Taishi Nakamura

3 papers · 2025–2025 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11) 👥 Mega-Team · Squad

Venues

ICLR (2) COLING (1)

Top co-authors

Rio Yokota (2) Takuya Akiba (2) Ben Bogin (1) Sampo Pyysalo (1) So Kuroki (1) Xuan-Son Vu (1) Jordan Clive (1) Jason T. Stillerman (1) Xiaozhe Yao (1) Tommaso Furlanello (1)

Research topics

Machine Learning (3) Artificial Intelligence (2) Application Areas (2) Core AI (2) Deep Learning (1) Natural Language Processing (1) Architectures (1) Learning Paradigms (1) Learning Types (1) Optimization & Theory (1) Resources & Methods (1)

Keywords

catastrophic forgetting (1) code generation (1) model merging (1) ai safety (1) mixture of expert (1) model fine-tuning (1) evolutionary algorithm (1) continual pre-training (1) parameter efficiency (1) expert specialization (1) quality diversity (1) multilingual model (1) multilingual language model (1) open-source model (1) large language model (1) skill acquisition (1) model upcycling (1)

Papers

Agent Skill Acquisition for Large Language Models via CycleQD ICLR 2025 Aurora-M: Open Source Continual Pre-training for Multilingual Language and Code COLING 2025 Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization ICLR 2025