Education

• UC Berkeley — M.S. EECS, GPA 4.0/4.0; Advisor: Kurt Keutzer
• UC Berkeley — Honors B.S. EECS; Honors B.A. Mathematics; Phi Beta Kappa

Research Interests

Efficient Machine Learning; Large-scale ML Systems; Optimization Models; Natural Language Processing.

Publications

Key Publications

Squeeze Evolve: Unified Multi-Model Orchestration for Verifier-Free Evolution
Monishwaran Maheswaran*, Leon Lakhani*, Zhongzhu Zhou†, Shijia Yang†, Junxiong Wang, Coleman Hooper, Yuezhou Hu, Rishabh Tiwari, Jue Wang, Harman Singh, Qingyang Wu, Yuqing Jian, Ce Zhang, Kurt Keutzer, Tri Dao, Xiaoxia Wu, Ben Athiwaratkun, James Zou‡, Chenfeng Xu*‡
*Equal contribution  †Equal second  ‡Co-advising
Preprint 2026
project page arXiv code

Residual Context Diffusion: Unleashing the Potential of Diffusion LLMs via Residual Denoising
Yuezhou Hu*, Harman Singh*, Monishwaran Maheswaran*, Haocheng Xi, Coleman Hooper, Jintao Zhang, Aditya Tomar, Michael W. Mahoney, Sewon Min, Mehrdad Farajtabar, Kurt Keutzer, Amir Gholami†, Chenfeng Xu†
*Equal contribution  †Equal advising
Preprint 2026
project page arXiv code models

EvoX: Meta-Evolution for Automated Discovery
Shu Liu*, Shubham Agarwal*, Monishwaran Maheswaran, Mert Cemri, Zhifei Li, Qiuyang Mang, Ashwin Naren, Ethan Boneh, Audrey Cheng, Melissa Z. Pan, Alexander Du, Kurt Keutzer, Alexandros G. Dimakis, Koushik Sen, Matei Zaharia, Ion Stoica
*Equal contribution
Preprint 2026
arXiv blog code

Arbitrage: Efficient Reasoning via Advantage-Aware Speculation
Monishwaran Maheswaran*, Rishabh Tiwari*, Yuezhou Hu*, Kerem Dilmen, Coleman Hooper, Haocheng Xi, Nicholas Lee, Mehrdad Farajtabar, Michael W. Mahoney, Kurt Keutzer, Amir Gholami
*Equal contribution
Preprint 2025
project page arXiv code

TASER: Translation Assessment via Systematic Evaluation and Reasoning
Monishwaran Maheswaran, Marco Carini, Christian Federmann, Tony Diaz
WMT @ EMNLP 2025 (Apple internship work) • 🏆 Winner of WMT 2025 Shared Metrics Task (SoTA 2025)
arXiv Apple MLR

Other Publications

V1: Unifying Generation and Self-Verification for Parallel Reasoners
Harman Singh*, Xiuyu Li*, Kusha Sareen, Monishwaran Maheswaran, Sijun Tan, Xiaoxia Wu, Junxiong Wang, Alpay Ariyak, Qingyang Wu, Samir Khaki, Rishabh Tiwari, Long Lian, Yucheng Lu, Boyi Li, Alane Suhr, Ben Athiwaratkun, Kurt Keutzer
*Equal contribution
Preprint 2026
project page arXiv code

Reward Under Attack: Analyzing the Robustness and Hackability of Process Reward Models
Rishabh Tiwari*, Aditya Tomar*, Udbhav Bamba*, Monishwaran Maheswaran, Heng Yang, Michael W. Mahoney, Kurt Keutzer, Amir Gholami
*Equal contribution
Preprint 2026
arXiv code

ETS: Efficient Tree Search for Inference-Time Scaling
Coleman Hooper, Sehoon Kim, Suhong Moon, Kerem Dilmen, Monishwaran Maheswaran, Nicholas Lee, Michael W. Mahoney, Sophia Shao, Kurt Keutzer, Amir Gholami
Preprint 2025
arXiv

Squeezed Attention: Accelerating Long-Context LLM Inference
Coleman Hooper*, Sehoon Kim*, Hiva Mohammadzadeh, Monishwaran Maheswaran, June Paik, Michael W. Mahoney, Kurt Keutzer, Amir Gholami
*Equal contribution
Main Track @ ACL 2025
arXiv code

Summation Identities
Monishwaran Maheswaran, Oliver Knill
Harvard University Mathematics Department, 2017
paper

Undergraduate Thesis

Scaling Laws and Training Dynamics in Extremely Wide Neural Networks — UC Berkeley. Empirical and theoretical analysis of loss landscapes, minima distribution, and weight evolution in wide networks. Supervisors: Prof. Federico Pasqualotto (Mathematics).

Awards

• 2023 — Phi Beta Kappa
  For academic excellence in a broad array of undergraduate courses in the liberal arts and sciences. Top 1/10th of UC Berkeley graduates campus wide in terms of GPA.
• 2022 — Texas Instruments–UC Berkeley Class Design Contest Award
  For efficient design of new high performance hardware systems for signal processing, custom manufactured and assembled for an ASIC project funded by EECS Department.
• 2022 — Tau Beta Pi National Engineering Honor Society
  For outstanding performance in Engineering. Top 1/8th of UC Berkeley College of Engineering in terms of GPA.
• 2021 — IEEE-Eta Kappa Nu National Electrical Engineering Honor Society (HKN)
  For outstanding performance in EECS. Top 1/4th of UC Berkeley EECS students in terms of GPA.
• 2019 — INK Fellowship
  INK identifies and nurtures 20 young achievers worldwide who are passionate to redefine the fields they are in.

Invited Talks & Interviews

• 2024 — CDAO | The West Coast Data & Analytics Event (San Francisco)
• 2024 — RE.WORK | AI in Finance Summit (New York)
• 2020 — Engineering-Mind Podcast: Making Machines Feel
• 2019 — GITEX: Technology, Humans, Evolution: What Is the Future of Humankind?
• 2019 — INK Keynote: Generating Expeditious Solutions for Pressing Problems
• 2019 — Rise of AI Berlin: Deep Learning To Save Lives
• 2019 — TEDx SereneMeadows: Curbing Suicides Using Machines
• 2019 — TEDx BMSCE: The Neural Connect
• 2019 — TEDx IIITA: Deep Learning and Healthcare
• 2019 — TEDx LakhotaLake: Saving Lives Through AI
• 2019 — Moin Zukunft! — Der Podcast vom Du Unternehmer-Magazin
• 2019 — Platform Tech Podcast

Beyond Research

• Besides my academic work, I love to teach. I share my projects and knowledge through numerous international keynotes and TEDx talks.
• Out of pure interest, I spend time analyzing the works of Friedrich Nietzsche, Ludwig Wittgenstein, and Bertrand Russell.
• I love endurance sports: I run ultramarathons, surf in San Francisco, and used to row at the California Lightweight Rowing Club at UC Berkeley.