Automated Bug Fixing. CoRR Ravi Raju, Mengmeng Ji, Shubhangi Upasani, Bo Li, Urmish Thakker
2025	J	`jnl`	Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models. CoRR Qizheng Zhang, Changran Hu, Shubhangi Upasani, Boyuan Ma, Fenglu Hong, Vamsidhar Kamanuru, Jay Rainton, Chen Wu, Mengmeng Ji, Hanchen Li, Urmish Thakker, James Zou, Kunle Olukotun
2025	J	`jnl`	Distributed LLMs and Multimodal Large Language Models: A Survey on Advances, Challenges, and Future Directions. CoRR M. Hadi Amini, Md. Jueal Mia, Yasaman Saadati, Ahmed Imteaj, Seyedsina Nabavirazavi, Urmish Thakker, Md. Zarif Hossain, Awal Ahmed Fime, S. S. Iyengar
2025	J	`jnl`	LLMs Know What to Drop: Self-Attention Guided KV Cache Eviction for Efficient Long-Context Inference. CoRR Guangtao Wang, Shubhangi Upasani, Chen Wu, Darshan Gandhi, Jonathan Li, Changran Hu, Bo Li, Urmish Thakker
2025	J	`jnl`	SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators. CoRR Jonathan Li, Nasim Farahini, Evgenii Iuliugin, Magnus Vesterlund, Christian Häggström, Guangtao Wang, Shubhangi Upasani, Ayush Sachdeva, Rui Li, Faline Fu, Chen Wu, Ayesha Siddiqua, John Long, Tuowen Zhao, Matheen Musaddiq, Håkan Zeffer, Yun Du, Mingran Wang, Qinghua Li, Bo Li, Urmish Thakker, Raghu Prabhakar
2025	J	`jnl`	Synthetic Document Question Answering in Hungarian. CoRR Jonathan Li, Zoltan Csaki, Nidhi Hiremath, Etash Kumar Guha, Fenglu Hong, Edward Ma, Urmish Thakker
2025	J	`jnl`	Training Domain Draft Models for Speculative Decoding: Best Practices and Insights. CoRR Fenglu Hong, Ravi Raju, Jonathan Lingjie Li, Bo Li, Urmish Thakker, Avinash Ravichandran, Swayambhoo Jain, Changran Hu
2024	J	`jnl`	Composition of Experts on the SN40L Reconfigurable Dataflow Unit. IEEE Micro Raghu Prabhakar, Ram Sivaramakrishnan, Darshan Gandhi, Yun Du, Mingran Wang, Xiangyu Song, Kejie Zhang, Tianren Gao, Angela Wang, Xiaoyan Li, Joshua Brot, Calvin Leung, Tuowen Zhao, Mark Gottscho, Zhengyu Chen, Kaizhao Liang, Swayambhoo Jain, Urmish Thakker, Kevin J. Brown, Kunle Olukotun
2024	J	`jnl`	Constructing Domain-Specific Evaluation Sets for LLM-as-a-judge. CoRR Ravi Raju, Swayambhoo Jain, Bo Li, Jonathan Li, Urmish Thakker
2024	J	`jnl`	SambaLingo: Teaching Large Language Models New Languages. CoRR Zoltan Csaki, Bo Li, Jonathan Li, Qiantong Xu, Pian Pawakapan, Leon Zhang, Yun Du, Hengyu Zhao, Changran Hu, Urmish Thakker
2024	A*	`conf`	SambaNova SN40L: Scaling the AI Memory Wall with Dataflow and Composition of Experts. MICRO Raghu Prabhakar, Ram Sivaramakrishnan, Darshan Gandhi, Yun Du, Mingran Wang, Xiangyu Song, Kejie Zhang, Tianren Gao, Angela Wang, Xiaoyan Li, Yongning Sheng, Joshua Brot, Denis Sokolov, Apurv Vivek, Calvin Leung, Arjun Sabnis, Jiayu Bai, Tuowen Zhao, Mark Gottscho, David Jackson, Mark Luttrell, Manish K. Shah, Zhengyu Chen, Kaizhao Liang, Swayambhoo Jain, Urmish Thakker, Dawei Huang, Sumti Jairath, Kevin J. Brown, Kunle Olukotun
2024	J	`jnl`	SambaNova SN40L: Scaling the AI Memory Wall with Dataflow and Composition of Experts. CoRR Raghu Prabhakar, Ram Sivaramakrishnan, Darshan Gandhi, Yun Du, Mingran Wang, Xiangyu Song, Kejie Zhang, Tianren Gao, Angela Wang, Karen Li, Yongning Sheng, Joshua Brot, Denis Sokolov, Apurv Vivek, Calvin Leung, Arjun Sabnis, Jiayu Bai, Tuowen Zhao, Mark Gottscho, David Jackson, Mark Luttrell, Manish K. Shah, Edison Chen, Kaizhao Liang, Swayambhoo Jain, Urmish Thakker, Dawei Huang, Sumti Jairath, Kevin J. Brown, Kunle Olukotun
2024	J	`jnl`	SubgoalXL: Subgoal-based Expert Learning for Theorem Proving. CoRR Xueliang Zhao, Lin Zheng, Haige Bo, Changran Hu, Urmish Thakker, Lingpeng Kong
2023	J	`jnl`	Efficiently Adapting Pretrained Language Models To New Languages. CoRR Zoltan Csaki, Pian Pawakapan, Urmish Thakker, Qiantong Xu
2023	J	`jnl`	Training Large Language Models Efficiently with Sparsity and Dataflow. CoRR Venkat Srinivasan, Darshan Gandhi, Urmish Thakker, Raghu Prabhakar
2022	J	`jnl`	A Survey on Federated Learning for Resource-Constrained IoT Devices. IEEE Internet Things J. Ahmed Imteaj, Urmish Thakker, Shiqiang Wang, Jian Li, M. Hadi Amini
2022	A*	`conf`	Multitask Prompted Training Enables Zero-Shot Task Generalization. ICLR Victor Sanh, Albert Webson, Colin Raffel, Stephen H. Bach, Lintang Sutawika, Zaid Alyafeai, Antoine Chaffin, Arnaud Stiegler, Arun Raja, Manan Dey, M Saiful Bari, Canwen Xu, Urmish Thakker, Shanya Sharma Sharma, Eliza Szczechla, Taewoon Kim, Gunjan Chhablani, Nihal V. Nayak, Debajyoti Datta, Jonathan Chang, Mike Tian-Jian Jiang, Han Wang, Matteo Manica, Sheng Shen, Zheng Xin Yong, Harshit Pandey, Rachel Bawden, Thomas Wang, Trishala Neeraj, Jos Rozen, Abheesht Sharma, Andrea Santilli, Thibault Févry, Jason Alan Fries, Ryan Teehan, Teven Le Scao, Stella Biderman, Leo Gao, Thomas Wolf, Alexander M. Rush
2022	—	`conf`	PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts. ACL (demo) Stephen H. Bach, Victor Sanh, Zheng Xin Yong, Albert Webson, Colin Raffel, Nihal V. Nayak, Abheesht Sharma, Taewoon Kim, M. Saiful Bari, Thibault Févry, Zaid Alyafeai, Manan Dey, Andrea Santilli, Zhiqing Sun, Srulik Ben-David, Canwen Xu, Gunjan Chhablani, Han Wang, Jason Alan Fries, Maged Saeed AlShaibani, Shanya Sharma, Urmish Thakker, Khalid Almubarak, Xiangru Tang, Dragomir R. Radev, Mike Tian-Jian Jiang, Alexander M. Rush
2022	J	`jnl`	PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts. CoRR Stephen H. Bach, Victor Sanh, Zheng Xin Yong, Albert Webson, Colin Raffel, Nihal V. Nayak, Abheesht Sharma, Taewoon Kim, M. Saiful Bari, Thibault Févry, Zaid Alyafeai, Manan Dey, Andrea Santilli, Zhiqing Sun, Srulik Ben-David, Canwen Xu, Gunjan Chhablani, Han Wang, Jason Alan Fries, Maged Saeed AlShaibani, Shanya Sharma, Urmish Thakker, Khalid Almubarak, Xiangru Tang, Mike Tian-Jian Jiang, Alexander M. Rush
2021	J	`jnl`	Compressing RNNs to Kilobyte Budget for IoT Devices Using Kronecker Products. ACM J. Emerg. Technol. Comput. Syst. Urmish Thakker, Igor Fedorov, Chu Zhou, Dibakar Gope, Matthew Mattina, Ganesh Dasika, Jesse G. Beu
2021	—	`conf`	Doping: A technique for Extreme Compression of LSTM Models using Sparse Structured Additive Matrices. MLSys Urmish Thakker, Paul N. Whatmough, Zhi Gang Liu, Matthew Mattina, Jesse G. Beu
2021	J	`jnl`	Doping: A technique for efficient compression of LSTM models using sparse structured additive matrices. CoRR Urmish Thakker, Paul N. Whatmough, Zhi Gang Liu, Matthew Mattina, Jesse G. Beu
2021	—	`conf`	MLPerf Tiny Benchmark. NeurIPS Datasets and Benchmarks Colby R. Banbury, Vijay Janapa Reddi, Peter Torelli, Nat Jeffries, Csaba Király, Jeremy Holleman, Pietro Montino, David Kanter, Pete Warden, Danilo Pau, Urmish Thakker, Antonio Torrini, Jay Cordaro, Giuseppe Di Guglielmo, Javier M. Duarte, Honson Tran, Nhan Tran, Wenxu Niu, Xuesong Xu
2021	J	`jnl`	MLPerf Tiny Benchmark. CoRR Colby R. Banbury, Vijay Janapa Reddi, Peter Torelli, Jeremy Holleman, Nat Jeffries, Csaba Király, Pietro Montino, David Kanter, Sebastian Ahmed, Danilo Pau, Urmish Thakker, Antonio Torrini, Pete Warden, Jay Cordaro, Giuseppe Di Guglielmo, Javier M. Duarte, Stephen Gibellini, Videet Parekh, Honson Tran, Nhan Tran, Wenxu Niu, Xuesong Xu
2021	—	`conf`	MicroNets: Neural Network Architectures for Deploying TinyML Applications on Commodity Microcontrollers. MLSys Colby R. Banbury, Chuteng Zhou, Igor Fedorov, Ramon Matas Navarro, Urmish Thakker, Dibakar Gope, Vijay Janapa Reddi, Matthew Mattina, Paul N. Whatmough
2021	J	`jnl`	Multitask Prompted Training Enables Zero-Shot Task Generalization. CoRR Victor Sanh, Albert Webson, Colin Raffel, Stephen H. Bach, Lintang Sutawika, Zaid Alyafeai, Antoine Chaffin, Arnaud Stiegler, Teven Le Scao, Arun Raja, Manan Dey, M. Saiful Bari, Canwen Xu, Urmish Thakker, Shanya Sharma, Eliza Szczechla, Taewoon Kim, Gunjan Chhablani, Nihal V. Nayak, Debajyoti Datta, Jonathan Chang, Mike Tian-Jian Jiang, Han Wang, Matteo Manica, Sheng Shen, Zheng Xin Yong, Harshit Pandey, Rachel Bawden, Thomas Wang, Trishala Neeraj, Jos Rozen, Abheesht Sharma, Andrea Santilli, Thibault Févry, Jason Alan Fries, Ryan Teehan, Stella Biderman, Leo Gao, Tali Bers, Thomas Wolf, Alexander M. Rush
2020	J	`jnl`	Benchmarking TinyML Systems: Challenges and Direction. CoRR Colby R. Banbury, Vijay Janapa Reddi, Max Lam, William Fu, Amin Fazel, Jeremy Holleman, Xinyuan Huang, Robert Hurtado, David Kanter, Anton Lokhmotov, David A. Patterson, Danilo Pau, Jae-sun Seo, Jeff Sieracki, Urmish Thakker, Marian Verhelst, Poonam Yadav
2020	J	`jnl`	Compressing Language Models using Doped Kronecker Products. CoRR Urmish Thakker, Paul N. Whatmough, Matthew Mattina, Jesse G. Beu
2020	J	`jnl`	Federated Learning for Resource-Constrained IoT Devices: Panoramas and State-of-the-art. CoRR Ahmed Imteaj, Urmish Thakker, Shiqiang Wang, Jian Li, M. Hadi Amini
2020	J	`jnl`	MicroNets: Neural Network Architectures for Deploying TinyML Applications on Commodity Microcontrollers. CoRR Colby R. Banbury, Chuteng Zhou, Igor Fedorov, Ramon Matas Navarro, Urmish Thakker, Dibakar Gope, Vijay Janapa Reddi, Matthew Mattina, Paul N. Whatmough
2020	—	`conf`	Pushing the Envelope of Dynamic Spatial Gating technologies. AIChallengeIoT@SenSys Xueqin Huang, Urmish Thakker, Dibakar Gope, Jesse G. Beu
2020	—	`conf`	Rank and run-time aware compression of NLP Applications. SustaiNLP@EMNLP Urmish Thakker, Jesse G. Beu, Dibakar Gope, Ganesh Dasika, Matthew Mattina
2020	J	`jnl`	Rank and run-time aware compression of NLP Applications. CoRR Urmish Thakker, Jesse G. Beu, Dibakar Gope, Ganesh Dasika, Matthew Mattina
2020	—	`conf`	Ternary MobileNets via Per-Layer Hybrid Filter Banks. CVPR Workshops Dibakar Gope, Jesse G. Beu, Urmish Thakker, Matthew Mattina
2020	—	`conf`	Understanding the Impact of Dynamic Channel Pruning on Conditionally Parameterized Convolutions. AIChallengeIoT@SenSys Ravi Raju, Dibakar Gope, Urmish Thakker, Jesse G. Beu
2019	J	`jnl`	A Static Analysis-based Cross-Architecture Performance Prediction Using Machine Learning. CoRR Newsha Ardalani, Urmish Thakker, Aws Albarghouthi, Karu Sankaralingam
2019	J	`jnl`	Compressing RNNs for IoT devices by 15-38x using Kronecker Products. CoRR Urmish Thakker, Jesse G. Beu, Dibakar Gope, Chu Zhou, Igor Fedorov, Ganesh Dasika, Matthew Mattina
2019	J	`jnl`	Measuring scheduling efficiency of RNNs for NLP applications. CoRR Urmish Thakker, Ganesh Dasika, Jesse G. Beu, Matthew Mattina
2019	—	`conf`	Pushing the limits of RNN Compression. EMC2@NeurIPS Urmish Thakker, Igor Fedorov, Jesse G. Beu, Dibakar Gope, Chu Zhou, Ganesh Dasika, Matthew Mattina
2019	J	`jnl`	Pushing the limits of RNN Compression. CoRR Urmish Thakker, Igor Fedorov, Jesse G. Beu, Dibakar Gope, Chu Zhou, Ganesh Dasika, Matthew Mattina
2019	—	`conf`	Run-Time Efficient RNN Compression for Inference on Edge Devices. EMC2@HPCA/CVPR/ISCA Urmish Thakker, Jesse G. Beu, Dibakar Gope, Ganesh Dasika, Matthew Mattina
2019	J	`jnl`	Run-Time Efficient RNN Compression for Inference on Edge Devices. CoRR Urmish Thakker, Jesse G. Beu, Dibakar Gope, Ganesh Dasika, Matthew Mattina
2019	—	`conf`	Skipping RNN State Updates without Retraining the Original Model. SenSys-ML Jin Tao, Urmish Thakker, Ganesh Dasika, Jesse G. Beu
2019	J	`jnl`	Ternary MobileNets via Per-Layer Hybrid Filter Banks. CoRR Dibakar Gope, Jesse G. Beu, Urmish Thakker, Matthew Mattina