Asli Celikyilmaz

Asli Celikyilmaz

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

Affiliate Professor @ University of Washington

Google Scholar


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:
  • Advanced Reasoning Architectures: My recent research aims to continuously innovate AI architectures to enhance their understanding, reasoning, and planning capabilities, striving to develop systems that can autonomously adapt to new environments and solve complex, real-world problems with minimal human intervention. This initiative will focus on creating more intuitive and human-like AI by integrating cognitive science principles and advanced computational techniques to improve decision-making processes. add agentic behaviors.
  • 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:

      Efficient Tool Use with Chain-of-Abstraction Reasoning
      Silin Gao, Jane Dwivedi-Yu, Ping Yu, Xiaoqing Ellen Tan, Ramakanth Pasunuru, Olga Golovneva, Koustuv Sinha, Asli Celikyilmaz, Antoine Bosselut, Tianlu Wang
      arxiv 2024

      An Introduction to Vision-Language Modeling
      Florian Bordes, Richard Yuanzhe Pang, Anurag Ajay, Alexander C. Li, Adrien Bardes, Suzanne Petryk, Oscar Mañas, Zhiqiu Lin, Anas Mahmoud, Bargav Jayaraman, Mark Ibrahim, Melissa Hall, Yunyang Xiong, Jonathan Lebensold, Candace Ross, Srihari Jayakumar, Chuan Guo, Diane Bouchacourt, Haider Al-Tahan, Karthik Padthe, Vasu Sharma, Hu Xu, Xiaoqing Ellen Tan, Megan Richards, Samuel Lavoie, Pietro Astolfi, Reyhane Askari Hemmat, Jun Chen, Kushal Tirumala, Rim Assouel, Mazda Moayeri, Arjang Talattof, Kamalika Chaudhuri, Zechun Liu, Xilun Chen, Quentin Garrido, Karen Ullrich, Aishwarya Agrawal, Kate Saenko, Asli Celikyilmaz, Vikas Chandra
      arxiv 2024

      Chain-of-Verification Reduces Hallucination in Large Language Models
      Shehzaad Dhuliawala, Mojtaba Komeili, Jing Xu, Roberta Raileanu, Xian Li, Asli Celikyilmaz, Jason Weston
      arxiv 2023

      DOMINO: A Dual-System for Multi-step Visual Language Reasoning
      Peifang Wang, Olga Golovneva, Armen Aghajanyan, Xiang Ren, Muhao Chen, Asli Celikyilmaz, Maryam Fazel-Zarandi
      arxiv 2023

      Shepherd: A Critic for Language Model Generation
      Tianlu Wang, Ping Yu, Xiaoqing Ellen Tan, Sean O'Brien, Ramakanth Pasunuru, Jane Dwivedi-Yu, Olga Golovneva, Luke Zettlemoyer, Maryam Fazel-Zarandi, Asli Celikyilmaz
      arxiv 2023

      Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning
      Lili Yu, Bowen Shi, Ramakanth Pasunuru, Benjamin Muller, Olga Golovneva, Tianlu Wang, Arun Babu, Binh Tang, Brian Karrer, Shelly Sheynin, Candace Ross, Adam Polyak, Russell Howes, Vasu Sharma, Puxin Xu, Hovhannes Tamoyan, Oron Ashual, Uriel Singer, Shang-Wen Li, Susan Zhang, Richard James, Gargi Ghosh, Yaniv Taigman, Maryam Fazel-Zarandi, Asli Celikyilmaz, Luke Zettlemoyer, Armen Aghajanyan
      arxiv 2023

      Open-Domain Text Evaluation via Meta Distribution Modeling
      Sidi Lu, Asli Celikyilmaz, Tianlu Wang, Nanyun Peng
      arxiv 2023

      Large Language Model Programs
      Imanol Schlag, Sainbayar Sukhbaatar, Asli Celikyilmaz, Wen-tau Yih, Jason Weston, Jürgen Schmidhuber, Xian Li
      arxiv 2023

    Peer-Reviewed Publications:


    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, Meta Fundamentals AI Research (Meta FAIR), 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


      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


      Editor in Chief,TACL
      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.