Weakly-Supervised Disentangled Representation Learning via Filter-Based Adaptive Swapping.

Hongpeng Cao

Zhenyu Zong Qidi Wang Simon Yu Hongpeng Cao Yanbing Mao Han Zhao 0002 Lui Sha Huajie Shao Weakly-Supervised Disentangled Representation Learning via Filter-Based Adaptive Swapping. 2026 2026 Trans. Mach. Learn. Res. https://openreview.net/forum?id=K69rKKozZU db/journals/tmlr/tmlr2026.html#ZongWYCMZSS26 streams/journals/tmlr

Liqun Zhao Keyan Miao Hongpeng Cao Konstantinos Gatsis Antonis Papachristodoulou NLBAC: A neural ODE-based algorithm for state-wise stable and safe reinforcement learning. 130041 2025 638 Neurocomputing https://doi.org/10.1016/j.neucom.2025.130041 db/journals/ijon/ijon638.html#ZhaoMCGP25 streams/journals/ijon

Yihao Cai Yanbing Mao Lui Sha Hongpeng Cao Marco Caccamo Runtime Learning of Quadruped Robots in Wild Environments. 2025 March abs/2503.04794 CoRR https://doi.org/10.48550/arXiv.2503.04794 db/journals/corr/corr2503.html#abs-2503-04794 streams/journals/corr

Yuliang Gu Hongpeng Cao Marco Caccamo Naira Hovakimyan Bregman Centroid Guided Cross-Entropy Method. 2025 June abs/2506.02205 CoRR https://doi.org/10.48550/arXiv.2506.02205 db/journals/corr/corr2506.html#abs-2506-02205 streams/journals/corr

Yuliang Gu Hongpeng Cao Marco Caccamo Naira Hovakimyan Observations Meet Actions: Learning Control-Sufficient Representations for Robust Policy Generalization. 2025 July abs/2507.19437 CoRR https://doi.org/10.48550/arXiv.2507.19437 db/journals/corr/corr2507.html#abs-2507-19437 streams/journals/corr

Hongpeng Cao Yanbing Mao Lui Sha Marco Caccamo Physics-Regulated Deep Reinforcement Learning: Invariant Embeddings. 2024 ICLR https://openreview.net/forum?id=5Dwqu5urzs conf/iclr/2024 db/conf/iclr/iclr2024.html#CaoMSC24 Mirco Theile Hongpeng Cao Marco Caccamo Alberto L. Sangiovanni-Vincentelli Equivariant Ensembles and Regularization for Reinforcement Learning in Map-based Path Planning. 14164-14171 2024 IROS https://doi.org/10.1109/IROS58592.2024.10801688 conf/iros/2024 db/conf/iros/iros2024.html#TheileCCS24

Mirco Theile Hongpeng Cao Marco Caccamo Alberto L. Sangiovanni-Vincentelli Equivariant Ensembles and Regularization for Reinforcement Learning in Map-based Path Planning. 2024 abs/2403.12856 CoRR https://doi.org/10.48550/arXiv.2403.12856 db/journals/corr/corr2403.html#abs-2403-12856

Yihao Cai Hongpeng Cao Yanbing Mao Lui Sha Marco Caccamo Simplex-enabled Safe Continual Learning Machine. 2024 abs/2409.05898 CoRR https://doi.org/10.48550/arXiv.2409.05898 db/journals/corr/corr2409.html#abs-2409-05898 streams/journals/corr

Hongpeng Cao Yanbing Mao Lui Sha Marco Caccamo Physics-model-guided Worst-case Sampling for Safe Reinforcement Learning. 2024 abs/2412.13224 CoRR https://doi.org/10.48550/arXiv.2412.13224 db/journals/corr/corr2412.html#abs-2412-13224 streams/journals/corr

Hongpeng Cao Lukas Dirnberger Daniele Bernardini 0002 Cristina Piazza Marco Caccamo 6IMPOSE: bridging the reality gap in 6D pose estimation for robotic grasping. 2023 October 10 Frontiers Robotics AI https://doi.org/10.3389/frobt.2023.1176492 db/journals/firai/firai10.html#CaoDBPC23

Bingzhuo Zhong Hongpeng Cao Majid Zamani 0001 Marco Caccamo Towards Safe AI: Sandboxing DNNs-Based Controllers in Stochastic Games. 15340-15349 2023 AAAI https://doi.org/10.1609/aaai.v37i12.26789 conf/aaai/2023 db/conf/aaai/aaai2023.html#ZhongC0C23 Hongpeng Cao Yanbing Mao Lui Sha Marco Caccamo Physics-Model-Regulated Deep Reinforcement Learning Towards Safety & Stability Guarantees. 8306-8311 2023 CDC https://doi.org/10.1109/CDC49753.2023.10383560 conf/cdc/2023 db/conf/cdc/cdc2023.html#CaoMSC23 Junjie Ming Daniel Bargmann Hongpeng Cao Marco Caccamo Flexible Gear Assembly with Visual Servoing and Force Feedback. 8276-8282 2023 IROS https://doi.org/10.1109/IROS55552.2023.10341833 db/conf/iros/iros2023.html#MingBCC23

Junjie Ming Daniel Bargmann Hongpeng Cao Marco Caccamo Flexible Gear Assembly With Visual Servoing and Force Feedback. 2023 abs/2303.03153 CoRR https://doi.org/10.48550/arXiv.2303.03153 db/journals/corr/corr2303.html#abs-2303-03153

Hongpeng Cao Yanbing Mao Lui Sha Marco Caccamo Physical Deep Reinforcement Learning Towards Safety Guarantee. 2023 abs/2303.16860 CoRR https://doi.org/10.48550/arXiv.2303.16860 db/journals/corr/corr2303.html#abs-2303-16860

Hongpeng Cao Yanbing Mao Lui Sha Marco Caccamo Physical Deep Reinforcement Learning: Safety and Unknown Unknowns. 2023 abs/2305.16614 CoRR https://doi.org/10.48550/arXiv.2305.16614 db/journals/corr/corr2305.html#abs-2305-16614

Hongpeng Cao Mirco Theile Federico G. Wyrwal Marco Caccamo Cloud-Edge Training Architecture for Sim-to-Real Deep Reinforcement Learning. 9363-9370 2022 IROS https://doi.org/10.1109/IROS47612.2022.9981565 conf/iros/2022 db/conf/iros/iros2022.html#CaoTWC22

Hongpeng Cao Mirco Theile Federico G. Wyrwal Marco Caccamo Cloud-Edge Training Architecture for Sim-to-Real Deep Reinforcement Learning. 2022 abs/2203.02230 CoRR https://doi.org/10.48550/arXiv.2203.02230 db/journals/corr/corr2203.html#abs-2203-02230

Bingzhuo Zhong Hongpeng Cao Majid Zamani 0001 Marco Caccamo Sandboxing (AI-based) Unverified Controllers in Stochastic Games: An Abstraction-based Approach with Safe-visor Architecture. 2022 abs/2203.14924 CoRR https://doi.org/10.48550/arXiv.2203.14924 db/journals/corr/corr2203.html#abs-2203-14924

Hongpeng Cao Lukas Dirnberger Daniele Bernardini 0002 Cristina Piazza Marco Caccamo Learning 6D Pose Estimation from Synthetic RGBD Images for Robotic Applications. 2022 abs/2208.14288 CoRR https://doi.org/10.48550/arXiv.2208.14288 db/journals/corr/corr2208.html#abs-2208-14288

Bingzhuo Zhong Abolfazl Lavaei Hongpeng Cao Majid Zamani 0001 Marco Caccamo Safe-visor Architecture for Sandboxing (AI-based) Unverified Controllers in Stochastic Cyber-Physical Systems. 2021 abs/2102.05490 CoRR https://arxiv.org/abs/2102.05490 db/journals/corr/corr2102.html#abs-2102-05490

Daniel Bargmann Daniele Bernardini 0002 Marco Caccamo Yihao Cai Lukas Dirnberger Konstantinos Gatsis Yuliang Gu Naira Hovakimyan Abolfazl Lavaei Yanbing Mao Keyan Miao Junjie Ming Antonis Papachristodoulou Cristina Piazza Alberto L. Sangiovanni-Vincentelli Lui Sha Huajie Shao Mirco Theile Qidi Wang Federico G. Wyrwal Simon Yu Majid Zamani 0001 Han Zhao 0002 Liqun Zhao Bingzhuo Zhong Zhenyu Zong