Takeuchi, Susumu

7 publications

ICLR 2026 Lossless Vocabulary Reduction for Auto-Regressive Language Models Daiki Chijiwa, Taku Hasegawa, Kyosuke Nishida, Shin'ya Yamaguchi, Tomoya Ohba, Tamao Sakao, Susumu Takeuchi

TMLR 2025 Partially Frozen Random Networks Contain Compact Strong Lottery Tickets Hikari Otsuka, Daiki Chijiwa, Ángel López García-Arias, Yasuyuki Okoshi, Kazushi Kawamura, Thiem Van Chu, Daichi Fujiki, Susumu Takeuchi, Masato Motomura

ICML 2025 Portable Reward Tuning: Towards Reusable Fine-Tuning Across Different Pretrained Models Daiki Chijiwa, Taku Hasegawa, Kyosuke Nishida, Kuniko Saito, Susumu Takeuchi

ICMLW 2024 Base-Change at Prediction: Inference-Time Update of Fine-Tuned Models Daiki Chijiwa, Taku Hasegawa, Kyosuke Nishida, Kuniko Saito, Susumu Takeuchi

NeurIPSW 2024 Partially Frozen Random Networks Contain Compact Strong Lottery Tickets Hikari Otsuka, Daiki Chijiwa, Ángel López García-Arias, Yasuyuki Okoshi, Kazushi Kawamura, Thiem Van Chu, Daichi Fujiki, Susumu Takeuchi, Masato Motomura

NeurIPSW 2024 The Trichromatic Strong Lottery Ticket Hypothesis: Neural Compression with Three Primary Supermasks Ángel López García-Arias, Yasuyuki Okoshi, Hikari Otsuka, Daiki Chijiwa, Yasuhiro Fujiwara, Susumu Takeuchi, Masato Motomura

AAAI 2023 Beam Search Optimized Batch Bayesian Active Learning Jingyu Sun, Hongjie Zhai, Osamu Saisho, Susumu Takeuchi