Tomoyuki Okuno

19 papers A* 4A 2Misc 1Journal 11Unranked 1

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	MoBiQuant: Mixture-of-Bits Quantization for Token-Adaptive Elastic LLMs. CoRR Dongwei Wang, Jinhee Kim, Seokho Han, Denis A. Gudovskiy, Yohei Nakata, Tomoyuki Okuno, KhayTze Peong, Kang Eun Jeon, Jong Hwan Ko, Yiran Chen, Huanrui Yang
2025	J	`jnl`	ODE CoRR Denis A. Gudovskiy, Wenzhao Zheng, Tomoyuki Okuno, Yohei Nakata, Kurt Keutzer
2025	A*	`conf`	SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference. ICML Yuan Zhang, Chun-Kai Fan, Junpeng Ma, Wenzhao Zheng, Tao Huang, Kuan Cheng, Denis A. Gudovskiy, Tomoyuki Okuno, Yohei Nakata, Kurt Keutzer, Shanghang Zhang
2024	J	`jnl`	ContextFlow++: Generalist-Specialist Flow-based Generative Models with Mixed-Variable Context Encoding. CoRR Denis A. Gudovskiy, Tomoyuki Okuno, Yohei Nakata
2024	A	`conf`	ContextFlow++: Generalist-Specialist Flow-based Generative Models with Mixed-variable Context Encoding. UAI Denis A. Gudovskiy, Tomoyuki Okuno, Yohei Nakata
2024	J	`jnl`	DFM: Interpolant-free Dual Flow Matching. CoRR Denis A. Gudovskiy, Tomoyuki Okuno, Yohei Nakata
2024	A*	`conf`	Efficient Deweahter Mixture-of-Experts with Uncertainty-Aware Feature-Wise Linear Modulation. AAAI Rongyu Zhang, Yulin Luo, Jiaming Liu, Huanrui Yang, Zhen Dong, Denis A. Gudovskiy, Tomoyuki Okuno, Yohei Nakata, Kurt Keutzer, Yuan Du, Shanghang Zhang
2024	J	`jnl`	Fisher-aware Quantization for DETR Detectors with Critical-category Objectives. CoRR Huanrui Yang, Yafeng Huang, Zhen Dong, Denis A. Gudovskiy, Tomoyuki Okuno, Yohei Nakata, Yuan Du, Kurt Keutzer, Shanghang Zhang
2024	J	`jnl`	SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference. CoRR Yuan Zhang, Chun-Kai Fan, Junpeng Ma, Wenzhao Zheng, Tao Huang, Kuan Cheng, Denis A. Gudovskiy, Tomoyuki Okuno, Yohei Nakata, Kurt Keutzer, Shanghang Zhang
2024	A*	`conf`	Split-Ensemble: Efficient OOD-aware Ensemble via Task and Model Splitting. ICML Anthony Chen, Huanrui Yang, Yulu Gan, Denis A. Gudovskiy, Zhen Dong, Haofan Wang, Tomoyuki Okuno, Yohei Nakata, Kurt Keutzer, Shanghang Zhang
2024	J	`jnl`	VeCAF: VLM-empowered Collaborative Active Finetuning with Training Objective Awareness. CoRR Rongyu Zhang, Zefan Cai, Huanrui Yang, Zidong Liu, Denis A. Gudovskiy, Tomoyuki Okuno, Yohei Nakata, Kurt Keutzer, Baobao Chang, Yuan Du, Li Du, Shanghang Zhang
2024	A*	`conf`	VeCAF: Vision-language Collaborative Active Finetuning with Training Objective Awareness. ACM Multimedia Rongyu Zhang, Zefan Cai, Huanrui Yang, Zidong Liu, Denis A. Gudovskiy, Tomoyuki Okuno, Yohei Nakata, Kurt Keutzer, Baobao Chang, Yuan Du, Li Du, Shanghang Zhang
2023	A	`conf`	Concurrent Misclassification and Out-of-Distribution Detection for Semantic Segmentation via Energy-Based Normalizing Flow. UAI Denis A. Gudovskiy, Tomoyuki Okuno, Yohei Nakata
2023	J	`jnl`	Concurrent Misclassification and Out-of-Distribution Detection for Semantic Segmentation via Energy-Based Normalizing Flow. CoRR Denis A. Gudovskiy, Tomoyuki Okuno, Yohei Nakata
2023	J	`jnl`	Efficient Deweather Mixture-of-Experts with Uncertainty-aware Feature-wise Linear Modulation. CoRR Rongyu Zhang, Yulin Luo, Jiaming Liu, Huanrui Yang, Zhen Dong, Denis A. Gudovskiy, Tomoyuki Okuno, Yohei Nakata, Kurt Keutzer, Yuan Du, Shanghang Zhang
2023	J	`jnl`	Split-Ensemble: Efficient OOD-aware Ensemble via Task and Model Splitting. CoRR Anthony Chen, Huanrui Yang, Yulu Gan, Denis A. Gudovskiy, Zhen Dong, Haofan Wang, Tomoyuki Okuno, Yohei Nakata, Shanghang Zhang, Kurt Keutzer
2022	J	`jnl`	Cross-Domain Object Detection with Mean-Teacher Transformer. CoRR Jinze Yu, Jiaming Liu, Xiaobao Wei, Haoyi Zhou, Yohei Nakata, Denis A. Gudovskiy, Tomoyuki Okuno, Jianxin Li, Kurt Keutzer, Shanghang Zhang
2022	—	`conf`	MTTrans: Cross-domain Object Detection with Mean Teacher Transformer. ECCV (9) Jinze Yu, Jiaming Liu, Xiaobao Wei, Haoyi Zhou, Yohei Nakata, Denis A. Gudovskiy, Tomoyuki Okuno, Jianxin Li, Kurt Keutzer, Shanghang Zhang
2021	Misc	`conf`	Lossless AI: Toward Guaranteeing Consistency between Inferences Before and After Quantization via Knowledge Distillation. MVA Tomoyuki Okuno, Yohei Nakata, Yasunori Ishii, Sotaro Tsukizawa