Publications

See my Google Scholar for the most up-to-date list of papers.

2026

  1. Preprint
    TabFM-Auto: Self-Evolving Pipelines for Tabular Foundation Models
    Preprint
    Deqing Fu, Huangyuan Su, Rajat Sen, Taman Narayan, Sujay Sanghavi, Abhimanyu Das, and Weihao Kong
    2026
    Paper Website
  2. Tech Report
    TabFM: A Zero-shot Foundation Model for Tabular Data
    Tech Report
    Weihao Kong, Erez Louidor Ilan, Shuxin Nie, Taman Narayan, Rajat Sen , Yichen Zhou, Deqing Fu, Samet Oymak, and Abhimanyu Das
    2026
    Paper Blog
  3. COLM
    topl.png
    Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift
    COLM
    Zitong Huang*, Gustavo Lucas Carvalho*, Deqing Fu, and Robin Jia
    In Conference on Language Modeling (COLM), 2026
    Paper
  4. ICML
    graph.png
    Transformers Provably Learn Algorithmic Solutions for Graph Connectivity, But Only with the Right Data
    ICML
    Qilin Ye*, Deqing Fu*, Robin Jia, and Vatsal Sharan
    In International Conference on Machine Learning (ICML), 2026
    Paper PDF
  5. NeurIPS
    vase.png
    Value-Aware Stochastic KV Cache Eviction for Reasoning Models
    NeurIPS
    Ting-Yun Chang* , Harvey Yiyun Fu*, Deqing Fu*, Chenghao Yang, Jesse Thomason, and Robin Jia
    In Conference on Neural Information Processing Systems (NeurIPS), 2026
    Paper Code
  6. COLM
    convergent.png
    Convergent Evolution: How Different Language Models Learn Similar Number Representations
    COLM
    Deqing Fu, Tianyi Zhou, Mikhail Belkin, Vatsal Sharan, and Robin Jia
    In Conference on Language Modeling (COLM), 2026
    Paper Blog Website
  7. ICML
    epsvec.png
    EPSVec: Efficient and Private Synthetic Data Generation via Dataset Vectors
    ICML
    Amin Banayeeanzade , Qingchuan Yang, Deqing Fu, Spencer Hong, Erin Babinsky, Alfy Samuel, Anoop Kumar, Robin Jia, and Sai Praneeth Karimireddy
    In International Conference on Machine Learning (ICML), 2026
    Paper
  8. EMNLP
    abstain.png
    Are LLM Decisions Faithful to Verbal Confidence?
    EMNLP
    Jiawei Wang , Yanfei Zhou, Siddartha Devic, and Deqing Fu
    In Conference on Empirical Methods in Natural Language Processing (EMNLP), 2026
    Paper
  9. ICLR
    zebra-cot.png
    Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning
    ICLR
    Ang Li*, Charles Wang*, Deqing Fu*, Kaiyu Yue*, Zikui Cai*, Wang Bill Zhu*, Ollie Liu* , Peng Guo*, Willie Neiswanger, Furong Huang, Tom Goldstein, and Micah Goldblum
    In International Conference on Learning Representations (ICLR), 2026
    Paper Dataset
  10. ICLR
    fone.png
    FoNE: Precise Single-Token Number Embeddings via Fourier Features
    ICLR
    Tianyi Zhou, Deqing Fu, Mahdi Soltanolkotabi, Robin Jia, and Vatsal Sharan
    In International Conference on Learning Representations (ICLR), 2026
    Paper Website
  11. COLM
    resa.png
    Resa: Transparent Reasoning Models via SAEs
    COLM
    Shangshang Wang, Julian Asilis, Ömer Faruk Akgül, Enes Burak Bilgin, Ollie Liu, Deqing Fu, and Willie Neiswanger
    In Conference on Language Modeling (COLM), 2026
    Paper
  12. ACL
    saegull.png
    Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models
    ACL
    Woody Haosheng Gan*, Deqing Fu*, Julian Asilis*, Ollie Liu*, Dani Yogatama, Vatsal Sharan, Robin Jia, and Willie Neiswanger
    In Association of Computational Linguistics (ACL), 2026
    Paper Blog

2025

  1. Tech Report
    Technical Report: Qwen3 Cross-layer Transcoders
    Tech Report
    Jakob Hansen, Deqing Fu , Shangshang Wang, and John Carlsson
    2025
    Paper
  2. NeurIPS
    visuallens.png
    VisualLens: Personalization through Visual History
    NeurIPS
    Wang Bill Zhu, Deqing Fu , Kai Sun, Yi Lu, Zhaojiang Lin, Seungwhan Moon, Kanika Narang, Mustafa Canim , Yue Liu, Anuj Kumar, and Xin Luna Dong
    In Conference on Neural Information Processing Systems (NeurIPS), 2025
    Paper
  3. ICLR
    tldr.png
    TLDR: Token-Level Detective Reward Model for Large Vision Language Models
    ICLR
    Deqing Fu, Tong Xiao , Rui Wang, Wang Zhu, Pengchuan Zhang, Guan Pang, Robin Jia, and Lawrence Chen
    In International Conference on Learning Representations (ICLR), 2025
    Paper
  4. ICLR
    sensitivity.png
    Transformers Learn Low Sensitivity Functions: Investigations and Implications
    ICLR
    Bhavya Vasudeva*, Deqing Fu*, Tianyi Zhou, Elliot Kau , You-Qi Huang, and Vatsal Sharan
    In International Conference on Learning Representations (ICLR), 2025
    Paper
  5. ICLR
    dellma.png
    DeLLMa: Decision Making Under Uncertainty with Large Language Models
    ICLR
    Ollie Liu*, Deqing Fu*, Dani Yogatama, and Willie Neiswanger
    In International Conference on Learning Representations (ICLR), 2025
    Spotlight (Top 5.1%)
    Paper Code Website
  6. NAACL
    dreamsync.png
    DreamSync: Aligning Text-to-Image Generation with Image Understanding Feedback
    NAACL
    Jiao Sun*, Deqing Fu*, Yushi Hu* , Su Wang, Royi Rassin, Da-Cheng Juan, Dana Alon, Charles Herrmann, Sjoerd Steenkiste, Ranjay Krishna, and Cyrus Rashtchian
    In Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2025
    Paper

2024

  1. NeurIPS
    transformer-icl.png
    Transformers Learn to Achieve Second-Order Convergence Rates for In-Context Linear Regression
    NeurIPS
    Deqing Fu, Tian-Qi Chen, Robin Jia, and Vatsal Sharan
    In Conference on Neural Information Processing Systems (NeurIPS), 2024
    SoCalNLP Symposium 2023 Best Paper Award
    Paper Code
  2. NeurIPS
    fourier.png
    Pre-trained Large Language Models Use Fourier Features to Compute Addition
    NeurIPS
    Tianyi Zhou, Deqing Fu, Vatsal Sharan, and Robin Jia
    In Conference on Neural Information Processing Systems (NeurIPS), 2024
    Paper
  3. COLM
    isobench.png
    IsoBench: Benchmarking Multimodal Foundation Models on Isomorphic Representations
    COLM
    Deqing Fu*, Ruohao Guo*, Ghazal Khalighinejad*, Ollie Liu*, Bhuwan Dhingra, Dani Yogatama, Robin Jia, and Willie Neiswanger
    In Conference on Language Modeling (COLM), 2024
    Paper Website

2023

  1. EMNLP
    scene.png
    SCENE: Self-Labeled Counterfactuals for Extrapolating to Negative Examples
    EMNLP
    Deqing Fu, Ameya Godbole, and Robin Jia
    In Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023
    Paper Code

* Equal contribution.