Foundation Models


PI
Xifeng Yan,  University of California at Santa Barbara
 
Publications

Publications

  1. Direct Multi-Token Decoding
    by Xuan Luo, Weizhi Wang, Xifeng Yan
    arXiv:2510.11958, 2025 [arxiv]
  2. Train a Unified Multimodal Data Quality Classifier with Synthetic Data
    by Weizhi Wang, Rongmei Lin, Shiyang Li, Colin Lockard, Ritesh Sarkhel, Sanket Lokegaonkar, Jingbo Shang, Xifeng Yan, Nasser Zalmout, Xian Li
    EMNLP'25 (Proceedings of Findings of EMNLP 2025) [pdf]
  3. Adaptive Layer-skipping in Pre-trained LLMs
    X. Luo, W. Wang, X. Yan
    COLM'25 (Conference on Language Modeling),  arXiv:2503.23798v2, 2025 [arxiv]
  4. Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources
    Weizhi Wang, Yu Tian, Linjie Yang, Heng Wang, Xifeng Yan
    COLM'25 (Conference on Language Modeling), arXiv:2504.00595v2, 2025 [arxiv]
  5. Language Models Augmented with Decoupled Memory,
    by W. Wang, L. Dong, H. Cheng, X. Liu, X. Yan, J. Gao, F. Wei
    NeurIPS'23 (The Thirty-seventh Annual Conference on Neural Information Processing Systems), 2023 [arxiv]
  6. Visually-augmented language modeling
    by W. Wang, L. Dong, H. Cheng, H. Song, X. Liu, X. Yan, J. Gao, F. Wei
    ICLR'23 (Proceedings of Int. Conf. on Learning Representations) [pdf]
  7. Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting,
    by S. Li, X. Jin, Y. Xuan, X. Zhou, W. Chen, Y.-X. Wang, X. Yan
    NeurIPS'19 (The Thirty-third Annual Conference on Neural Information Processing Systems) [pdf]