Sudarshan Harithas

Dept. of Computer Science Brown University.

Sudarshan Harithas in a research laboratory

Email | Google Scholar
CV | GitHub

Follow @sudarshan_s_h

I’m a fourth-year Ph.D. candidate in the Department of Computer Science at Brown University, advised by Prof. Srinath Sridhar. Previously, I graduated from the International Institute of Information Technology Hyderabad (IIIT-H) with an MS in Computer Science, where I worked with Prof. K Madhava Krishna.

My research focuses on enabling general-purpose robots to acquire interaction-rich motor behaviors for diverse tasks in the physical world. I study generative models and physics-aware policy learning to develop robust, adaptable skills across multiple embodiments. I intend to build scalable robot learning systems that integrate perception and physical interaction dynamics to enable whole-body humanoid control and dexterous manipulation, allowing robots to reliably perform complex tasks in unstructured real-world environments.

News

Oct 2026 Introducing BRACE!
Aug 2026 I’m co-organizing the NeuRo-SymBolic World Models (RoBoWoMo) workshop, bringing together neural and symbolic perspectives on world models for robotics.
Jun 2026 DreamControl-v2 accepted at IROS 2026! See you all in Pittsburgh!
Jun 2026 Started my summer internship at Multiply Labs.
Sep/Dec 2025 Introducing DreamControl/v2, scalable generative priors for whole-body humanoid interaction tasks.
Older news (6)
Jun 2025 Started a summer internship at General Robotics, working on humanoid robots.
Apr 2025 Recognized as a Outstanding Reviewer for CVPR2025 .
Jan 2025 MotionGlot is Accepted at ICRA 2025.
Aug 2023 Started my PhD at Brown CS after graduating from IIIT-H with an MS in CS.
Aug 2023 Our work FinderNet is accepted at WACV2024 in the first round
Jul 2022 Stated with the SGI program organized by MIT

Selected publications

View all publications →

  1. brace-video-teaser-4s-17s.gif
    BRACE: Adapting Whole-Body References for Force and Terrain Aware Humanoid Motion Tracking
    Sudarshan Harithas, Chen Yu, Juan Borbon, Shubhankar Mondal, Winston Zha, Srinath Sridhar, Dingqi Zhang, and Jiuguang Wang
    arXiv preprint arXiv:2610.07052, 2026
    Under review
    HTML PDF Code Live demo
  2. dreamcontrol_v2.png
    DreamControl-v2: Simpler and Scalable Autonomous Humanoid Skills via Trainable Guided Diffusion Priors.
    Sudarshan S. Harithas, Sangkyung Kwak, Pushkal Katara, Srujan Deolasee, Dvij Kalaria, Srinath Sridhar, Sai Vemprala, Ashish Kapoor, and Jonathan Chung-Kuan Huang.
    In IROS 2026
    HTML PDF
  3. dream_control.gif
    DreamControl: Human-Inspired Whole-Body Humanoid Control for Scene Interaction via Guided Diffusion
    Dvij Kalaria, Sudarshan S. Harithas, Pushkal Katara, Sangkyung Kwak, Sarthak Bhagat, Shankar Sastry, Srinath Sridhar, Sai H. Vemprala, Ashish Kapoor, and Jonathan Chung-Kuan Huang
    In ICRA 2026
    Oral presentation
    HTML PDF
  4. motionglot.gif
    MotionGlot: A multi embodied Motion Generator.
    Sudarshan S Harithas, and Srinath Sridhar
    In ICRA 2025,
    Accepted at X-Embodiment Workshop CORL 2024
    HTML PDF Video Code Live demo
  5. SimulationUrbanFly.gif
    Urbanfly: Uncertainty-aware planning for navigation amongst high-rises with monocular visual-inertial slam maps
    Sudarshan S Harithas, Ayyappa Swamy Thatavarthy, Gurkirat Singh, Arun K Singh, and K Madhava Krishna
    In 2023 American Control Conference (ACC)
    HTML PDF Video
  6. simulation.gif
    Cco-voxel: Chance constrained optimization over uncertain voxel-grid representation for safe trajectory planning
    Sudarshan S Harithas, Rishabh Dev Yadav, Deepak Singh, Arun Kumar Singh, and K Madhava Krishna
    In 2022 International Conference on Robotics and Automation (ICRA)
    HTML PDF Video
  7. ldc.gif
    FinderNet: A Data Augmentation Free Canonicalization aided Loop Detection and Closure technique for Point clouds in 6-DOF separation.
    Sudarshan S Harithas, Gurkirat Singh, Aneesh Chavan, Sarthak Sharma, Suraj Patni, Chetan Arora, and Madhava Krishna
    In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2024
    Round 1 acceptance
    PDF Video

Awards and grants

  • June 2025
    NVIDIA Academic Grant Program

    “Large Action Models: A Cross-Embodied Model for Dexterous Manipulation.” Co-written with Srinath Sridhar and Tao Lu.

  • May 2025
    Outstanding Reviewer, CVPR 2025
  • April 2025
    Doctoral Consortium, ICRA 2025 Oral Highlight
  • 2021–2023
    Research Fellowship, IIIT Hyderabad
  • March 2022
    IEEE RAS Travel Grant, ICRA 2022

Press

MotionGlot

Invited talks

  • October 2026
    BRACE: Adapting Whole-Body References for Force and Terrain Aware Humanoid Motion Tracking

    Invited talk · General Robotics

    Project page
  • April 2025
    Large Action Models: Towards Building a Foundation Model for Cross-Embodied Action Generation

    Invited talk · Robotics and AI Institute (RAI)

Service

Reviewing

  • Conferences: CoRL, ICRA, IROS, CVPR, and ECCV.
  • Journal: IEEE Robotics and Automation Letters (RA-L).

Admissions

  • January 2026
    CS Ph.D. Application Reader

    Brown University

Brown University Multiply Labs General Robotics IIIT Hyderabad