Subramanian "Subbu" Chidambaram

Currently in Sunnyvale, CA

Hello! I’m Subbu, a researcher specializing in the intersection of Human-Computer Interaction (HCI) and Artificial Intelligence (AI). As an Applied scientist, I work on advancements in intelligent user interface frameworks for AI applications. My current work focuses on AI Agents, Evaluation for AI Agents, Synthetic Data Generation, Model Steerability, and Human-AI Agent interactions. I leverage my background in HCI to enhance data annotation processes for machine learning model development.

As part of Amazon Web Services’ Bedrock AgentCore organization, I develop foundational primitives for the agent stack — connectivity, evaluation, and simulation — that let agents be deployed at scale with measurable reliability. My most recent work centers on Agent Evaluations, where I design evaluation methodologies and tooling for single- and multi-agent systems, shipped as part of AgentCore Evaluation service. I previously shipped capabilities for Amazon Bedrock AgentCore Gateway. I also contribute to AWS’s open-source agent ecosystem, including Strands Agents (AWS’s open-source agent framework)

I earned my Ph.D. from Purdue University’s C Design Lab, where I specialized in designing, developing, and evaluating novel 3D interfaces and interaction techniques to progress Extended Reality (XR) applications. I am deeply passionate about the potential of AI to transform human interactions with technology and its implications for our future. My aim is to integrate my expertise in HCI with my current research in AI to drive innovation and enrich everyday life.

My research has been published at premier venues for HCI research, including ACM CHI, CSCW, UIST, Ubicomp, DIS, and ISMAR.

Please reach out to me at subbu10123 [at] gmail.com if you find any of my work interesting. Thank you!

News

Aug 07, 2024	The AnnotateXR paper has been accepted and published in the ASME Journal of Computing and Information Science in Engineering (ASME JCISE).
Jul 24, 2024	The paper ‘Annorama: Enabling Immersive At-Desk Annotation Experiences in Virtual Reality with 3D Point Cloud Dioramas’ has been conditionally accepted to the ACM SUI 2024 conference. [Preprint available soon]
Dec 04, 2022	Started new position as PostDoctoral Scientist at AWS Science!

Selected Publications

AnnotateXR: An Extended Reality Workflow for Automating Data Annotation to Support Computer Vision Applications

Subramanian Chidambaram*, Rahul Jain*, Sai Swarup Reddy, and 2 more authors

Journal of Computing and Information Science in Engineering, Aug 2024

Abs PDF Video

Computer Vision (CV) algorithms require large annotated datasets that are often labor-intensive and expensive to create. We propose AnnotateXR, an extended reality (XR) workflow to collect various high fidelity data and auto-annotate it in a single demonstration. AnnotateXR allows users to align virtual models over physical objects, tracked with 6DoF sensors. AnnotateXR utilizes a hand tracking capable XR HMD coupled with 6DoF information and collision detection to enable algorithmic segmentation of different actions in videos through its digital twin. The virtual-physical mapping provides a tight bounding volume to generate semantic segmentation masks for the captured image data. Alongside supporting object and action segmentation, we also support other dimensions of annotation required by modern CV, such as Human-Object, Object-Object, and rich 3D recordings, all with a single demonstration. Our user study shows AnnotateXR produced over 112,000 annotated data points in 67 minutes.
EditAR: A Digital Twin Authoring Environment for Creation of AR/VR and Video Instructions from a Single Demonstration

Subramanian Chidambaram, Sai Swarup Reddy, Matthew Rumple, and 5 more authors

In 2022 IEEE International Symposium on Mixed and Augmented Reality (ISMAR) , Aug 2022

Abs PDF Video

Augmented/Virtual reality and video-based media play a vital role in the digital learning revolution to train novices in spatial tasks. However, creating content for these different media requires expertise in several fields. We present EditAR, a unified authoring, and editing environment to create content for AR, VR, and video based on a single demonstration. EditAR captures the user’s interaction within an environment and creates a digital twin, enabling users without programming backgrounds to develop content. We conducted formative interviews with both subject and media experts to design the system. The prototype was developed and reviewed by experts. We also performed a user study comparing traditional video creation with 2D video creation from 3D recordings, via a 3D editor, which uses freehand interaction for in-headset editing. Users took 5 times less time to record instructions and preferred EditAR, along with giving significantly higher usability scores.
ProcessAR: An augmented reality-based tool to create in-situ procedural 2D/3D AR Instructions

Subramanian Chidambaram, Hank Huang, Fengming He, and 5 more authors

In Proceedings of the 2021 ACM Designing Interactive Systems Conference , Virtual Event, USA, Aug 2021

Abs PDF Video

Augmented reality (AR) is an efficient form of delivering spatial information and has great potential for training workers. However, AR is still not widely used for such scenarios due to the technical skills and expertise required to create interactive AR content. We developed ProcessAR, an AR-based system to develop 2D/3D content that captures subject matter expert’s (SMEs) environment-object interactions in situ. The design space for ProcessAR was identified from formative interviews with AR programming experts and SMEs, alongside a comparative design study with SMEs and novice users. To enable smooth workflows, ProcessAR locates and identifies different tools/objects through computer vision within the workspace when the author looks at them. We explored additional features such as embedding 2D videos with detected objects and user-adaptive triggers. A final user evaluation comparing ProcessAR and a baseline AR authoring environment showed that, according to our qualitative questionnaire, users preferred ProcessAR.