Global PIQA was accepted as a poster to the NeurIPS 2026 Evaluations and Datasets Track, and a soccer inverse-reinforcement-learning paper was accepted as an oral presentation at IEEE GCCE 2026.
Joined the Autumn 2026 Redwood Research stream at MATS Research.
Our paper on human-like inductive biases for improving LLM data efficiency received an SAC Highlight Award at ACL 2026.
Two papers were accepted to the ACL 2026 Main Conference, on language acquisition in language models and garden-path effects via surprisal.
I will give invited talks at UCI and Boston University.
Joining Prof. Tal Linzen's group from Nov 2025 to May 2026.
Presenting work on information locality, attention as memory, and derivational probing.
Recognized for large-scale multimodal model research.
Awarded JSPS DC2 fellowship (later declined to accept BOOST NAIS).
MITOU (Exploratory IT Human Resources Project) Super Creator recognition.
Targeted syntactic evaluations across the Chomsky hierarchy won Best Paper (1/1554; Top 0.06%).