Explore the lab's research areas, with related people and publications.

Language Models and NLP

Large-scale language modeling, reasoning, evaluation, and reliable deployment.

llm nlp reasoning evaluation prompting

People

  • Prof. Chris Pal (Principal Investigator)
  • Gaurav Sahu (Postdoc)
  • Matthew Wiens (PhD)
  • Chris Emezue (PhD)
  • Aristides Milios (PhD)

Publications

  • ReviewerToo: Should AI Join The Program Committee? A Look At The Future of Peer Review (2025)
  • LitLLMs, LLMs for Literature Review: Are we there yet? (2025)
  • Self-evaluation and self-prompting to improve the reliability of LLMs (2024)
  • Llms can learn self-restraint through iterative self-reflection (2024)
  • Generative Floor Plan Design with LLMs via Reinforcement Learning with Verifiable Rewards

Browse all people · Browse all publications

Vision and Generative Modeling

Computer vision, image/video generation, and visual representation learning.

vision generative-modeling video graphics

People

  • Prof. Chris Pal (Principal Investigator)
  • Florian Golemo (Postdoc)
  • Mattie Tesfaldet (PhD)
  • Juan Rodriguez (PhD)
  • Olga Luo (PhD)
  • Michelle Lin (MSc)
  • Hugo Baudchon (MSc)
  • Joanna Wolski (Collaborator)

Publications

  • Unsupervised depth estimation, 3d face rotation and replacement (2018)
  • Deep Convolutional Networks with Non-convolutional Recurrent Memory for Structured Prediction (2017)
  • Convolutional residual memory networks (2016)
  • Generative Floor Plan Design with LLMs via Reinforcement Learning with Verifiable Rewards

Browse all people · Browse all publications

Multimodal and Embodied AI

Methods combining modalities with interaction, perception, and action.

multimodal embodied-ai navigation

People

  • Prof. Chris Pal (Principal Investigator)
  • Florian Golemo (Postdoc)
  • Mattie Tesfaldet (PhD)
  • Juan Rodriguez (PhD)
  • Joel Ruben Antony Moniz (PhD)
  • Joanna Wolski (Collaborator)
  • Can (Sam) Chen (Collaborator)

Publications

  • No publication matches found yet.

Browse all people · Browse all publications

Robustness, Safety, and Trustworthy AI

Reliable and interpretable ML systems with strong safety and robustness properties.

safety robustness trustworthy-ai introspection

People

  • Prof. Chris Pal (Principal Investigator)
  • Chris Emezue (PhD)
  • Aristides Milios (PhD)

Publications

  • Self-evaluation and self-prompting to improve the reliability of LLMs (2024)
  • Llms can learn self-restraint through iterative self-reflection (2024)

Browse all people · Browse all publications

Scientific and Agentic AI

AI systems for discovery, scientific workflows, and autonomous research support.

scientific-ai agentic-ai literature-review reinforcement-learning

People

  • Prof. Chris Pal (Principal Investigator)
  • Gaurav Sahu (Postdoc)
  • Martin Weiss (Postdoc)
  • Chris Emezue (PhD)
  • Can (Sam) Chen (Collaborator)

Publications

  • ReviewerToo: Should AI Join The Program Committee? A Look At The Future of Peer Review (2025)
  • LitLLMs, LLMs for Literature Review: Are we there yet? (2025)
  • AInstein: Assessing the Feasibility of AI-Generated Approaches to Research Problems (2025)
  • Generative Floor Plan Design with LLMs via Reinforcement Learning with Verifiable Rewards

Browse all people · Browse all publications

Applied ML for Environment, Health, and Accessibility

High-impact applications in environmental monitoring, computational pathology, and assistive technology.

environment health accessibility smart-cities

People

  • Florian Golemo (Postdoc)
  • Michelle Lin (MSc)
  • Hugo Baudchon (MSc)
  • Yousef Kotp (MSc)
  • Joanna Wolski (Collaborator)
  • Mai Ababneh (Collaborator)

Publications

  • Generative Floor Plan Design with LLMs via Reinforcement Learning with Verifiable Rewards

Browse all people · Browse all publications