Hi! I am Manan, a Visiting Researcher at Microsoft Research, working on safe agentic reasoning for Vision-Language-Action (VLA) models under Dr. Akshay Nambi. My research focuses on building trustworthy and safe AI for autonomous physical systems, spanning foundational models for Physical AI, agentic AI, offline reinforcement learning, and generative policy synthesis. I am broadly interested in developing principled methods that bring together learning and formal safety guarantees, ensuring that intelligent agents can operate reliably in the real world.

I recently completed my PhD at the Centre for Cyber Physical Systems, Indian Institute of Science (IISc) Bangalore, where I worked on Safe Robot Learning in the Stochastic Robotics Lab under Prof. Shishir N. Y. Kolathaya and Prof. Pushpak Jagtap. Prior to that, I completed my B.Tech from Indian Institute of Technology Bombay (IITB) in 2021.

I also frequently collaborate with Prof. Somil Bansal’s SIA Lab at Stanford University and Prof. Rahul Mangharam’s xLab at University of Pennsylvania.

Before joining Microsoft Research, I spent time at Fujitsu Research (NextGenAI Lab) improving VLA model inference under Dr. Manu Kaul. I have also worked as a Research Consultant at ARTPARK and as a Student Researcher at Washington University in St. Louis under Prof. Andrew Clark.

Click here for my detailed CV .

Follow me on Google Scholar, X (earlier twitter) and LinkedIn to keep informed with my latest research and projects.

News

Mar 28, 2026 Our paper V-OCBF: Learning Safety Filters from Offline Data via Value-Guided Offline Control Barrier Functions has been accepted to Transactions on Machine Learning Research (TMLR)! :tada: Check out the project page.
Jan 29, 2026 Our paper A Collision Cone Approach for Control Barrier Functions has been accepted to IEEE Transactions on Control Systems Technology (TCST)! :tada: Check out the project page.
Jan 16, 2026 Our paper On Convergence of Adam with Data Dependent Stepsize has been accepted to IEEE Transactions on Artificial Intelligence (TAI)! :tada:
Jan 01, 2026 Thrilled to join Microsoft Research India as a Visiting Researcher, working on Safe Agentic Reasoning for Vision-Language-Action (VLA) models! :rocket:
Oct 15, 2025 Excited to join Fujitsu Research as a Research Intern at the NextGenAI Lab in Bengaluru, working on Vision-Language-Action (VLA) models! :rocket:

Selected Publications

  1. TMLR
    v-ocbf.jpg
    V-OCBF: Learning Safety Filters from Offline Data via Value-Guided Offline Control Barrier Functions
    Mumuksh Tayal*, Manan Tayal*, Aditya Singh, Shishir Kolathaya, and Ravi Prakash
    Transactions on Machine Learning Research (TMLR), 2026
    Also accepted at AAAI Workshop on Deployable AI (DAI) 2026 (Oral)
    arXiv Bib Code Website
  2. ICML
    piml-soc.jpg
    A Physics-Informed Machine Learning Framework for Safe and Optimal Control of Autonomous Systems
    Manan Tayal*, Aditya Singh*, Shishir Kolathaya, and Somil Bansal
    In International Conference on Machine Learning (ICML), 2025
    arXiv Bib Code Website
  3. CDC
    cdc2024.gif
    Learning a Formally Verified Control Barrier Function in Stochastic Environment
    Manan Tayal, Hongchao Zhang, Pushpak Jagtap, Andrew Clark, and Shishir Kolathaya
    In 2024 IEEE 63rd Conference on Decision and Control (CDC), 2024
    DOI arXiv Bib Code
  4. ACC
    c3bf_uav.jpg
    Control Barrier Functions in Dynamic UAVs for Kinematic Obstacle Avoidance: A Collision Cone Approach
    Manan Tayal, Rajpal Singh, Jishnu Keshavan, and Shishir Kolathaya
    In 2024 American Control Conference (ACC), 2024
    DOI arXiv Bib Website