Yasuyuki Okoshi

19 papers A* 3Journal 11Unranked 5
YearRankTypeTitle / Venue / Authors
2026 A* conf
AQPIM: Breaking the PIM Capacity Wall for LLMs with in-Memory Activation Quantization.
HPCA
Kosuke Matsushima, Yasuyuki Okoshi, Masato Motomura, Daichi Fujiki
2026 A* conf
The Strong Lottery Ticket Hypothesis for Multi-Head Attention Mechanisms.
AAAI
Hikari Otsuka, Daiki Chijiwa, Yasuyuki Okoshi, Daichi Fujiki, Susumu Takeuchi, Masato Motomura
2025 J jnl
Binary Quadratic Quantization: Beyond First-Order Quantization for Real-Valued Matrix Compression.
CoRR
Kyo Kuroki, Yasuyuki Okoshi, Thiem Van Chu, Kazushi Kawamura, Masato Motomura
2025 J jnl
Partially Frozen Random Networks Contain Compact Strong Lottery Tickets.
Trans. Mach. Learn. Res.
Hikari Otsuka, Daiki Chijiwa, Ángel López García-Arias, Yasuyuki Okoshi, Kazushi Kawamura, Thiem Van Chu, Daichi Fujiki, Susumu Takeuchi, Masato Motomura
2025 J jnl
Rethinking Optimal Verification Granularity for Compute-Efficient Test-Time Scaling.
CoRR
Hao Mark Chen, Guanxi Lu, Yasuyuki Okoshi, Zhiwen Mo, Masato Motomura, Hongxiang Fan
2025 J jnl
The Strong Lottery Ticket Hypothesis for Multi-Head Attention Mechanisms.
CoRR
Hikari Otsuka, Daiki Chijiwa, Yasuyuki Okoshi, Daichi Fujiki, Susumu Takeuchi, Masato Motomura
2025 J jnl
TicketLLM: Next-Generation Sparse and Low-bit Transformers with Supermask-based Method.
Trans. Mach. Learn. Res.
Yasuyuki Okoshi, Hikari Otsuka, Daichi Fujiki, Masato Motomura
2025 J jnl
WhiteDwarf: A Holistic Co-Design Approach to Ultra-Compact Neural Inference Acceleration.
IEEE Access
Ángel López García-Arias, Yasuyuki Okoshi, Jaehoon Yu, Junnosuke Suzuki, Hikari Otsuka, Kazushi Kawamura, Thiem Van Chu, Daichi Fujiki, Masato Motomura
2024 — conf
Exploiting N:M Sparsity in Quantized-Folded ResNets: Signed Multicoat Supermasks and Iterative Pruning-Quantization.
CANDAR
Akihiro Shioda, Ángel López García-Arias, Hikari Otsuka, Yuki Ichikawa, Yasuyuki Okoshi, Kazushi Kawamura, Thiem Van Chu, Daichi Fujiki, Masato Motomura
2024 J jnl
Partial Search in a Frozen Network is Enough to Find a Strong Lottery Ticket.
CoRR
Hikari Otsuka, Daiki Chijiwa, Ángel López García-Arias, Yasuyuki Okoshi, Kazushi Kawamura, Thiem Van Chu, Daichi Fujiki, Susumu Takeuchi, Masato Motomura
2024 J jnl
Pianissimo: A Sub-mW Class DNN Accelerator With Progressively Adjustable Bit-Precision.
IEEE Access
Junnosuke Suzuki, Jaehoon Yu, Mari Yasunaga, Ángel López García-Arias, Yasuyuki Okoshi, Shungo Kumazawa, Kota Ando, Kazushi Kawamura, Thiem Van Chu, Masato Motomura
2024 J jnl
Restricted Random Pruning at Initialization for High Compression Range.
Trans. Mach. Learn. Res.
Hikari Otsuka, Yasuyuki Okoshi, Ángel López García-Arias, Kazushi Kawamura, Thiem Van Chu, Daichi Fujiki, Masato Motomura
2024 — conf
WhiteDwarf: 12.24 TFLOPS/W 40 nm Versatile Neural Inference Engine for Ultra-Compact Execution of CNNs and MLPs Through Triple Unstructured Sparsity Exploitation and Triple Model Compression.
A-SSCC
Yasuyuki Okoshi, Ángel López García-Arias, Jaehoon Yu, Junnosuke Suzuki, Hikari Otsuka, Thiem Van Chu, Kazushi Kawamura, Daichi Fujiki, Masato Motomura
2023 — conf
Multicoated and Folded Graph Neural Networks With Strong Lottery Tickets.
LoG
Jiale Yan, Hiroaki Ito, Ángel López García-Arias, Yasuyuki Okoshi, Hikari Otsuka, Kazushi Kawamura, Thiem Van Chu, Masato Motomura
2023 J jnl
Multicoated and Folded Graph Neural Networks with Strong Lottery Tickets.
CoRR
Jiale Yan, Hiroaki Ito, Ángel López García-Arias, Yasuyuki Okoshi, Hikari Otsuka, Kazushi Kawamura, Thiem Van Chu, Masato Motomura
2023 — conf
Pianissimo: A Sub-mW Class DNN Accelerator with Progressive Bit-by-Bit Datapath Architecture for Adaptive Inference at Edge.
VLSI Technology and Circuits
Junnosuke Suzuki, Jaehoon Yu, Mari Yasunaga, Ángel López García-Arias, Yasuyuki Okoshi, Shungo Kumazawa, Kota Ando, Kazushi Kawamura, Thiem Van Chu, Masato Motomura
2023 J jnl
Recurrent Residual Networks Contain Stronger Lottery Tickets.
IEEE Access
Ángel López García-Arias, Yasuyuki Okoshi, Masanori Hashimoto, Masato Motomura, Jaehoon Yu
2022 — conf
Hiddenite: 4K-PE Hidden Network Inference 4D-Tensor Engine Exploiting On-Chip Model Construction Achieving 34.8-to-16.0TOPS/W for CIFAR-100 and ImageNet.
ISSCC
Kazutoshi Hirose, Jaehoon Yu, Kota Ando, Yasuyuki Okoshi, Ángel López García-Arias, Junnosuke Suzuki, Thiem Van Chu, Kazushi Kawamura, Masato Motomura
2022 A* conf
Multicoated Supermasks Enhance Hidden Networks.
ICML
Yasuyuki Okoshi, Ángel López García-Arias, Kazutoshi Hirose, Kota Ando, Kazushi Kawamura, Thiem Van Chu, Masato Motomura, Jaehoon Yu