Publications

4,075 major publications by members of the MERL staff.


  •  Wang, Y., Liu, J., Koike-Akino, T., "Temper and Tilt Lead to SLOP: Reward Hacking Mitigation with Inference-Time Alignment", arXiv, May 2026.
    BibTeX arXiv
    • @article{Wang2026may,
    • author = {Wang, Ye and Liu, Jing and Koike-Akino, Toshiaki},
    • title = {{Temper and Tilt Lead to SLOP: Reward Hacking Mitigation with Inference-Time Alignment}},
    • journal = {arXiv},
    • year = 2026,
    • month = may,
    • url = {https://arxiv.org/abs/2605.13537}
    • }
  •  Mumcu, F., Jones, M.J., Cherian, A., Yilmaz, Y., "Is Video Anomaly Detection Misframed? Evidence from LLM-Based and Multi-Scene Models", arXiv, May 2026.
    BibTeX arXiv
    • @article{Mumcu2026may,
    • author = {Mumcu, Furkan and Jones, Michael J. and Cherian, Anoop and Yilmaz, Yasin},
    • title = {{Is Video Anomaly Detection Misframed? Evidence from LLM-Based and Multi-Scene Models}},
    • journal = {arXiv},
    • year = 2026,
    • month = may,
    • url = {https://arxiv.org/abs/2605.12725}
    • }
  •  Richter, J., Masuyama, Y., Boeddeker, C., Edo, T., Wichern, G., Le Roux, J., "Predictive-Generative Drift Decomposition for Speech Enhancement and Separation", arXiv, May 2026.
    BibTeX arXiv
    • @article{Richter2026may,
    • author = {{Richter, Julius and Masuyama, Yoshiki and Boeddeker, Christoph and Edo, Takahiro and Wichern, Gordon and Le Roux, Jonathan}},
    • title = {{Predictive-Generative Drift Decomposition for Speech Enhancement and Separation}},
    • journal = {arXiv},
    • year = 2026,
    • month = may,
    • url = {https://arxiv.org/abs/2605.06189}
    • }
  •  Ju, R., Zhang, D., Wang, Y., Zhou, M., Cao, Z., "3D-Dynamic Safety Envelope-Based Control Strategy for Hyper-Redundant Manipulator Moving in Confined Space", IEEE Transactions on Industrial Electronics, DOI: 10.1109/​TIE.2026.3682383, May 2026.
    BibTeX TR2026-105 PDF
    • @article{Ju2026may,
    • author = {Ju, Renjie and Zhang, Dong and Wang, Yebin and Zhou, Mengchu and Cao, Zhengcai},
    • title = {{3D-Dynamic Safety Envelope-Based Control Strategy for Hyper-Redundant Manipulator Moving in Confined Space}},
    • journal = {IEEE Transactions on Industrial Electronics},
    • year = 2026,
    • month = may,
    • doi = {10.1109/TIE.2026.3682383},
    • url = {https://www.merl.com/publications/TR2026-105}
    • }
  •  Cherian, A., Corcodel, R., Jain, S., Romeres, D., "LLMPhy: Parameter-Identifiable Physical Reasoning Combining Large Language Models and Physics Engines", International Conference on Artificial Intelligence and Statistics (AISTATS), May 2026.
    BibTeX TR2026-052 PDF Data Software
    • @inproceedings{Cherian2026may,
    • author = {Cherian, Anoop and Corcodel, Radu and Jain, Siddarth and Romeres, Diego},
    • title = {{LLMPhy: Parameter-Identifiable Physical Reasoning Combining Large Language Models and Physics Engines}},
    • booktitle = {International Conference on Artificial Intelligence and Statistics (AISTATS)},
    • year = 2026,
    • month = may,
    • url = {https://www.merl.com/publications/TR2026-052}
    • }
  •  Tandi, K., Ali, W.H., Rapp, J., Mansour, H., "Single View Camera-Based Dynamic Airflow Sensing", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2026.
    BibTeX TR2026-038 PDF
    • @inproceedings{Tandi2026may,
    • author = {Tandi, Kevin and Ali, Wael H. and Rapp, Joshua and Mansour, Hassan},
    • title = {{Single View Camera-Based Dynamic Airflow Sensing}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2026,
    • month = may,
    • url = {https://www.merl.com/publications/TR2026-038}
    • }
  •  Aihara, R., Masuyama, Y., Paissan, F., Germain, F.G., Wichern, G., Le Roux, J., "SUNAC: Source-aware Unified Neural Audio Codec", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP55912.2026.11461849, May 2026, pp. 14427-14431.
    BibTeX TR2026-032 PDF
    • @inproceedings{Aihara2026may,
    • author = {Aihara, Ryo and Masuyama, Yoshiki and Paissan, Francesco and Germain, François G and Wichern, Gordon and {Le Roux}, Jonathan},
    • title = {{SUNAC: Source-aware Unified Neural Audio Codec}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2026,
    • pages = {14427--14431},
    • month = may,
    • doi = {10.1109/ICASSP55912.2026.11461849},
    • url = {https://www.merl.com/publications/TR2026-032}
    • }
  •  Han, J., Wang, R., Masuyama, Y., Delcroix, M., Rohdin, J., Du, J., Burget, L., "Spatially Aware Self-Supervised Models for Multi-Channel Neural Speaker Diarization", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP55912.2026.11463023, May 2026, pp. 17447-17451.
    BibTeX TR2026-047 PDF
    • @inproceedings{Han2026may,
    • author = {Han, Jiangyu and Wang, Ruoyu and Masuyama, Yoshiki and Delcroix, Marc and Rohdin, Johan and Du, Jun and Burget, Lukáš},
    • title = {{Spatially Aware Self-Supervised Models for Multi-Channel Neural Speaker Diarization}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2026,
    • pages = {17447--17451},
    • month = may,
    • doi = {10.1109/ICASSP55912.2026.11463023},
    • url = {https://www.merl.com/publications/TR2026-047}
    • }
  •  Kato, S., Wang, P., Fujihashi, T., Markham, A., "Heatmap-to-SMPL Multi-View Radar Transformer for Multi-Person 3D Pose Estimation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP55912.2026.11463668, May 2026.
    BibTeX TR2026-040 PDF
    • @inproceedings{Kato2026may,
    • author = {Kato, Sorachi and Wang, Pu and Fujihashi, Takuya and Markham, Andrew},
    • title = {{Heatmap-to-SMPL Multi-View Radar Transformer for Multi-Person 3D Pose Estimation}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2026,
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP55912.2026.11463668},
    • issn = {2379-190X},
    • isbn = {979-8-3315-6701-9},
    • url = {https://www.merl.com/publications/TR2026-040}
    • }
  •  Masuyama, Y., Germain, F.G., Wichern, G., Hori, C., Le Roux, J., "Velocity Potential Neural Field for Efficient Ambisonics Impulse Response Modeling", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP55912.2026.11460631, May 2026, pp. 22582-22586.
    BibTeX TR2026-033 PDF
    • @inproceedings{Masuyama2026may,
    • author = {Masuyama, Yoshiki and Germain, François G and Wichern, Gordon and Hori, Chiori and {Le Roux}, Jonathan},
    • title = {{Velocity Potential Neural Field for Efficient Ambisonics Impulse Response Modeling}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2026,
    • pages = {22582--22586},
    • month = may,
    • doi = {10.1109/ICASSP55912.2026.11460631},
    • url = {https://www.merl.com/publications/TR2026-033}
    • }
  •  Masuyama, Y., Saijo, K., Paissan, F., Han, J., Delcroix, M., Aihara, R., Germain, F.G., Wichern, G., Le Roux, J., "FlexIO: Flexible Single- and Multi-Channel Speech Separation and Enhancement", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP55912.2026.11462393, May 2026, pp. 14417-14421.
    BibTeX TR2026-034 PDF
    • @inproceedings{Masuyama2026may2,
    • author = {Masuyama, Yoshiki and Saijo, Kohei and Paissan, Francesco and Han, Jiangyu and Delcroix, Marc and Aihara, Ryo and Germain, François G and Wichern, Gordon and {Le Roux}, Jonathan},
    • title = {{FlexIO: Flexible Single- and Multi-Channel Speech Separation and Enhancement}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2026,
    • pages = {14417--14421},
    • month = may,
    • doi = {10.1109/ICASSP55912.2026.11462393},
    • url = {https://www.merl.com/publications/TR2026-034}
    • }
  •  Takahashi, R., Mansour, H., Boufounos, P.T., "DUAL-REGULARIZED ITERATIVE ADAPTIVE APPROACH FOR DOA SPECTRUM RECONSTRUCTION IN LIMITED ANGLE SECTOR", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2026.
    BibTeX TR2026-039 PDF
    • @inproceedings{Takahashi2026may,
    • author = {Takahashi, Ryuhei and Mansour, Hassan and Boufounos, Petros T.},
    • title = {{DUAL-REGULARIZED ITERATIVE ADAPTIVE APPROACH FOR DOA SPECTRUM RECONSTRUCTION IN LIMITED ANGLE SECTOR}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2026,
    • month = may,
    • url = {https://www.merl.com/publications/TR2026-039}
    • }
  •  Zhang, H., Ma, Y., Kitichotkul, R., Rapp, J., Boufounos, P.T., "ProxiCBO: A Consensus-based Method for Composite Optimization", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP55912.2026.11464733, May 2026, pp. 946-950.
    BibTeX TR2026-041 PDF
    • @inproceedings{Zhang2026may,
    • author = {Zhang, Haoyu and Ma, Yanting and Kitichotkul, Ruangrawee and Rapp, Joshua and Boufounos, Petros T.},
    • title = {{ProxiCBO: A Consensus-based Method for Composite Optimization}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2026,
    • pages = {946--950},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP55912.2026.11464733},
    • issn = {1520-6149},
    • isbn = {979-8-3315-6702-6},
    • url = {https://www.merl.com/publications/TR2026-041}
    • }
  •  Aihara, R., Masuyama, Y., Germain, F.G., Wichern, G., Le Roux, J., "Exploring Disentangled Neural Speech Codecs from Self-Supervised Representations", IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW), DOI: 10.1109/​ICASSP55912.2026.11462776, May 2026, pp. 21992-21996.
    BibTeX TR2026-035 PDF
    • @inproceedings{Aihara2026may2,
    • author = {Aihara, Ryo and Masuyama, Yoshiki and Germain, François G and Wichern, Gordon and {Le Roux}, Jonathan},
    • title = {{Exploring Disentangled Neural Speech Codecs from Self-Supervised Representations}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)},
    • year = 2026,
    • pages = {21992--21996},
    • month = may,
    • doi = {10.1109/ICASSP55912.2026.11462776},
    • url = {https://www.merl.com/publications/TR2026-035}
    • }
  •  Kitichotkul, R., Rapp, J., Ma, Y., Mansour, H., "Unambiguous Range Extension for1 Doppler Single-Photon Lidar", Optics Express, DOI: 10.1364/​OE.592528, Vol. 34, No. 9, pp. 15933-15952, May 2026.
    BibTeX TR2026-050 PDF
    • @article{Kitichotkul2026apr,
    • author = {Kitichotkul, Ruangrawee and Rapp, Joshua and Ma, Yanting and Mansour, Hassan},
    • title = {{Unambiguous range extension for Doppler single-photon lidar}},
    • journal = {Optics Express},
    • year = 2026,
    • volume = 34,
    • number = 9,
    • pages = {15933--15952},
    • month = apr,
    • doi = {10.1364/OE.592528},
    • url = {https://www.merl.com/publications/TR2026-050}
    • }
  •  Rapp, J., Kitichotkul, R., Ma, Y., Mansour, H., "Velocity estimation with single-photon lidar", SPIE Conference on Advanced Photon Counting Techniques, Mark A. Itzler, Joshua C. Bienfang, K. Alex McIntosh, Eds., DOI: 10.1117/​12.3097621, April 2026, vol. 14019, pp. 1401903.
    BibTeX TR2026-051 PDF
    • @inproceedings{Rapp2026apr,
    • author = {Rapp, Joshua and Kitichotkul, Ruangrawee and Ma, Yanting and Mansour, Hassan},
    • title = {{Velocity estimation with single-photon lidar}},
    • booktitle = {Advanced Photon Counting Techniques XX},
    • year = 2026,
    • editor = {Mark A. Itzler, Joshua C. Bienfang, K. Alex McIntosh},
    • volume = 14019,
    • pages = 1401903,
    • month = apr,
    • publisher = {SPIE},
    • doi = {10.1117/12.3097621},
    • url = {https://www.merl.com/publications/TR2026-051}
    • }
  •  Bimbraw, K., Wang, Y., Liu, J., Koike-Akino, T., "GPT Sonography: Hand Gesture Decoding from Forearm Ultrasound Images via a Large Vision-Language Model", IEEE Access, DOI: 10.1109/​ACCESS.2026.3687477, Vol. 14, pp. 70724-70736, April 2026.
    BibTeX TR2026-054 PDF
    • @article{Bimbraw2026may,
    • author = {Bimbraw, Keshav and Wang, Ye and Liu, Jing and Koike-Akino, Toshiaki},
    • title = {{GPT Sonography: Hand Gesture Decoding from Forearm Ultrasound Images via a Large Vision-Language Model}},
    • journal = {IEEE Access},
    • year = 2026,
    • volume = 14,
    • pages = {70724--70736},
    • month = may,
    • doi = {10.1109/ACCESS.2026.3687477},
    • issn = {2169-3536},
    • url = {https://www.merl.com/publications/TR2026-054}
    • }
  •  Suzuki, K., Liu, J., Wang, Y., Hori, C., Brand, M., Romeres, D., Koike-Akino, T., "Embedding Morphology into Transformers for Cross-Robot Policy Learning", International Conference on Learning Representations (ICLR) Workshop, April 2026.
    BibTeX TR2026-048 PDF
    • @inproceedings{Suzuki2026apr,
    • author = {Suzuki, Kei and Liu, Jing and Wang, Ye and Hori, Chiori and Brand, Matthew and Romeres, Diego and Koike-Akino, Toshiaki},
    • title = {{Embedding Morphology into Transformers for Cross-Robot Policy Learning}},
    • booktitle = {International Conference on Learning Representations (ICLR) Workshop on Efficient Spatial Reasoning},
    • year = 2026,
    • month = apr,
    • url = {https://www.merl.com/publications/TR2026-048}
    • }
  •  Wang, Y., Liu, J., Koike-Akino, T., "Directional Embedding Smoothing for Robust Vision Language Models", International Conference on Learning Representations (ICLR) Workshop on Agents in the Wild, April 2026.
    BibTeX TR2026-049 PDF Software Presentation
    • @inproceedings{Wang2026apr4,
    • author = {{Wang, Ye and Liu, Jing and Koike-Akino, Toshiaki}},
    • title = {{Directional Embedding Smoothing for Robust Vision Language Models}},
    • booktitle = {International Conference on Learning Representations (ICLR) Workshop on Agents in the Wild},
    • year = 2026,
    • month = apr,
    • url = {https://www.merl.com/publications/TR2026-049}
    • }
  •  Zhang, Y., Corcodel, R., Hori, C., Cherian, A., Zhao, D., "SpinBench: 3D Rotation as a Lens on Spatial Reasoning in VLMs", International Conference on Learning Representations (ICLR) 2026, C. Vondrick and B. Hariharan and C. Raffel and L. Pinto and D. Yang and A. Faust, Eds., April 2026, pp. 70072-70141.
    BibTeX TR2026-045 PDF
    • @inproceedings{Zhang2026apr2,
    • author = {Zhang, Yuyou and Corcodel, Radu and Hori, Chiori and Cherian, Anoop and Zhao, Ding},
    • title = {{SpinBench: 3D Rotation as a Lens on Spatial Reasoning in VLMs}},
    • booktitle = {International Conference on Learning Representations},
    • year = 2026,
    • editor = {C. Vondrick and B. Hariharan and C. Raffel and L. Pinto and D. Yang and A. Faust},
    • pages = {70072--70141},
    • month = apr,
    • url = {https://www.merl.com/publications/TR2026-045}
    • }
  •  Koike-Akino, T., Liu, J., Wang, Y., "TTQ: Activation-Aware Test-Time Quantization to Accelerate LLM Inference on the Fly", International Conference on Learning Representations (ICLR) Workshop, April 2026.
    BibTeX TR2026-044 PDF Presentation
    • @inproceedings{Koike-Akino2026apr,
    • author = {{Koike-Akino, Toshiaki and Liu, Jing and Wang, Ye}},
    • title = {{TTQ: Activation-Aware Test-Time Quantization to Accelerate LLM Inference on the Fly}},
    • booktitle = {International Conference on Learning Representations (ICLR) Workshop on Test-Time Updates (TTU)},
    • year = 2026,
    • month = apr,
    • url = {https://www.merl.com/publications/TR2026-044}
    • }
  •  Wang, Z., Hu, H., Deng, X., Mowlavi, S., Nakahira, Y., "OpInf-LLM: Parametric PDE Solving with LLMs via Operator Inference", International Conference on Learning Representations (ICLR) Workshop on AI and Partial Differential Equations (AI&PDE), April 2026.
    BibTeX TR2026-043 PDF
    • @inproceedings{Wang2026apr2,
    • author = {Wang, Zhuoyuan and Hu, Hanjiang and Deng, Xiyu and Mowlavi, Saviz and Nakahira, Yorie},
    • title = {{OpInf-LLM: Parametric PDE Solving with LLMs via Operator Inference}},
    • booktitle = {International Conference on Learning Representations (ICLR) Workshop on AI and Partial Differential Equations (AI\&PDE)},
    • year = 2026,
    • month = apr,
    • url = {https://www.merl.com/publications/TR2026-043}
    • }
  •  Wang, Z., Romagnoli, R., Mowlavi, S., Nakahira, Y., "Physics-Informed Deep B-Spline Networks", International Conference on Learning Representations (ICLR) Workshop on AI and Partial Differential Equations (AI&PDE), April 2026.
    BibTeX TR2026-046 PDF
    • @inproceedings{Wang2026apr3,
    • author = {Wang, Zhuoyuan and Romagnoli, Raffaele and Mowlavi, Saviz and Nakahira, Yorie},
    • title = {{Physics-Informed Deep B-Spline Networks}},
    • booktitle = {International Conference on Learning Representations (ICLR) Workshop on AI and Partial Differential Equations (AI\&PDE)},
    • year = 2026,
    • month = apr,
    • url = {https://www.merl.com/publications/TR2026-046}
    • }
  •  Zhai, H., Qiao, H., Mansour, H., Laughman, C.R., "Scalable Physics-Informed Neural Differential Equations and Data-Driven Algorithms for HVAC Systems", arXiv, April 2026.
    BibTeX arXiv
    • @article{Zhai2026apr,
    • author = {Zhai, Hanfeng and Qiao, Hongtao and Mansour, Hassan and Laughman, Christopher R.},
    • title = {{Scalable Physics-Informed Neural Differential Equations and Data-Driven Algorithms for HVAC Systems}},
    • journal = {arXiv},
    • year = 2026,
    • month = apr,
    • url = {https://arxiv.org/abs/2604.18438}
    • }
  •  Li, X., Wang, Y., Jiang, Z.-P., "Adaptive Dynamic Programming with Control Barrier Function for Safety-Critical Control Applications", SCIENTIA SINICA Informationis, DOI: 10.1360/​SSI-2025-0475, Vol. 56, No. 5, April 2026.
    BibTeX TR2026-104 PDF
    • @article{Li2026apr,
    • author = {Li, Xianning and Wang, Yebin and Jiang, Zhong-Ping},
    • title = {{Adaptive Dynamic Programming with Control Barrier Function for Safety-Critical Control Applications}},
    • journal = {SCIENTIA SINICA Informationis},
    • year = 2026,
    • volume = 56,
    • number = 5,
    • month = apr,
    • doi = {10.1360/SSI-2025-0475},
    • url = {https://www.merl.com/publications/TR2026-104}
    • }