publications

Selected publications and preprints.

2026

  1. EMNLP
    Latent Mechanisms of Language Control in Multilingual Language Models
    Ryo Mitsuhashi, Sabri Boughorbel, and Majd Hawasly
    In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, 2026
    Accepted to EMNLP 2026 (Main). Also presented at the Mechanistic Interpretability Workshop, ICML 2026.
    arXiv OpenReview
  2. ICML Workshop
    Quantifying Empirical Compute-Supervision Tradeoffs in RLVR
    Ryo Mitsuhashi*, Patrick Chen*, Isabelle Tseng*, and 2 more authors
    In Combining Theory and Benchmarks Workshop, ICML, 2026
    arXiv OpenReview
  3. ACL SRW
    Disentangling the Effects of Unlearning in Measuring Parametric Faithfulness of Chain-of-Thought
    Ryo Mitsuhashi, Gaku Morio, Ayana Niwa, and 5 more authors
    In ACL 2026 Student Research Workshop, 2026
    Oral presentation.
    Anthology
  4. CVPR Workshop
    OccludeBench: Can VLMs Find What’s Missing?
    Jasin Cekinmez*, Addison J. Wu*, Ryo Mitsuhashi*, and 3 more authors
    In Computer Vision in the Wild Workshop, CVPR, 2026
    arXiv
  5. ICLR Workshop
    Guess the Unified Model: Domain and Linguistic Effects in Generated Images
    Jasin Cekinmez*, Ryo Mitsuhashi*, and Yida Yin
    In Workshop on Navigating and Addressing Data Problems For Foundation Models (DATA-FM), ICLR, 2026
    arXiv OpenReview