Leena Mathur
Scholar

Leena Mathur

Google Scholar ID: loh93ZkAAAAJ
Carnegie Mellon University, School of Computer Science
machine learningnatural language processingcomputer visionmultimodal interaction
Citations & Impact
All-time
Citations
484
 
H-index
9
 
i10-index
9
 
Publications
18
 
Co-authors
11
list available
Resume (English only)
Academic Achievements
  • Papers published: 'Social Genome: Grounded Social Reasoning Abilities of Multimodal Models' accepted at EMNLP 2025; 'OpenFace 3.0: A Lightweight Multitask System for Comprehensive Facial Behavior Analysis' accepted at FG 2025; 'Advancing Social Intelligence in AI Agents: Technical Challenges and Open Questions' accepted at EMNLP 2024; 'HEMM: Holistic Evaluation of Multimodal Foundation Models' accepted at NeurIPS 2024; 'SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents' accepted at ICLR 2024; 'Expanding the Role of Affective Phenomena in Multimodal Interaction Research' accepted at ICMI 2023. Received the SoftBank Group-Arm Fellowship to support her PhD research.
Research Experience
  • Interned at Robust.AI where she worked on perception and human-robot interaction challenges for collaborative mobile robots. Worked with mentors including Maja Matarić at USC's Robotics and Autonomous Systems Center, Leila Takayama at Robust.AI, Khalil Iskarous from USC's Linguistics Department, Ralph Adolphs at Caltech, Michael Shindler at UC Irvine, and Rémi Lebret at EPFL.
Education
  • Works in the Language Technologies Institute (LTI) and Robotics, Embodied AI, and Learning Center (REAL) at CMU. Advised by Louis-Philippe Morency and Yonatan Bisk. PhD research supported by the NSF Graduate Research Fellowship and the SoftBank Group-Arm Fellowship. Earned an MS from CMU SCS/LTI and a BS in Computer Science, BA in Cognitive Science, and BA in Linguistics from the University of Southern California.
Background
  • PhD student at Carnegie Mellon University's School of Computer Science (SCS) and a Student Researcher at Google DeepMind. Her research focuses on foundations of multimodal intelligence, social intelligence, and embodied intelligence in AI systems interacting with humans in real-world contexts, with applications to support human health and well-being.
Miscellany
  • Led and grew the engineering school's student AI organization CAIS++ at USC, mentored by Bistra Dilkina from USC's Center for AI in Society. Now serves on the CAIS++ alumni advisory board.