Research
研究
研究業績
カテゴリー
研究領域
年
-
解釈可能性を高めて信頼し得るエージェントを実現するための脳型認知モデル
田和辻 可昌, 大森 隆司, 太田 博三, 宮本 竜也, 芦原 佑太, 荒川 直哉, 山川 宏
人工知能, Vol.39 No.2, p.197-204, 2024
-
脳科学とロボティクスを結ぶ統合認知モデルの実践と展望
谷口 彰, 山川 宏, 谷口 忠大
人工知能, Vol.39 No.2, p.205-213, 2024.
-
“Geometric-Averaged Preference Optimization for Soft Preference Labels”
Hiroki Furuta, Kuang-Huei Lee, Shixiang Shane Gu, Yutaka Matsuo, Aleksandra Faust, Heiga Zen, Izzeddin Gur
Advances in Neural Information Processing Systems 37 (NeurIPS 2024)
-
“ADOPT: Modified Adam Can Converge with Any β2 with the Optimal Rate”
Shohei Taniguchi, Keno Harada, Gouki Minegishi, Yuta Oshima, Seong Cheol Jeong, Go Nagahara, Tomoshi Iiyama, Masahiro Suzuki, Yusuke Iwasawa, Yutaka Matsuo
Advances in Neural Information Processing Systems 37 (NeurIPS 2024)
-
“Which Programming Language and What Features at Pre-training Stage Affect Downstream Logical Inference Performance?“
Fumiya Uchiyama, Takeshi Kojima, Andrew Gambardella, Qi Cao, Yusuke Iwasawa, Yutaka Matsuo
The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024)
-
“Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4”
Jiaxian Guo*, Bo Yang*, Paul Yoo, Yuchen Lin, Yutaka Matsuo, Yusuke Iwasawa
AAAI RL+LLM, 2024 (Oral).
-
“Decoupling Noise and Toxic Parameters for Language Model Detoxification by Task Vector Merging”
Yongmin Kim, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo
2024 First Conference on Language Modeling (COLM 2024).
-
“Aligning Superintelligence Goals with Societal Welfare: An Evolutionary Perspective”
Hiroshi Yamakawa
9th International Conference on Robot Ethics and Standards (ICRES 2024).
-
“Sustainability of Digital Life Form Societies”
Hiroshi Yamakawa
9th International Conference on Robot Ethics and Standards (ICRES 2024)
-
”Language Models Do Hard Arithmetic Tasks Easily and Hardly Do Easy Arithmetic Tasks”
Andrew Gambardella, Yusuke Iwasawa, Yutaka Matsuo
Proceeding of the 62nd Annual Meeting of the Association for Computer Linguistics (ACL2024)