publications

*: equal contribution

2025

  1. NeurIPS
    AION-1: Omnimodal Foundation Model for Astronomical Sciences
    Liam Holden Parker*, Francois Lanusse*, Jeff Shen*, Ollie Liu, and 21 more authors
    In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025
  2. Preprint
    OpenMETAGENE: Large-Scale, Diverse, and Open Data Recipes for Multimodal Metagenomics Models
    Shangshang Wang, Ollie Liu, Jiarui Zhang, and Willie Neiswanger
    In NeurIPS 2025 AI for Science Workshop, 2025
  3. COLM
    LLM Unlearning Without an Expert Curated Dataset
    Xiaoyuan Zhu, Muru Zhang, Ollie Liu, Robin Jia, and 1 more author
    2025
    arXiv
  4. Preprint
    Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning
    Ang Li*, Charles Wang*, Kaiyu Yue, Zikui Cai*, and 10 more authors
    2025
    arXiv
  5. Preprint
    Resa: Transparent Reasoning Models via SAEs
    Shangshang Wang, Julian Asilis, Ömer Faruk Akgül, Enes Burak Bilgin, and 3 more authors
    2025
    arXiv
  6. Preprint
    Tina: Tiny Reasoning Models via LoRA
    Shangshang Wang, Julian Asilis, Ömer Faruk Akgül, Enes Burak Bilgin, and 2 more authors
    2025
    arXiv
  7. Preprint
    Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models
    Woody Haosheng Gan*, Deqing Fu*, Julian Asilis, Ollie Liu*, and 4 more authors
    2025
    arXiv
  8. Preprint
    Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems
    Bang Liu, Xinfeng Li, Jiayi Zhang, Jinlin Wang, and 44 more authors
    2025
    arXiv
  9. NAACL
    MatViX: Multimodal Information Extraction from Visually Rich Articles
    Ghazal Khalighinejad, Sharon Scott, Ollie Liu, Kelly L Anderson, and 3 more authors
    2025
    arXiv Website
  10. Preprint
    METAGENE-1: Metagenomic Foundation Model for Pandemic Monitoring
    Ollie Liu, Sami Jaghouar, Johannes Hagemann, Shangshang Wang, and 3 more authors
    arXiv preprint arXiv:2501.02045, 2025
    arXiv Code Website

2024

  1. Preprint
    Euclid: Supercharging Multimodal LLMs with Synthetic High-Fidelity Visual Descriptions
    Jiarui Zhang, Ollie Liu, Tianyu Yu, Jinyi Hu, and 1 more author
    arXiv preprint arXiv:2412.08737, 2024
    Code Website
  2. Preprint
    Game-theoretic LLM: Agent Workflow for Negotiation Games
    Wenyue Hua, Ollie Liu, Lingyao Li, Alfonso Amayuelas, and 8 more authors
    arXiv preprint arXiv:2411.05990, 2024
    arXiv
  3. COLM
    IsoBench: Benchmarking Multimodal Foundation Models on Isomorphic Representations
    Deqing Fu*, Ghazal Khalighinejad*, Ruohao Guo*, Ollie Liu*, and 4 more authors
    In The First Conference on Language Modeling, 2024
    arXiv Website
  4. ICLR
    DeLLMa: Decision Making Under Uncertainty with Large Language Models
    Ollie Liu*, Deqing Fu*, Dani Yogatama, and Willie Neiswanger
    In [Spotlight] The Thirteenth International Conference on Learning Representations, 2024
    arXiv Code Slides Website

2023

  1. NAACL
    On Retrieval Augmentation and the Limitations of Language Model Training
    Ting-Rui Chiang, Xinyan Velocity Yu, Joshua Robinson, Ollie Liu, and 2 more authors
    In 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics, 2023
    arXiv
  2. ICLR
    Interpretable Diffusion via Information Decomposition
    Xianghao Kong*, Ollie Liu*, Han Li, Dani Yogatama, and 1 more author
    In The Twelfth International Conference on Learning Representations, 2023
    arXiv Code
  3. NeurIPS
    How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model
    Michael Hanna, Ollie Liu, and Alexandre Variengien
    In Thirty-seventh Conference on Neural Information Processing Systems, 2023
    arXiv Code
  4. EMNLP
    Approximating CKY with Transformers
    Ghazal Khalighinejad, Ollie Liu, and Sam Wiseman
    In Findings of the Association for Computational Linguistics: EMNLP 2023, Dec 2023
    arXiv