publications

publications by categories in reversed chronological order.

2026

  1. NeurIPS
    asyncopd.png
    AsyncOPD: How Stale Can On-Policy Distillation Be?
    Wonjun Kang*, Kevin Galim*, Seunghyuk Oh, and 9 more authors
    NeurIPS 2026, ICML 2026 DEMO Workshop, 2026
    arXiv Code
  2. NeurIPS
    efficientrollout.png
    EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts
    Minseo Kim*, Minjae Lee*, Seunghyuk Oh, and 7 more authors
    NeurIPS 2026, ICML 2026 AdaptFM Workshop, 2026
    arXiv Code
  3. NeurIPS
    mage.png
    MAGE: All-[MASK] Block Already Knows Where to Look in Block Diffusion LLM
    Omin Kwon, Yeonjae Kim, Doyeon Kim, and 3 more authors
    NeurIPS 2026, ICML 2026 AdaptFM Workshop (Best paper award), 2026
    arXiv
  4. ICLR DeLTa
    group_traj.png
    CATS: Inference-aligned SFT for Diffusion LLMs via Context-sensitivity Aware Trajectory Sampling
    Seunghyuk Oh, Minjae Lee, Kevin Galim, and 5 more authors
    ICLR 2026 DeLTa Workshop, Extended version under review , 2026
  5. ISCA MLArchSys
    llminaflash.png
    LLM Inference in a Flash!
    Sebastian Zhao*, Minseo Kim*, Coleman Hooper*, and 5 more authors
    ISCA 2026 MLArchSys Workshop (Oral), 2026
    arXiv
  6. MLSys
    cdlm.png
    CDLM: Consistency Diffusion Language Models for Faster Sampling
    Minseo Kim, Chenfeng Xu, Coleman Hooper, and 5 more authors
    In Proceedings of the 9th MLSys Conference, 2026
    arXiv Code

2025

  1. beyond.png
    Beyond Next-Token Prediction: A Performance Characterization of Diffusion versus Autoregressive Language Models
    Minseo Kim, Coleman Hooper, Aditya Tomar, and 5 more authors
    arXiv Preprint , 2025
    arXiv
  2. EMNLP
    kreta.png
    KRETA: A Benchmark for Korean Reading and Reasoning in Text-Rich VQA Attuned to Diverse Visual Contexts
    Taebaek Hwang*, Minseo Kim*, Gisang Lee, and 2 more authors
    In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025
    DOI HTML Code
  3. CIKM
    instanns.png
    InstANNS: Scalable Approximate Nearest Neighbor Search via Cost-Efficient In-Storage Processing
    Bonggeun Sim, Yushin Kim, Minseo Kim, and 2 more authors
    In Proceedings of the 34th ACM International Conference on Information and Knowledge Management (CIKM ’25), 2025
    DOI HTML