Skip to content
View rohithpeddi's full-sized avatar

Highlights

  • Pro

Block or report rohithpeddi

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
rohithpeddi/README.md

👨‍💻 About Me

I am a Ph.D. student in Computer Science at the University of Texas at Dallas, under the guidance of Dr. Vibhav Gogate and Dr. Yu Xiang. Before starting my Ph.D., I earned my undergraduate degree from IIT Kharagpur and worked as an R&D Engineer at Next Education India Pvt Ltd. and ZeMoSo Labs Pvt Ltd.

🧩 Research Focus

My research focuses on developing algorithms that enable machines to understand human interactions in a data-efficient manner

  1. 🎥 Accurate Interpretation of Human Interactions
    By integrating multiple data modalities—vision, text, and audio—I aim to answer the what of observed interactions.

    • Tackling challenges in robust learning
    • Addressing issues in long-tailed recognition
  2. 🔮 Anticipation of Human Interactions
    Exploring the why behind actions to enhance AI systems' ability to anticipate future interactions.

    • Leveraging underlying priors for predictive AI behaviour
  3. 🤖 Transfer of Observed Interactions to Robots
    Adapting observed human interactions to specific robotic embodiments.

    • Enabling robots to interpret, understand, and replicate human interactions effectively

📚 Relevant Publications

🧠 Interpretation (Long-Tail Learning, Robust Learning)

(1) UAI 2022 , (2) NeurIPS 2024, Under review at (3) CVPR 2025 and (4) ACL 2025

🔗 Anticipation (Relational Anticipation)

(5) ECCV 2024 (Oral), Under review at (3) CVPR 2025 and (4) ACL 2025

🛠️ Transfer (Skill Learning)

(6) IROS 2024 (Oral), Under review at (7) RSS 2025


Feel free to reach out via mail if you share similar research interests or want to collaborate!

Pinned Loading

  1. SceneSayer SceneSayer Public

    [ECCV 2024 (Oral)] Towards Scene Graph Anticipation

    Python 13 1

  2. RobustTPMs RobustTPMs Public

    [UAI 2022] Robust learning of Tractable Probabilistic Models

    Python

  3. DroTPM DroTPM Public

    [TPM Workshop @ UAI 2022] Distributionally Robust Learning of Sum Product Networks

    Python

  4. UTD_CS UTD_CS Public

    UTD CS Courses and assignments

    HTML 6 11

  5. CaptainCook4D/CaptainCook4D CaptainCook4D/CaptainCook4D Public

    [NeurIPS 2024]

    8