KY
Kentaro Yoshioka
cs.ARcs.CVcs.LGcs.ROcs.CRcs.AIcs.OH
On Valency
published · living versionsW_sng42shk·v1 · currentpublished
Towards Real-Time Full-Waveform LiDAR Transformers via Intensity-Guided Token Reduction and Physics-Aware Augmentation
with Kotaro Oishi, Kazuma Ikeda, Ryosei Hara, Ryo Yoshida +1
1 version
Preprints & journals
25 papers in the corpus · 2018–2026The Era of Vibe Tapeout: Dark Age or Golden Age for Analog Circuit Design?2610.15240v1 · Kentaro Yoshioka2026 · 0 citationsarXiv
A Secure dToF LiDAR SoC with Dual-Domain Fingerprinting and Event-Driven AFE Circuit Achieving Sensor-Level Attack Resilience2610.03562v1 · Risa Nonaka, Ryoya Matsuno, Shota Nagai et al.2026 · 0 citationsarXiv
Illusion of Depth: Revealing Hidden Stereo Vision Vulnerabilities in Depth Estimation2609.16336v1 · Sri Hrushikesh Varma Bhupathiraju, Tetsu Ishizue, Nicholas U. Costagliola et al.2026 · 0 citationsarXiv
Detect in Any Scene: An Agentic Framework for Object Detection with Experience-Aware Reasoning2605.31174v1 · Wenlun Zhang, Jun Yin, Kentaro Yoshioka2026 · 0 citationsarXiv
Neural Reconstruction of LiDAR Point Clouds under Jamming Attacks via Full-Waveform Representation and Simultaneous Laser Sensing2604.00371v1 · Ryo Yoshida, Takami Sato, Wenlun Zhang et al.2026 · 0 citationsarXiv
Ghost-FWL: A Large-Scale Full-Waveform LiDAR Dataset for Ghost Detection and Removal2603.28224v1 · Kazuma Ikeda, Ryosei Hara, Rokuto Nagata et al.2026 · 0 citationsarXiv
MirrorDrift: Actuated Mirror-Based Attacks on LiDAR SLAM2603.11364v1 · Rokuto Nagata, Kenji Koide, Kazuma Ikeda et al.2026 · 0 citationsarXiv
D-SLAMSpoof: An Environment-Agnostic LiDAR Spoofing Attack using Dynamic Point Cloud Injection2603.11365v1 · Rokuto Nagata, Kenji Koide, Kazuma Ikeda et al.2026 · 0 citationsarXiv
D4C: Data-Free Quantization for Contrastive Language-Image Pre-training Models2511.15411v2 · Wenlun Zhang, Yunshan Zhong, Zihao Ding et al.2025 · 0 citationsarXiv
BitROM: Weight Reload-Free CiROM Architecture Towards Billion-Parameter 1.58-bit LLM Inference2509.08542v1 · Wenlun Zhang, Xinyu Li, Shimpei Ando et al.2025 · 0 citationsarXiv
BasketLiDAR: The First LiDAR-Camera Multimodal Dataset for Professional Basketball MOT2508.15299v1 · Ryunosuke Hayashi, Kohei Torimi, Rokuto Nagata et al.2025 · 0 citationsarXiv
AHCQ-SAM: Toward Accurate and Hardware-Compatible Post-Training Segment Anything Model Quantization2503.03088v4 · Wenlun Zhang, Yunshan Zhong, Weiqi Yan et al.2025 · 0 citationsarXiv
SLAMSpoof: Practical LiDAR Spoofing Attacks on Localization Systems Guided by Scan Matching Vulnerability Analysis2502.13641v1 · Rokuto Nagata, Kenji Koide, Yuki Hayakawa et al.2025 · 3 citationsarXiv
LiSA: Leveraging Link Recommender to Attack Graph Neural Networks via Subgraph Injection2502.09271v3 · Wenlun Zhang, Enyan Dai, Kentaro Yoshioka2025 · 0 citationsPacific-Asia Conference on Knowledge Discovery and Data Mining 2025
ASiM: Modeling and Analyzing Inference Accuracy of SRAM-Based Analog CiM Circuits2411.11022v4 · Wenlun Zhang, Shimpei Ando, Yung-Chin Chen et al.2024 · 14 citationsarXiv
A Review of SRAM-based Compute-in-Memory Circuits2411.06079v2 · Kentaro Yoshioka, Shimpei Ando, Satomi Miyagi et al.2024 · 24 citationsarXiv
PACiM: A Sparsity-Centric Hybrid Compute-in-Memory Architecture via Probabilistic Approximation2408.16246v1 · Wenlun Zhang, Shimpei Ando, Yung-Chin Chen et al.2024 · 4 citationsIEEE/ACM International Conference on Computer-Aided Design (ICCAD 2024)
HALO-CAT: A Hidden Network Processor with Activation-Localized CIM Architecture and Layer-Penetrative Tiling2312.06086v1 · Yung-Chin Chen, Shimpei Ando, Daichi Fujiki et al.2023 · 0 citationsarXiv
OSA-HCIM: On-The-Fly Saliency-Aware Hybrid SRAM CIM with Dynamic Precision Configuration2308.15040v2 · Yung-Chin Chen, Shimpei Ando, Daichi Fujiki et al.2023 · 10 citationsarXiv
LiDAR Spoofing Meets the New-Gen: Capability Improvements, Broken Assumptions, and New Attack Strategies2303.10555v2 · Takami Sato, Yuki Hayakawa, Ryo Suzuki et al.2023 · 31 citationsNetwork and Distributed System Security (NDSS) Symposium 2024
An 818-TOPS/W CSNR-31dB SQNR-45dB 10-bit Capacitor-Reconfiguring Computing-in-Memory Macro with Software-Analog Co-Design for Transformers2302.06463v1 · Kentaro Yoshioka2023 · 0 citationsarXiv
Through the Looking Glass: Diminishing Occlusions in Robot Vision Systems with Mirror Reflections2108.13599v1 · Kentaro Yoshioka, Hidenori Okuni, Tuan Thanh Ta et al.2021 · 3 citationsarXiv
Dataset Culling: Towards Efficient Training Of Distillation-Based Domain Specific Models1902.00173v3 · Kentaro Yoshioka, Edward Lee, Simon Wong et al.2019 · 3 citationsarXiv
Training Domain Specific Models for Energy-Efficient Object Detection1811.02689v2 · Kentaro Yoshioka, Edward Lee, Mark Horowitz2018 · 0 citationsarXiv
PhaseMAC: A 14 TOPS/W 8bit GRO based Phase Domain MAC Circuit for In-Sensor-Computed Deep Learning Accelerators1808.09335v1 · Kentaro Yoshioka, Yosuke Toyama, Koichiro Ban et al.2018 · 8 citationsarXiv
Career total: 96 works. 25 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.