Takuya Akiba - RankMe

65 papers A* 16A 6B 2Journal 34Unranked 7

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	SoftMatcha 2: A Fast and Soft Pattern Matcher for Trillion-Scale Corpora. CoRR Masataka Yoneda, Yusuke Matsushita, Go Kamoda, Kohei Suenaga, Takuya Akiba, Masaki Waga, Sho Yokoi
2026	J	`jnl`	UnMaskFork: Test-Time Scaling for Masked Diffusion via Deterministic Action Branching. CoRR Kou Misaki, Takuya Akiba
2025	J	`jnl`	ALE-Bench: A Benchmark for Long-Horizon Objective-Driven Algorithm Engineering. CoRR Yuki Imajuku, Kohki Horie, Yoichi Iwata, Kensho Aoki, Naohiro Takahashi, Takuya Akiba
2025	A*	`conf`	Agent Skill Acquisition for Large Language Models via CycleQD. ICLR So Kuroki, Taishi Nakamura, Takuya Akiba, Yujin Tang
2025	J	`jnl`	DiffusionBlocks: Blockwise Training for Generative Models via Score-Based Diffusion. CoRR Makoto Shing, Takuya Akiba
2025	A*	`conf`	Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization. ICLR Taishi Nakamura, Takuya Akiba, Kazuki Fujii, Yusuke Oda, Rio Yokota, Jun Suzuki
2025	J	`jnl`	Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization. CoRR Taishi Nakamura, Takuya Akiba, Kazuki Fujii, Yusuke Oda, Rio Yokota, Jun Suzuki
2025	J	`jnl`	Evolutionary optimization of model merging recipes. Nat. Mac. Intell. Takuya Akiba, Makoto Shing, Yujin Tang, Qi Sun, David Ha
2025	J	`jnl`	Extending the Context of Pretrained LLMs by Dropping Their Positional Embeddings. CoRR Yoav Gelberg, Koshi Eguchi, Takuya Akiba, Edoardo Cetin
2025	J	`jnl`	KAME: Tandem Architecture for Enhancing Knowledge in Real-Time Speech-to-Speech Conversational AI. CoRR So Kuroki, Yotaro Kubo, Takuya Akiba, Yujin Tang
2025	J	`jnl`	Reimagining Agent-based Modeling with Large Language Model Agents via Shachi. CoRR So Kuroki, Yingtao Tian, Kou Misaki, Takashi Ikegami, Takuya Akiba, Yujin Tang
2025	J	`jnl`	String Seed of Thought: Prompting LLMs for Distribution-Faithful and Diverse Generation. CoRR Kou Misaki, Takuya Akiba
2025	A*	`conf`	TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models. ICLR Makoto Shing, Kou Misaki, Han Bao, Sho Yokoi, Takuya Akiba
2025	J	`jnl`	TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models. CoRR Makoto Shing, Kou Misaki, Han Bao, Sho Yokoi, Takuya Akiba
2025	J	`jnl`	Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Branching Tree Search. CoRR Kou Misaki, Yuichi Inoue, Yuki Imajuku, So Kuroki, Taishi Nakamura, Takuya Akiba
2024	J	`jnl`	Agent Skill Acquisition for Large Language Models via CycleQD. CoRR So Kuroki, Taishi Nakamura, Takuya Akiba, Yujin Tang
2024	J	`jnl`	Evolutionary Optimization of Model Merging Recipes. CoRR Takuya Akiba, Makoto Shing, Yujin Tang, Qi Sun, David Ha
2021	—	`conf`	MN-Core - A Highly Efficient and Scalable Approach to Deep Learning. VLSI Circuits Ken Namura, Johannes Maximilian Kühn, Tohru Adachi, H. Imachi, H. Kaneko, T. Kato, Go Watanabe, Naoto Tanaka, S. Kashihara, Hiroshi Miyashita, Y. Tomonaga, Ryosuke Okuta, Takuya Akiba, Brian Vogel, S. Kitajo, F. Osawa, K. Takahashi, Y. Takatsukasa, K. Mizumaru, Takuya Yamauchi, J. Ono, A. Takahashi, Tanvir Ahmed, Y. Doi, K. Hiraki, Jun Makino
2020	—	`conf`	Online-Codistillation Meets LARS, Going beyond the Limit of Data Parallelism in Deep Learning. DLS@SC Shogo Murai, Hiroaki Mikami, Masanori Koyama, Shuji Suzuki, Takuya Akiba
2019	A*	`conf`	A Graph Theoretic Framework of Recomputation Algorithms for Memory-Efficient Backpropagation. NeurIPS Mitsuru Kusumoto, Takuya Inoue, Gentaro Watanabe, Takuya Akiba, Masanori Koyama
2019	J	`jnl`	A Graph Theoretic Framework of Recomputation Algorithms for Memory-Efficient Backpropagation. CoRR Mitsuru Kusumoto, Takuya Inoue, Gentaro Watanabe, Takuya Akiba, Masanori Koyama
2019	A*	`conf`	Chainer: A Deep Learning Framework for Accelerating the Research Cycle. KDD Seiya Tokui, Ryosuke Okuta, Takuya Akiba, Yusuke Niitani, Toru Ogawa, Shunta Saito, Shuji Suzuki, Kota Uenishi, Brian Vogel, Hiroyuki Yamazaki Vincent
2019	J	`jnl`	Chainer: A Deep Learning Framework for Accelerating the Research Cycle. CoRR Seiya Tokui, Ryosuke Okuta, Takuya Akiba, Yusuke Niitani, Toru Ogawa, Shunta Saito, Shuji Suzuki, Kota Uenishi, Brian Vogel, Hiroyuki Yamazaki Vincent
2019	A*	`conf`	Optuna: A Next-generation Hyperparameter Optimization Framework. KDD Takuya Akiba, Shotaro Sano, Toshihiko Yanase, Takeru Ohta, Masanori Koyama
2019	J	`jnl`	Optuna: A Next-generation Hyperparameter Optimization Framework. CoRR Takuya Akiba, Shotaro Sano, Toshihiko Yanase, Takeru Ohta, Masanori Koyama
2019	A*	`conf`	Sampling Techniques for Large-Scale Object Detection From Sparsely Annotated Objects. CVPR Yusuke Niitani, Takuya Akiba, Tommi Kerola, Toru Ogawa, Shotaro Sano, Shuji Suzuki
2019	J	`jnl`	Shakedrop Regularization for Deep Residual Learning. IEEE Access Yoshihiro Yamada, Masakazu Iwamura, Takuya Akiba, Koichi Kise
2019	J	`jnl`	Team PFDet's Methods for Open Images Challenge 2019. CoRR Yusuke Niitani, Toru Ogawa, Shuji Suzuki, Takuya Akiba, Tommi Kerola, Kohei Ozaki, Shotaro Sano
2018	J	`jnl`	Adversarial Attacks and Defences Competition. CoRR Alexey Kurakin, Ian J. Goodfellow, Samy Bengio, Yinpeng Dong, Fangzhou Liao, Ming Liang, Tianyu Pang, Jun Zhu, Xiaolin Hu, Cihang Xie, Jianyu Wang, Zhishuai Zhang, Zhou Ren, Alan L. Yuille, Sangxia Huang, Yao Zhao, Yuzhe Zhao, Zhonglin Han, Junjiajia Long, Yerkebulan Berdibekov, Takuya Akiba, Seiya Tokui, Motoki Abe
2018	J	`jnl`	PFDet: 2nd Place Solution to Open Images Challenge 2018 Object Detection Track. CoRR Takuya Akiba, Tommi Kerola, Yusuke Niitani, Toru Ogawa, Shotaro Sano, Shuji Suzuki
2018	J	`jnl`	Sampling Techniques for Large-Scale Object Detection from Sparsely Annotated Objects. CoRR Yusuke Niitani, Takuya Akiba, Tommi Kerola, Toru Ogawa, Shotaro Sano, Shuji Suzuki
2018	—	`conf`	Variance-based Gradient Compression for Efficient Distributed Deep Learning. ICLR (Workshop) Yusuke Tsuzuku, Hiroto Imachi, Takuya Akiba
2018	J	`jnl`	Variance-based Gradient Compression for Efficient Distributed Deep Learning. CoRR Yusuke Tsuzuku, Hiroto Imachi, Takuya Akiba
2017	J	`jnl`	BDD-Constrained A IEICE Trans. Inf. Syst. Fumito Takeuchi, Masaaki Nishino, Norihito Yasuda, Takuya Akiba, Shin-ichi Minato, Masaaki Nagata
2017	—	`conf`	BDD-Constrained A* Search: A Fast Method for Solving Constrained DAG Shortest-Path Problems. AAAI Workshops Fumito Takeuchi, Masaaki Nishino, Norihito Yasuda, Takuya Akiba, Shin-ichi Minato, Masaaki Nagata
2017	J	`jnl`	ChainerMN: Scalable Distributed Deep Learning Framework. CoRR Takuya Akiba, Keisuke Fukuda, Shuji Suzuki
2017	J	`jnl`	Extremely Large Minibatch SGD: Training ResNet-50 on ImageNet in 15 Minutes. CoRR Takuya Akiba, Shuji Suzuki, Keisuke Fukuda
2017	A*	`conf`	Random-Radius Ball Method for Estimating Closeness Centrality. AAAI Wataru Inariba, Takuya Akiba, Yuichi Yoshida
2016	J	`jnl`	Branch-and-reduce exponential/FPT algorithms in practice: A case study of vertex cover. Theor. Comput. Sci. Takuya Akiba, Yoichi Iwata
2016	A*	`conf`	Compact and Scalable Graph Neighborhood Sketching. KDD Takuya Akiba, Yosuke Yano
2016	A*	`conf`	Cut Tree Construction from Massive Graphs. ICDM Takuya Akiba, Yoichi Iwata, Yosuke Sameshima, Naoto Mizuno, Yosuke Yano
2016	J	`jnl`	Cut Tree Construction from Massive Graphs. CoRR Takuya Akiba, Yoichi Iwata, Yosuke Sameshima, Naoto Mizuno, Yosuke Yano
2016	J	`jnl`	Dynamic Influence Analysis in Evolving Networks. Proc. VLDB Endow. Naoto Ohsaka, Takuya Akiba, Yuichi Yoshida, Ken-ichi Kawarabayashi
2016	A*	`conf`	Efficient Algorithms for Spanning Tree Centrality. IJCAI Takanori Hayashi, Takuya Akiba, Yuichi Yoshida
2016	A*	`conf`	Fractality of Massive Graphs: Scalable Analysis with Sketch-Based Box-Covering Algorithm. ICDM Takuya Akiba, Kenko Nakamura, Taro Takaguchi
2016	J	`jnl`	Fractality of Massive Graphs: Scalable Analysis with Sketch-Based Box-Covering Algorithm. CoRR Takuya Akiba, Kenko Nakamura, Taro Takaguchi
2016	A	`conf`	Fully Dynamic Shortest-Path Distance Query Acceleration on Massive Networks. CIKM Takanori Hayashi, Takuya Akiba, Ken-ichi Kawarabayashi
2016	A	`conf`	Hierarchical and Dynamic CIKM Takuya Akiba, Yosuke Yano, Naoto Mizuno
2016	—	`conf`	Integer programming approach for directed minimum spanning tree problem on temporal graphs. NDA@SIGMOD Takuto Ikuta, Takuya Akiba
2015	B	`conf`	An Exact Algorithm for Diameters of Large Real Directed Graphs. SEA Takuya Akiba, Yoichi Iwata, Yuki Kawata
2015	A	`conf`	Branch-and-Reduce Exponential/FPT Algorithms in Practice: A Case Study of Vertex Cover. ALENEX Takuya Akiba, Yoichi Iwata
2015	A*	`conf`	Efficient Top-k Shortest-Path Distance Queries on Large Networks by Pruned Landmark Labeling. AAAI Takuya Akiba, Takanori Hayashi, Nozomi Nori, Yoichi Iwata, Yuichi Yoshida
2015	J	`jnl`	Fully Dynamic Betweenness Centrality Maintenance on Massive Networks. Proc. VLDB Endow. Takanori Hayashi, Takuya Akiba, Yuichi Yoshida
2014	J	`jnl`	Branch-and-Reduce Exponential/FPT Algorithms in Practice: A Case Study of Vertex Cover. CoRR Takuya Akiba, Yoichi Iwata
2014	J	`jnl`	Computing Personalized PageRank Quickly by Exploiting Graph Structures. Proc. VLDB Endow. Takanori Maehara, Takuya Akiba, Yoichi Iwata, Ken-ichi Kawarabayashi
2014	A*	`conf`	Dynamic and historical shortest-path distance queries on large evolving networks by pruned landmark labeling. WWW Takuya Akiba, Yoichi Iwata, Yuichi Yoshida
2014	A	`conf`	Fast Shortest-path Distance Queries on Road Networks by Pruned Highway Labeling. ALENEX Takuya Akiba, Yoichi Iwata, Ken-ichi Kawarabayashi, Yuki Kawata
2014	A*	`conf`	Fast and Accurate Influence Maximization on Large Networks with Pruned Monte-Carlo Simulations. AAAI Naoto Ohsaka, Takuya Akiba, Yuichi Yoshida, Ken-ichi Kawarabayashi
2014	A*	`conf`	Network structural analysis via core-tree-decomposition Publication of this article pending inquiry. KDD Takuya Akiba, Takanori Maehara, Ken-ichi Kawarabayashi
2014	—	`conf`	Pruned labeling algorithms: fast, exact, dynamic, simple and general indexing scheme for shortest-path queries. WWW (Companion Volume) Takuya Akiba
2013	J	`jnl`	Fast Exact Shortest-Path Distance Queries on Large Networks by Pruned Landmark Labeling CoRR Takuya Akiba, Yoichi Iwata, Yuichi Yoshida
2013	A	`conf`	Fast and scalable reachability queries on graphs by pruned labeling with landmarks and paths. CIKM Yosuke Yano, Takuya Akiba, Yoichi Iwata, Yuichi Yoshida
2013	—	`conf`	Fast exact shortest-path distance queries on large networks by pruned landmark labeling. SIGMOD Conference Takuya Akiba, Yoichi Iwata, Yuichi Yoshida
2013	A	`conf`	Linear-time enumeration of maximal K-edge-connected subgraphs in large networks by random contraction. CIKM Takuya Akiba, Yoichi Iwata, Yuichi Yoshida
2012	B	`conf`	Shortest-path queries for complex networks: exploiting low tree-width outside the core. EDBT Takuya Akiba, Christian Sommer, Ken-ichi Kawarabayashi