Sosuke Kobayashi

39 papers A* 6A 1Journal 21Unranked 11

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Pre-training LLM without Learning Rate Decay Enhances Supervised Fine-Tuning. CoRR Kazuki Yano, Shun Kiyono, Sosuke Kobayashi, Sho Takase, Jun Suzuki
2025	J	`jnl`	Efficient Construction of Model Family through Progressive Training Using Model Expansion. CoRR Kazuki Yano, Sho Takase, Sosuke Kobayashi, Shun Kiyono, Jun Suzuki
2025	A	`conf`	User-Guided Correction of Reconstruction Errors in Structure-from-Motion. IUI Sotaro Kanazawa, Jinyao Zhou, Yuta Kikuchi, Sosuke Kobayashi, Chunyu Li, Fabrice Matulic, Takeo Igarashi, Keita Higuchi
2025	J	`jnl`	When Does Metadata Conditioning (NOT) Work for Language Model Pre-Training? A Study with Context-Free Grammars. CoRR Rei Higuchi, Ryotaro Kawata, Naoki Nishikawa, Kazusato Oko, Shoichiro Yamaguchi, Sosuke Kobayashi, Seiya Tokui, Kohei Hayashi, Daisuke Okanohara, Taiji Suzuki
2023	—	`conf`	B2T Connection: Serving Stability and Performance in Deep Transformers. ACL (Findings) Sho Takase, Shun Kiyono, Sosuke Kobayashi, Jun Suzuki
2023	J	`jnl`	Spike No More: Stabilizing the Pre-training of Large Language Models. CoRR Sho Takase, Shun Kiyono, Sosuke Kobayashi, Jun Suzuki
2022	A*	`conf`	Decomposing NeRF for Editing via Feature Field Distillation. NeurIPS Sosuke Kobayashi, Eiichi Matsumoto, Vincent Sitzmann
2022	J	`jnl`	Decomposing NeRF for Editing via Feature Field Distillation. CoRR Sosuke Kobayashi, Eiichi Matsumoto, Vincent Sitzmann
2022	J	`jnl`	Diverse Lottery Tickets Boost Ensemble from a Single Pretrained Model. CoRR Sosuke Kobayashi, Shun Kiyono, Jun Suzuki, Kentaro Inui
2022	J	`jnl`	On Layer Normalizations and Residual Connections in Transformers. CoRR Sho Takase, Shun Kiyono, Sosuke Kobayashi, Jun Suzuki
2022	A*	`conf`	VocabEncounter: NMT-powered Vocabulary Learning by Presenting Computer-Generated Usages of Foreign Words into Users' Daily Lives. CHI Riku Arakawa, Hiromu Yakura, Sosuke Kobayashi
2021	J	`jnl`	Instance-Based Neural Dependency Parsing. CoRR Hiroki Ouchi, Jun Suzuki, Sosuke Kobayashi, Sho Yokoi, Tatsuki Kuribayashi, Masashi Yoshikawa, Kentaro Inui
2021	J	`jnl`	Instance-Based Neural Dependency Parsing. Trans. Assoc. Comput. Linguistics Hiroki Ouchi, Jun Suzuki, Sosuke Kobayashi, Sho Yokoi, Tatsuki Kuribayashi, Masashi Yoshikawa, Kentaro Inui
2021	—	`conf`	SHAPE : Shifted Absolute Position Embedding for Transformers. EMNLP (1) Shun Kiyono, Sosuke Kobayashi, Jun Suzuki, Kentaro Inui
2021	J	`jnl`	SHAPE: Shifted Absolute Position Embedding for Transformers. CoRR Shun Kiyono, Sosuke Kobayashi, Jun Suzuki, Kentaro Inui
2020	A*	`conf`	All Word Embeddings from One Embedding. NeurIPS Sho Takase, Sosuke Kobayashi
2020	J	`jnl`	All Word Embeddings from One Embedding. CoRR Sho Takase, Sosuke Kobayashi
2020	—	`conf`	Efficient Estimation of Influence of a Training Instance. SustaiNLP@EMNLP Sosuke Kobayashi, Sho Yokoi, Jun Suzuki, Kentaro Inui
2020	J	`jnl`	Efficient Estimation of Influence of a Training Instance. CoRR Sosuke Kobayashi, Sho Yokoi, Jun Suzuki, Kentaro Inui
2020	A*	`conf`	Instance-Based Learning of Span Representations: A Case Study through Named Entity Recognition. ACL Hiroki Ouchi, Jun Suzuki, Sosuke Kobayashi, Sho Yokoi, Tatsuki Kuribayashi, Ryuto Konno, Kentaro Inui
2020	J	`jnl`	Instance-Based Learning of Span Representations: A Case Study through Named Entity Recognition. CoRR Hiroki Ouchi, Jun Suzuki, Sosuke Kobayashi, Sho Yokoi, Tatsuki Kuribayashi, Ryuto Konno, Kentaro Inui
2020	J	`jnl`	Train Sparsely, Generate Densely: Memory-Efficient Unsupervised Training of High-Resolution Temporal GAN. Int. J. Comput. Vis. Masaki Saito, Shunta Saito, Masanori Koyama, Sosuke Kobayashi
2019	J	`jnl`	Data Interpolating Prediction: Alternative Interpretation of Mixup. CoRR Takuya Shimada, Shoichiro Yamaguchi, Kohei Hayashi, Sosuke Kobayashi
2019	—	`conf`	Learning from Observation-Only Demonstration for Task-Oriented Language Grounding via Self-Examination. ViGIL@NeurIPS Tsu-Jui Fu, Yuta Tsuboi, Sosuke Kobayashi, Yuta Kikuchi
2018	—	`conf`	Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations. NAACL-HLT (2) Sosuke Kobayashi
2018	J	`jnl`	Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations. CoRR Sosuke Kobayashi
2018	J	`jnl`	DQN-TAMER: Human-in-the-Loop Reinforcement Learning with Intractable Feedback. CoRR Riku Arakawa, Sosuke Kobayashi, Yuya Unno, Yuta Tsuboi, Shin-ichi Maeda
2018	A*	`conf`	Interactively Picking Real-World Objects with Unconstrained Spoken Language Instructions. ICRA Jun Hatori, Yuta Kikuchi, Sosuke Kobayashi, Kuniyuki Takahashi, Yuta Tsuboi, Yuya Unno, Wilson Ko, Jethro Tan
2018	A*	`conf`	Pointwise HSIC: A Linear-Time Kernelized Co-occurrence Norm for Sparse Linguistic Expressions. EMNLP Sho Yokoi, Sosuke Kobayashi, Kenji Fukumizu, Jun Suzuki, Kentaro Inui
2018	J	`jnl`	Pointwise HSIC: A Linear-Time Kernelized Co-occurrence Norm for Sparse Linguistic Expressions. CoRR Sho Yokoi, Sosuke Kobayashi, Kenji Fukumizu, Jun Suzuki, Kentaro Inui
2018	—	`conf`	Unsupervised Learning of Style-sensitive Word Vectors. ACL (2) Reina Akama, Kento Watanabe, Sho Yokoi, Sosuke Kobayashi, Kentaro Inui
2018	J	`jnl`	Unsupervised Learning of Style-sensitive Word Vectors. CoRR Reina Akama, Kento Watanabe, Sho Yokoi, Sosuke Kobayashi, Kentaro Inui
2017	—	`conf`	A Neural Language Model for Dynamically Representing the Meanings of Unknown Words and Entities in a Discourse. IJCNLP(1) Sosuke Kobayashi, Naoaki Okazaki, Kentaro Inui
2017	J	`jnl`	A Neural Language Model for Dynamically Representing the Meanings of Unknown Words and Entities in a Discourse. CoRR Sosuke Kobayashi, Naoaki Okazaki, Kentaro Inui
2017	—	`conf`	An RNN-based Binary Classifier for the Story Cloze Test. LSDSem@EACL Melissa Roemmele, Sosuke Kobayashi, Naoya Inoue, Andrew Gordon
2017	—	`conf`	Generating Stylistically Consistent Dialog Responses with Transfer Learning. IJCNLP(2) Reina Akama, Kazuaki Inada, Naoya Inoue, Sosuke Kobayashi, Kentaro Inui
2017	J	`jnl`	Interactively Picking Real-World Objects with Unconstrained Spoken Language Instructions. CoRR Jun Hatori, Yuta Kikuchi, Sosuke Kobayashi, Kuniyuki Takahashi, Yuta Tsuboi, Yuya Unno, Wilson Ko, Jethro Tan
2016	—	`conf`	Dynamic Entity Representation with Max-pooling Improves Machine Reading. HLT-NAACL Sosuke Kobayashi, Ran Tian, Naoaki Okazaki, Kentaro Inui
2016	—	`conf`	Tohoku at SemEval-2016 Task 6: Feature-based Model versus Convolutional Neural Network for Stance Detection. SemEval@NAACL-HLT Yuki Igarashi, Hiroya Komatsu, Sosuke Kobayashi, Naoaki Okazaki, Kentaro Inui