日本語

News

Two papers accepted to NeurIPS 2026 ED Track and IEEE GCCE 2026
  • Global PIQA: Evaluating Commonsense Reasoning Across 100+ Languages and Cultures
  • Inferring Collective Reward Preferences from Multi-Agent Trajectories with Gradient-Based Inverse Reinforcement Learning in Soccer
Joined MATS Research as a MATS Fellow
SAC Highlight Award at ACL 2026
  • Language Acquisition Device in Large Language Models
Two papers accepted to ACL 2026
  • Language Acquisition Device in Large Language Models
  • An Existence Proof for Neural Language Models That Can Explain Garden-Path Effects via Surprisal
Invited talks at UCI and Boston University
Two papers accepted to ACL 2025 and one to CoNLL 2025
  • Information Locality as an Inductive Bias for Neural Language Models
  • If Attention Serves as a Cognitive Model of Human Memory Retrieval, What is the Plausible Memory Representation?
  • Derivational Probing: Unveiling the Layer-wise Construction of Syntactic Structures in Neural Language Models
KAKUSEI Project "Ha" Outstanding Achievement Award
Selected for JSPS Research Fellowship (DC2)