KO
Kei Ota
cs.ROcs.LGcs.AIcs.CVstat.MLcs.CGcs.CLcs.SYeess.SY
On Valency
published · living versionsW_6uwgxvck·v1 · currentpublished
AIRoA-0: Long-Horizon, Precise, Cross-Embodiment Manipulation from Handheld Data
with Yueh-Hua Wu, Hanlong Li, Hayata Yuasa, Jason Wang +15
1 version
Preprints & journals
22 papers in the corpus · 2019–2026RoboPace: Contact-Aware Time-Optimal Retiming for Action-Chunk Policies2610.09696v1 · Mimo Shirasaka, Takehiko Ohkawa, Takuya Okubo et al.2026 · 0 citationsarXiv
CounterAlign: Counterfactual Supervision for Vision-Language-Action Models2608.21740v1 · Haru Kondoh, Kei Ota, Asako Kanezaki et al.2026 · 0 citationsarXiv
Auditing Instruction-Trajectory Mismatches in Multimodal Robot Demonstrations2608.07895v1 · Simon Holk, Ryosuke Takanami, Tatsuya Matsushima et al.2026 · 0 citationsarXiv
See Less, Specify More: Visual Evidence Budgets for Generalizable VLAs2606.02735v2 · Yueh-Hua Wu, Tatsuya Matsushima, Kei Ota2026 · 0 citationsarXiv
Continuous Reasoning for Vision-Language-Action2606.00229v2 · Yueh-Hua Wu, Tatsuya Matsushima, Kei Ota2026 · 0 citationsarXiv
Simultaneous Extrinsic Contact and In-Hand Pose Estimation via Distributed Tactile Sensing2512.23856v1 · Mark Van der Merwe, Kei Ota, Dmitry Berenson et al.2025 · 0 citationsarXiv
Analytic Conditions for Differentiable Collision Detection in Trajectory Optimization2509.26459v1 · Akshay Jaitly, Devesh K. Jha, Kei Ota et al.2025 · 0 citationsarXiv
Learning Pivoting Manipulation with Force and Vision Feedback Using Optimization-based Demonstrations2508.01082v2 · Yuki Shirai, Kei Ota, Devesh K. Jha et al.2025 · 0 citationsarXiv
Modality Selection and Skill Segmentation via Cross-Modality Attention2504.14573v1 · Jiawei Jiang, Kei Ota, Devesh K. Jha et al.2025 · 1 citationarXiv
Zero-Shot Peg Insertion: Identifying Mating Holes and Estimating SE(2) Poses with Vision-Language Models2503.06026v1 · Masaru Yajima, Kei Ota, Asako Kanezaki et al.2025 · 2 citationsarXiv
Robust In-Hand Manipulation with Extrinsic Contacts2403.18960v1 · Boyuan Liang, Kei Ota, Masayoshi Tomizuka et al.2024 · 5 citationsarXiv
Tactile Estimation of Extrinsic Contact Patch for Stable Placement2309.14552v2 · Kei Ota, Devesh K. Jha, Krishna Murthy Jatavallabhula et al.2023 · 7 citationsarXiv
Style-transfer based Speech and Audio-visual Scene Understanding for Robot Action Sequence Acquisition from Videos2306.15644v1 · Chiori Hori, Puyuan Peng, David Harwath et al.2023 · 6 citationsarXiv
H-SAUR: Hypothesize, Simulate, Act, Update, and Repeat for Understanding Object Articulations from Interactions2210.12521v1 · Kei Ota, Hsiao-Yu Tung, Kevin A. Smith et al.2022 · 3 citationsarXiv
Object Memory Transformer for Object Goal Navigation2203.14708v1 · Rui Fukushima, Kei Ota, Asako Kanezaki et al.2022 · 35 citationsarXiv
OPIRL: Sample Efficient Off-Policy Inverse Reinforcement Learning via Distribution Matching2109.04307v2 · Hana Hoshino, Kei Ota, Asako Kanezaki et al.2021 · 8 citationsarXiv
Training Larger Networks for Deep Reinforcement Learning2102.07920v1 · Kei Ota, Devesh K. Jha, Asako Kanezaki2021 · 11 citationsarXiv
Data-Efficient Learning for Complex and Real-Time Physical Problem Solving using Augmented Simulation2011.07193v2 · Kei Ota, Devesh K. Jha, Diego Romeres et al.2020 · 16 citationsarXiv
Deep Reactive Planning in Dynamic Environments2011.00155v2 · Kei Ota, Devesh K. Jha, Tadashi Onishi et al.2020 · 5 citationsarXiv
Can Increasing Input Dimensionality Improve Deep Reinforcement Learning?2003.01629v2 · Kei Ota, Tomoaki Oiki, Devesh K. Jha et al.2020 · 26 citationsarXiv
Efficient Exploration in Constrained Environments with Goal-Oriented Reference Path2003.01641v1 · Kei Ota, Yoko Sasaki, Devesh K. Jha et al.2020 · 25 citationsarXiv
Trajectory Optimization for Unknown Constrained Systems using Reinforcement Learning1903.05751v2 · Kei Ota, Devesh K. Jha, Tomoaki Oiki et al.2019 · 33 citationsarXiv
Career total: 28 works. 22 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.