Takeshi Kojima

48 papers A* 5B 1Journal 30Unranked 12

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	ClinDet-Bench: Beyond Abstention, Evaluating Judgment Determinability of LLMs in Clinical Decision-Making. CoRR Yusuke Watanabe, Yohei Kobashi, Takeshi Kojima, Yusuke Iwasawa, Yasushi Okuno, Yutaka Matsuo
2026	J	`jnl`	Emergent Analogical Reasoning in Transformers. CoRR Gouki Minegishi, Jingyuan Feng, Hiroki Furuta, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo
2026	—	`conf`	Infinity-MoE: Generalizing Mixture of Experts to Infinite Experts. EACL (Volume 2: Short Papers) Shota Takashiro, Takeshi Kojima, Shohei Taniguchi, Yusuke Iwasawa, Yutaka Matsuo
2026	—	`conf`	Revealing Redundant Syntax in Large Language Models through Multi-Hop Dependency Paths. EACL (Findings) Masaki Sashida, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo
2026	J	`jnl`	Safe Transformer: An Explicit Safety Bit For Interpretable And Controllable Alignment. CoRR Jingyuan Feng, Andrew Gambardella, Gouki Minegishi, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo
2026	—	`conf`	Semantic Token Clustering for Efficient Uncertainty Quantification in Large Language Models. EACL (Volume 2: Short Papers) Qi Cao, Andrew Gambardella, Takeshi Kojima, Yutaka Matsuo, Yusuke Iwasawa
2026	J	`jnl`	Semantic Token Clustering for Efficient Uncertainty Quantification in Large Language Models. CoRR Qi Cao, Andrew Gambardella, Takeshi Kojima, Yutaka Matsuo, Yusuke Iwasawa
2026	J	`jnl`	∞-MoE: Generalizing Mixture of Experts to Infinite Experts. CoRR Shota Takashiro, Takeshi Kojima, Shohei Taniguchi, Yusuke Iwasawa, Yutaka Matsuo
2025	A*	`conf`	A Comprehensive Survey on Physical Risk Control in the Era of Foundation Model-enabled Robotics. IJCAI Takeshi Kojima, Yaonan Zhu, Yusuke Iwasawa, Toshinori Kitamura, Gang Yan, Shu Morikuni, Ryosuke Takanami, Alfredo Solano, Tatsuya Matsushima, Akiko Murakami, Yutaka Matsuo
2025	J	`jnl`	A Comprehensive Survey on Physical Risk Control in the Era of Foundation Model-enabled Robotics. CoRR Takeshi Kojima, Yaonan Zhu, Yusuke Iwasawa, Toshinori Kitamura, Gang Yan, Shu Morikuni, Ryosuke Takanami, Alfredo Solano, Tatsuya Matsushima, Akiko Murakami, Yutaka Matsuo
2025	—	`conf`	Answer When Needed, Forget When Not: Language Models Pretend to Forget via In-Context Knowledge Unlearning. ACL (Findings) Shota Takashiro, Takeshi Kojima, Andrew Gambardella, Qi Cao, Yusuke Iwasawa, Yutaka Matsuo
2025	J	`jnl`	Automated Refinement of Essay Scoring Rubrics for Language Models via Reflect-and-Revise. CoRR Keno Harada, Lui Yoshida, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo
2025	J	`jnl`	Continual Pre-training on Character-level Noisy Texts Makes Decoder-based Language Models Robust Few-shot Learners. Trans. Assoc. Comput. Linguistics Takeshi Kojima, Yutaka Matsuo, Yusuke Iwasawa
2025	—	`conf`	Crypto-LLM: Two-Stage Language Model Pre-training with Ciphered and Natural Language Data. IJCNLP-AACL (long papers) Yohei Kobashi, Fumiya Uchiyama, Takeshi Kojima, Andrew Gambardella, Qi Cao, Yusuke Iwasawa, Yutaka Matsuo
2025	—	`conf`	Dynamic Injection of Entity Knowledge into Dense Retrievers. EMNLP (Findings) Ikuya Yamada, Ryokan Ri, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo
2025	J	`jnl`	Dynamic Injection of Entity Knowledge into Dense Retrievers. CoRR Ikuya Yamada, Ryokan Ri, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo
2025	—	`conf`	Inconsistent Tokenizations Cause Language Models to be Perplexed by Japanese Grammar. ACL (2) Andrew Gambardella, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo
2025	J	`jnl`	Inconsistent Tokenizations Cause Language Models to be Perplexed by Japanese Grammar. CoRR Andrew Gambardella, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo
2025	—	`conf`	Lost in the Distance: Large Language Models Struggle to Capture Long-Distance Relational Knowledge. NAACL (Findings) Meiyun Wang, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo
2025	J	`jnl`	RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs. CoRR Kohsei Matsutani, Shota Takashiro, Gouki Minegishi, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo
2025	B	`conf`	Slender-Mamba: Fully Quantized Mamba in 1.58 Bits From Head to Toe. COLING Zhenxuan Yu, Takeshi Kojima, Yutaka Matsuo, Yusuke Iwasawa
2025	J	`jnl`	Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph Properties. CoRR Gouki Minegishi, Hiroki Furuta, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo
2025	—	`conf`	When Instructions Multiply: Measuring and Estimating LLM Capabilities of Multiple Instructions Following. EMNLP (Findings) Keno Harada, Yudai Yamazaki, Masachika Taniguchi, Edison Marrese-Taylor, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo
2025	J	`jnl`	When Instructions Multiply: Measuring and Estimating LLM Capabilities of Multiple Instructions Following. CoRR Keno Harada, Yudai Yamazaki, Masachika Taniguchi, Edison Marrese-Taylor, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo
2024	J	`jnl`	Answer When Needed, Forget When Not: Language Models Pretend to Forget via In-Context Knowledge Unlearning. CoRR Shota Takashiro, Takeshi Kojima, Andrew Gambardella, Qi Cao, Yusuke Iwasawa, Yutaka Matsuo
2024	J	`jnl`	Iterative Tomographic Image Reconstruction Algorithm Based on Extended Power Divergence by Dynamic Parameter Tuning. J. Imaging Ryuto Yabuki, Yusaku Yamaguchi, Omar M. Abou Al-Ola, Takeshi Kojima, Tetsuya Yoshinaga
2024	—	`conf`	On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons. NAACL-HLT Takeshi Kojima, Itsuki Okimura, Yusuke Iwasawa, Hitomi Yanaka, Yutaka Matsuo
2024	J	`jnl`	On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons. CoRR Takeshi Kojima, Itsuki Okimura, Yusuke Iwasawa, Hitomi Yanaka, Yutaka Matsuo
2024	J	`jnl`	On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons. J. Nat. Lang. Process. Takeshi Kojima
2024	J	`jnl`	Optimizing Parameters for Enhanced Iterative Image Reconstruction Using Extended Power Divergence. Algorithms Takeshi Kojima, Yusaku Yamaguchi, Omar M. Abou Al-Ola, Tetsuya Yoshinaga
2024	A*	`conf`	Which Programming Language and What Features at Pre-training Stage Affect Downstream Logical Inference Performance? EMNLP Fumiya Uchiyama, Takeshi Kojima, Andrew Gambardella, Qi Cao, Yusuke Iwasawa, Yutaka Matsuo
2024	J	`jnl`	Which Programming Language and What Features at Pre-training Stage Affect Downstream Logical Inference Performance? CoRR Fumiya Uchiyama, Takeshi Kojima, Andrew Gambardella, Qi Cao, Yusuke Iwasawa, Yutaka Matsuo
2023	J	`jnl`	Iterative Image Reconstruction Algorithm with Parameter Estimation by Neural Network for Computed Tomography. Algorithms Takeshi Kojima, Tetsuya Yoshinaga
2023	J	`jnl`	Robustifying Vision Transformer Without Retraining from Scratch Using Attention-Based Test-Time Adaptation. New Gener. Comput. Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo
2023	A*	`conf`	Unnatural Error Correction: GPT-4 Can Almost Perfectly Handle Unnatural Scrambled Text. EMNLP Qi Cao, Takeshi Kojima, Yutaka Matsuo, Yusuke Iwasawa
2023	J	`jnl`	Unnatural Error Correction: GPT-4 Can Almost Perfectly Handle Unnatural Scrambled Text. CoRR Qi Cao, Takeshi Kojima, Yutaka Matsuo, Yusuke Iwasawa
2022	J	`jnl`	Block-Iterative Reconstruction from Dynamically Selected Sparse Projection Views Using Extended Power-Divergence Measure. Entropy Kazuki Ishikawa, Yusaku Yamaguchi, Omar M. Abou Al-Ola, Takeshi Kojima, Tetsuya Yoshinaga
2022	A*	`conf`	Large Language Models are Zero-Shot Reasoners. NeurIPS Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, Yusuke Iwasawa
2022	J	`jnl`	Large Language Models are Zero-Shot Reasoners. CoRR Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, Yusuke Iwasawa
2022	A*	`conf`	Robustifying Vision Transformer without Retraining from Scratch by Test-Time Class-Conditional Feature Alignment. IJCAI Takeshi Kojima, Yutaka Matsuo, Yusuke Iwasawa
2022	J	`jnl`	Robustifying Vision Transformer without Retraining from Scratch by Test-Time Class-Conditional Feature Alignment. CoRR Takeshi Kojima, Yutaka Matsuo, Yusuke Iwasawa
2021	—	`conf`	Making Use of Latent Space in Language GANs for Generating Diverse Text without Pre-training. EACL (Student Research Workshop) Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo
2021	J	`jnl`	Noise-Robust Image Reconstruction Based on Minimizing Extended Class of Power-Divergence Measures. Entropy Ryosuke Kasai, Yusaku Yamaguchi, Takeshi Kojima, Omar M. Abou Al-Ola, Tetsuya Yoshinaga
2013	—	`conf`	Hierarchical concern-based pointcuts. AOAsia@AOSD Takeshi Kojima, Tomoyuki Aotani
2004	J	`jnl`	Behavior of Cu(In, Ga)Se Microelectron. Reliab. Takeshi Yanagisawa, Takeshi Kojima, Tadamasa Koyanagi
2003	J	`jnl`	Degradation of InGaN blue light-emitting diodes under continuous and low-speed pulse operations. Microelectron. Reliab. Takeshi Yanagisawa, Takeshi Kojima
2003	J	`jnl`	The stability of the CuInSe Microelectron. Reliab. Takeshi Yanagisawa, Takeshi Kojima
2002	J	`jnl`	Changes in the characteristics of CuInGaSe Microelectron. Reliab. Takeshi Yanagisawa, Takeshi Kojima, Tadamasa Koyanagi, Kiyoshi Takahisa, Kuniomi Nakamura