Asli Celikyilmaz


Asli Celikyilmaz

Senior Staff Research Manager
Fundamentals AI Research (FAIR) @ Meta

Affiliate Professor @ University of Washington
email:asli.ca@live.com

Google Scholar

Talks
Research
Publications
Interns
Bio
Experience
Teaching
Awards
Service


Research Interests:


My primary research interests are in the fields of Artificial Intelligence, Natural Language Processing, Machine Learning, with broader interests in Human Computer Interaction. My research centers on building natural language agents enriched with advanced capabilities to memorize, learn and reason about social and physical world. Specifically, my research interests can be grouped into:
  • Neural Language Generation and Reasoning: My research focuses on building advanced natural language agents that can generate coherent and contextually relevant text, as well as ground language in multimodal knowledge such as images, videos, and spatial data. This includes modeling long-term context, tracking and simulating the world represented in stories or narratives, teaching agents to write coherently, and predicting mental states in narrative by stateful language modeling. It also involves learning semantic correspondences between language and multimodal knowledge for applications such as multimodal summarization, image captioning, and neuro-symbolic and logical reasoning.
  • Evaluation of Large Language Models: I aim to scrutinize the capabilities and limitations of LLMs, particularly their factual accuracy, semantic coherence, and transparency. To achieve this, I develop new evaluation metrics and methods that can precisely gauge the performance and potential bias inherent in LLMs. Additionally, I investigate the interpretability of these models by probing their internal mechanisms and decision-making processes.
  • World Models and Reasoning: My research centers on integrating diverse data modalities into language models to enhance their understanding and reasoning abilities. This includes imbuing multimodal LLMs with world modeling capabilities such that they can generate sequences of images/video/text that are physically and temporally consistent and have advanced multimodal reasoning systems.


Selected Invited Talks and Tutorials:




Recent Preprints:

Peer-Reviewed Publications:


Bio:

Asli Celikyilmaz is a Senior Research Manager at Fundmendals AI Research (FAIR). Formerly, she was Senior Principal Researcher at Microsoft Research (MSR) in Redmond, Washington. She is also an Affiliate Associate Member at the University of Washington. She has received Ph.D. Degree in Information Science from University of Toronto, Canada, and later continued her Postdoc study at Computer Science Department of the University of California, Berkeley. Her research interests are mainly in deep learning and natural language, specifically on language generation with long-term coherence, language understanding, language grounding with vision, and building intelligent agents for human-computer interaction She is serving on the editorial boards of Transactions of the ACL (TACL) as area editor and Open Journal of Signal Processing (OJSP) as Associate Editor. She has received several “best of” awards including NAFIPS 2007, Semantic Computing 2009, CVPR 2019, EMNLP 2023.

Work Experience:

    2021-Present Senior Research Manager, Fundamentals AI Research (FAIR) at META, Seattle, WA
    2018-Present Affiliate Professor at the Paul G. Allen School University of Washington, Seattle, WA
    2010-2021 Senior Principal Researcher, Microsoft Research, Redmond, WA
    2008-2010 Post-Doctorate Research, Computer Science, University of California, Berkeley, CA
    2005-2008 Doctor of Philosopy, Engineering, University of Toronto
    2003-2005 Master of applied Science, Engineering, University of Toronto

Teaching:

    2017 Lecture on Generative Adversarial Networks at the AI School at MSR AI
    2017 Lecture on Deep Learning for Interactive Systems at the AI School at MSR AI
    2007 Lecture on Knowledge Modeling and Management, Univ. of Toronto
    2006 Lecture on Data Modeling, University of Toronto
    2005 Lecture on Decision Analysis, University of Toronto

Honors and Awards:

    Ourtanding Paper Award, EMNLP 2023
    Best Student Paper Award, CVPR 2019
    Best Paper Award, IEEE Int. Conference on Semantic Computing, Berkeley, 2009
    Postdoctoral Fellowship from British Telecom University of California, Berkeley, 2008-2010
    NSERC (Natural Sci. and Eng. Research Council of Canada), Postdoc Fellowship (PDF), 2008-2010
    NSERC (Natural Sci. and Eng. Research Council, Graduate Scholarships), PGSD2, 2007-2009
    OGS-Ontario Graduate Scholarships in Science and Technology, Ph.D., 2007-2008
    Ph.D. Fellowship, University of Toronto, 2005-2008

Service


    Organizing workshop at at ICML 2021 on Self-Supervised Learning for Reasoning and Perception
    Organizing workshop at Nerual Conversational AI at ICLR 2021 on safety, integrity, continual learning, and so much more!
    Panel Chair for IEEE SLT 2021
    Organized ALVR2020: Advances in Language and Vision Research Workshop at ACL 2020
    Organized NLP4CONVAI: NLP for Conversational AI Workshop at ACL 2020
    Organized 3rd Conversational AI Workshop at NeurIPS 2019
    Organized Neuralgen Workshop at NAACL 2019
    Other academic service:
        EMNLP 2022 Workshop Co-Chair
        ACL 2022 Senoir Area Chair of Generation Track
        SIGDIAL 2021 Senoir Area Chair
        ACL 2021 Area Chair for Dialog Track
        NAACL 2021 Senior Area Chair for Generation Track
        ACL 2020 Demo Chair
        Associate Editor for IEEE ODSP,
        Area Editor for Transactions of ACL (TACL),
        Editor for AI Magazine: AAAI Special Issue on Conversational AI,
        PC member for ACL, EMNLP, NAACL, NIPS, CoNLL, ConvAI.