PPaperPicks

Jun Suzuki

14 papers at tracked venues · 7 at CORE A* · active 2024–2026

DBLP profile ↗ORCID search ↗

Venues

ACL ×3EACL ×2EMNLP ×2NAACL ×2AAAI ×1CVPR ×1ICLR ×1IUI ×1NeurIPS ×1

Frequent coauthors

Kazuki Yano
×4
Reina Akama
×3
Ryohei Kamei
×2
Mengyu Ye
×2
Tatsuki Kuribayashi
×2
Takumi Ito
×2
Ryota Tanaka
×2
Taichi Iki
×2
Kyosuke Nishida
×2
Kuniko Saito
×2
Keigo Shibata
×1
Ryosuke Takahashi
×1

Papers

  1. Suppressing Final Layer Hidden State Jumps in Transformer Pretraining
    EACL 2026 ·
    Keigo Shibata
    ,
    Kazuki Yano
    ,
    Ryosuke Takahashi
    ,
    Jaesung Lee
    ,
    Wataru Ikeda
    , Jun Suzuki
  2. TimeMachine-bench: A Benchmark for Evaluating Model Capabilities in Repository-Level Migration Tasks
    EACL 2026 ·
    Ryo Fujii
    ,
    Makoto Morishita
    ,
    Kazuki Yano
    , Jun Suzuki
  3. Vulnerability of LLM Outputs to Heuristics-Inducing Prompt Structures
    IUI 2026 ·
    Toshiki Kuramoto
    ,
    Ryohei Kamei
    , Jun Suzuki
  4. Can Input Attributions Explain Inductive Reasoning in In-Context Learning?
    ACL 2025 ·
    Mengyu Ye
    ,
    Tatsuki Kuribayashi
    ,
    Goro Kobayashi
    , Jun Suzuki
  5. Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization
    ICLR 2025 ·
    Taishi Nakamura
    ,
    Takuya Akiba
    ,
    Kazuki Fujii
    ,
    Yusuke Oda
    ,
    Rio Yokota
    , Jun Suzuki
  6. Enhancing Persuasive Dialogue Agents by Synthesizing Cross-Disciplinary Communication Strategies
    EMNLP 2025 ·
    Shinnosuke Nozue
    ,
    Yuto Nakano
    ,
    Yotaro Watanabe
    ,
    Meguru Takasaki
    ,
    Shoji Moriya
    ,
    Reina Akama
    , Jun Suzuki
  7. STEP: Staged Parameter-Efficient Pre-training for Large Language Models
    NAACL 2025 ·
    Kazuki Yano
    ,
    Takumi Ito
    , Jun Suzuki
  8. Transformer Key-Value Memories Are Nearly as Interpretable as Sparse Autoencoders
    NeurIPS 2025 ·
    Mengyu Ye
    , Jun Suzuki,
    Tatsuro Inaba
    ,
    Tatsuki Kuribayashi
  9. VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents
    CVPR 2025 ·
    Ryota Tanaka
    ,
    Taichi Iki
    ,
    Taku Hasegawa
    ,
    Kyosuke Nishida
    ,
    Kuniko Saito
    , Jun Suzuki
  10. A Large Collection of Model-generated Contradictory Responses for Consistency-aware Dialogue Systems
    ACL 2024 ·
    Shiki Sato
    ,
    Reina Akama
    , Jun Suzuki,
    Kentaro Inui
  11. Detecting Response Generation Not Requiring Factual Judgment
    NAACL 2024 ·
    Ryohei Kamei
    ,
    Daiki Shiono
    ,
    Reina Akama
    , Jun Suzuki
  12. InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructions
    AAAI 2024 ·
    Ryota Tanaka
    ,
    Taichi Iki
    ,
    Kyosuke Nishida
    ,
    Kuniko Saito
    , Jun Suzuki
  13. Pruning Multilingual Large Language Models for Multilingual Inference
    EMNLP 2024 ·
    Hwichan Kim
    , Jun Suzuki,
    Tosho Hirasawa
    ,
    Mamoru Komachi
  14. STEP: Staged Parameter-Efficient Pre-training for Large Language Models
    ACL 2024 ·
    Kazuki Yano
    ,
    Takumi Ito
    , Jun Suzuki