MixQuant: Adaptive Mixed-Precision Quantization for Large Language Models.

Ashitabh Misra

Ashitabh Misra Madhav Agrawal Arham Jain Tarek F. Abdelzaher MixQuant: Adaptive Mixed-Precision Quantization for Large Language Models. 2026 July abs/2607.23047 CoRR https://doi.org/10.48550/arXiv.2607.23047 db/journals/corr/corr2607.html#abs-2607-23047 streams/journals/corr

Tarek F. Abdelzaher Yigong Hu Denizhan Kara Tomoyoshi Kimura Ashitabh Misra Vishakha Ramani Olivier Tardieu Tianshi Wang 0002 Maggie B. Wigness Alaa Youssef The bottlenecks of AI: challenges for embedded and real-time research in a data-centric age. 185-236 2025 June 61 Real Time Syst. 2 https://doi.org/10.1007/s11241-025-09452-w db/journals/rts/rts61.html#AbdelzaherHKKMRTWWY25 streams/journals/rts

Jinyang Li 0004 Herman Wu Hongjue Zhao Tomoyoshi Kimura Denizhan Kara Tianshi Wang 0002 Yizhuo Chen Tianchen Wang Yigong Hu Ashitabh Misra Tarek F. Abdelzaher Agentic LLM-Assisted Edge AI for CPS/IoT Applications. 371-380 2025 CogMI https://doi.org/10.1109/CogMI67134.2025.00049 conf/cogmi/2025 db/conf/cogmi/cogmi2025.html#LiWZKKWCWHMA25 Ashitabh Misra Nurani Saoda Tarek F. Abdelzaher Latency-Constrained Input-Aware Quantization of Time Series Inference Workflows at the Edge. 1-10 2025 INFOCOM https://doi.org/10.1109/INFOCOM55648.2025.11044709 conf/infocom/2025 db/conf/infocom/infocom2025.html#MisraSA25 Tomoyoshi Kimura Ashitabh Misra Yizhuo Chen Denizhan Kara Jinyang Li 0004 Tianshi Wang 0002 Ruijie Wang 0004 Joydeep Bhattacharyya Jae Kim Prashant J. Shenoy Mani Srivastava 0001 Maggie B. Wigness Tarek F. Abdelzaher The Case for Micro Foundation Models to Support Robust Edge Intelligence. 23-31 2024 CogMI https://doi.org/10.1109/CogMI62246.2024.00014 conf/cogmi/2024 db/conf/cogmi/cogmi2024.html#KimuraMCKLWWBKSSWA24 streams/conf/cogmi

Nilesh Rajendra Shah Ashitabh Misra Antoine Miné Rakesh Venkat Ramakrishna Upadrasta BullsEye : Scalable and Accurate Approximation Framework for Cache Miss Calculation. 2:1-2:28 2023 March 20 ACM Trans. Archit. Code Optim. 1 https://doi.org/10.1145/3558003 db/journals/taco/taco20.html#ShahMMVU23

Ashitabh Misra Jacob Laurel Sasa Misailovic ViX: Analysis-driven Compiler for Efficient Low-Precision Variational Inference. 1-6 2023 DATE https://doi.org/10.23919/DATE56975.2023.10137324 conf/date/2023 db/conf/date/date2023.html#MisraLM23 Rishi Ranjan Singh Amit Kumar Dhar Arzad Alam Kherani Naveen Varghese Jacob Ashitabh Misra Devansh Bajpai Network Based Framework to Compare Vaccination Strategies. 218-230 2021 CSoNet https://doi.org/10.1007/978-3-030-91434-9_20 conf/csonet/2021 db/conf/csonet/csonet2021.html#SinghDKJMB21 Tarek F. Abdelzaher Madhav Agrawal Devansh Bajpai Joydeep Bhattacharyya Yizhuo Chen Amit Kumar Dhar Yigong Hu Naveen Varghese Jacob Arham Jain Denizhan Kara Arzad Alam Kherani Jae Kim Tomoyoshi Kimura Jacob Laurel Jinyang Li 0004 Antoine Miné Sasa Misailovic Vishakha Ramani Nurani Saoda Nilesh Rajendra Shah Prashant J. Shenoy Rishi Ranjan Singh Mani Srivastava 0001 Olivier Tardieu Ramakrishna Upadrasta Rakesh Venkat Ruijie Wang 0004 Tianchen Wang Tianshi Wang 0002 Maggie B. Wigness Herman Wu Alaa Youssef Hongjue Zhao