Publications

614 / 3,686 publications found.


  •  Wu, S.-L., Chang, X., Wichern, G., Jung, J.-W., Germain, F., Le Roux, J., Watanabe, S., "BEATs-based Audio Captioning Model with Instructor Embedding Supervision and ChatGPT Mix-up," Tech. Rep. TR2023-068, DCASE2023 Challenge, May 2023.
    BibTeX TR2023-068 PDF
    • @techreport{Wu2023may,
    • author = {Wu, Shih-Lun and Chang, Xuankai and Wichern, Gordon and Jung, Jee-weon and Germain, Francois and Le Roux, Jonathan and Watanabe, Shinji},
    • title = {BEATs-based Audio Captioning Model with Instructor Embedding Supervision and ChatGPT Mix-up},
    • institution = {DCASE2023 Challenge},
    • year = 2023,
    • month = may,
    • url = {https://www.merl.com/publications/TR2023-068}
    • }
  •  Cherian, A., Jain, S., Marks, T.K., Sullivan, A., "Discriminative 3D Shape Modeling for Few-Shot Instance Segmentation", IEEE International Conference on Robotics and Automation (ICRA), DOI: 10.1109/​ICRA48891.2023.10160644, May 2023, pp. 9296-9302.
    BibTeX TR2023-010 PDF Presentation
    • @inproceedings{Cherian2023may,
    • author = {Cherian, Anoop and Jain, Siddarth and Marks, Tim K. and Sullivan, Alan},
    • title = {Discriminative 3D Shape Modeling for Few-Shot Instance Segmentation},
    • booktitle = {IEEE International Conference on Robotics and Automation (ICRA)},
    • year = 2023,
    • pages = {9296--9302},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICRA48891.2023.10160644},
    • url = {https://www.merl.com/publications/TR2023-010}
    • }
  •  Curtis, A., Kaelbling, L., Jain, S., "Task-Directed Exploration in Continuous POMDPs for Robotic Manipulation of Articulated Objects", IEEE International Conference on Robotics and Automation (ICRA), DOI: 10.1109/​ICRA48891.2023.10160306, May 2023, pp. 3721-3728.
    BibTeX TR2023-046 PDF
    • @inproceedings{Curtis2023may,
    • author = {Curtis, Aidan and Kaelbling, Leslie and Jain, Siddarth},
    • title = {Task-Directed Exploration in Continuous POMDPs for Robotic Manipulation of Articulated Objects},
    • booktitle = {IEEE International Conference on Robotics and Automation (ICRA)},
    • year = 2023,
    • pages = {3721--3728},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICRA48891.2023.10160306},
    • isbn = {979-8-3503-2365-8},
    • url = {https://www.merl.com/publications/TR2023-046}
    • }
  •  Haruna, M., Ogino, M., Tagashira, S., Kashiwa, M., Morita, S., Koike-Akino, T., Imai, K., Zuho, T., Makita, M., Takahashi, Y., "Avatar Technologies of Team LAST MILE Toward Mobile Smart Device Operation Service", IEEE International Conference on Robotics and Automation (ICRA), May 2023.
    BibTeX TR2023-047 PDF
    • @inproceedings{Haruna2023may,
    • author = {Haruna, Masaki and Ogino, Masaki and Tagashira, Shigeaki and Kashiwa, Munetaka and Morita, Susumu and Koike-Akino, Toshiaki and Imai, Kota and Zuho, Tiancheng and Makita, Masashi and Takahashi, Yasutake},
    • title = {Avatar Technologies of Team LAST MILE Toward Mobile Smart Device Operation Service},
    • booktitle = {IEEE International Conference on Robotics and Automation (ICRA)},
    • year = 2023,
    • month = may,
    • url = {https://www.merl.com/publications/TR2023-047}
    • }
  •  Ota, K., Tung, H.-Y., Smith, K., Cherian, A., Marks, T.K., Sullivan, A., Kanezaki, A., Tenenbaum, J.B., "H-SAUR: Hypothesize, Simulate, Act, Update, and Repeat for Understanding Object Articulations from Interactions", IEEE International Conference on Robotics and Automation (ICRA), DOI: 10.1109/​ICRA48891.2023.10160575, May 2023, pp. 7272-7278.
    BibTeX TR2023-009 PDF
    • @inproceedings{Ota2023may,
    • author = {Ota, Kei and Tung, Hsiao-Yu and Smith, Kevin and Cherian, Anoop and Marks, Tim K. and Sullivan, Alan and Kanezaki, Asako and Tenenbaum, Joshua B.},
    • title = {H-SAUR: Hypothesize, Simulate, Act, Update, and Repeat for Understanding Object Articulations from Interactions},
    • booktitle = {IEEE International Conference on Robotics and Automation (ICRA)},
    • year = 2023,
    • pages = {7272--7278},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICRA48891.2023.10160575},
    • url = {https://www.merl.com/publications/TR2023-009}
    • }
  •  Wang, X., Kim, K.J., Wang, Y., Koike-Akino, T., Parsons, K., "DeepEAD: Explainable Anomaly Detection from System Logs", IEEE International Conference on Communications (ICC), DOI: 10.1109/​ICC45041.2023.10279563, May 2023.
    BibTeX TR2023-050 PDF
    • @inproceedings{Wang2023may,
    • author = {Wang, Xinda and Kim, Kyeong Jin and Wang, Ye and Koike-Akino, Toshiaki and Parsons, Kieran},
    • title = {DeepEAD: Explainable Anomaly Detection from System Logs},
    • booktitle = {IEEE International Conference on Communications (ICC)},
    • year = 2023,
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICC45041.2023.10279563},
    • issn = {1938-1883},
    • isbn = {978-1-5386-7462-8},
    • url = {https://www.merl.com/publications/TR2023-050}
    • }
  •  Kim, K.J., Vinod, A.P., Guo, J., Deshpande, V.M., Parsons, K., "Spectrum Sharing-inspired Safe Motion Planning", IEEE International Conference on Communications Workshops (ICC), May 2023.
    BibTeX TR2023-049 PDF
    • @inproceedings{Kim2023may2,
    • author = {Kim, Kyeong Jin and Vinod, Abraham P. and Guo, Jianlin and Deshpande, Vedang M. and Parsons, Kieran},
    • title = {Spectrum Sharing-inspired Safe Motion Planning},
    • booktitle = {IEEE International Conference on Communications Workshops (ICC)},
    • year = 2023,
    • month = may,
    • url = {https://www.merl.com/publications/TR2023-049}
    • }
  •  Xu, Y., Wang, B., Sakamoto, Y., Yamamoto, T., Nishimura, Y., "Comparison of Learning-based Surrogate Models for Electric Motors", Conference on the Computation of Electromagnetic Fields (COMPUMAG), DOI: 10.1109/​COMPUMAG56388.2023.10411811, May 2023, pp. 1-4.
    BibTeX TR2023-042 PDF
    • @inproceedings{Xu2023may,
    • author = {Xu, Yihao and Wang, Bingnan and Sakamoto, Yusuke and Yamamoto, Tatsuya and Nishimura, Yuki},
    • title = {Comparison of Learning-based Surrogate Models for Electric Motors},
    • booktitle = {2023 24th International Conference on the Computation of Electromagnetic Fields (COMPUMAG)},
    • year = 2023,
    • pages = {1--4},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/COMPUMAG56388.2023.10411811},
    • url = {https://www.merl.com/publications/TR2023-042}
    • }
  •  Chen, K., Wichern, G., Germain, F., Le Roux, J., "Pac-HuBERT: Self-Supervised Music Source Separation via Primitive Auditory Clustering and Hidden-Unit BERT", IEEE ICASSP Satellite Workshop on Self-supervision in Audio, Speech and Beyond (SASB), DOI: 10.1109/​ICASSPW59220.2023.10193575, May 2023.
    BibTeX TR2023-030 PDF
    • @inproceedings{Chen2023may,
    • author = {Chen, Ke and Wichern, Gordon and Germain, Francois and Le Roux, Jonathan},
    • title = {Pac-HuBERT: Self-Supervised Music Source Separation via Primitive Auditory Clustering and Hidden-Unit BERT},
    • booktitle = {IEEE ICASSP Satellite Workshop on Self-supervision in Audio, Speech and Beyond (SASB)},
    • year = 2023,
    • month = may,
    • doi = {10.1109/ICASSPW59220.2023.10193575},
    • isbn = {979-8-3503-0261-5},
    • url = {https://www.merl.com/publications/TR2023-030}
    • }
  •  Aralikatti, R., Boeddeker, C., Wichern, G., Subramanian, A.S., Le Roux, J., "Reverberation as Supervision for Speech Separation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP49357.2023.10095022, May 2023, pp. 1-5.
    BibTeX TR2023-016 PDF
    • @inproceedings{Aralikatti2023may,
    • author = {Aralikatti, Rohith and Boeddeker, Christoph and Wichern, Gordon and Subramanian, Aswin Shanmugam and Le Roux, Jonathan},
    • title = {Reverberation as Supervision for Speech Separation},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2023,
    • pages = {1--5},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP49357.2023.10095022},
    • url = {https://www.merl.com/publications/TR2023-016}
    • }
  •  Berk, A., Ma, Y., Boufounos, P.T., Wang, P., Mansour, H., "Deep Proximal Gradient Method for Learned Convex Regularizers", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP49357.2023.10094632, May 2023, pp. 1-5.
    BibTeX TR2023-032 PDF Video
    • @inproceedings{Berk2023may,
    • author = {Berk, Aaron and Ma, Yanting and Boufounos, Petros T. and Wang, Pu and Mansour, Hassan},
    • title = {Deep Proximal Gradient Method for Learned Convex Regularizers},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2023,
    • pages = {1--5},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP49357.2023.10094632},
    • isbn = {978-1-7281-6327-7},
    • url = {https://www.merl.com/publications/TR2023-032}
    • }
  •  Bralios, D., Tzinis, E., Wichern, G., Smaragdis, P., Le Roux, J., "Latent Iterative Refinement for Modular Source Separation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP49357.2023.10096897, May 2023, pp. 1-5.
    BibTeX TR2023-019 PDF
    • @inproceedings{Bralios2023may,
    • author = {Bralios, Dimitrios and Tzinis, Efthymios and Wichern, Gordon and Smaragdis, Paris and Le Roux, Jonathan},
    • title = {Latent Iterative Refinement for Modular Source Separation},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2023,
    • pages = {1--5},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP49357.2023.10096897},
    • url = {https://www.merl.com/publications/TR2023-019}
    • }
  •  Fujihashi, T., Koike-Akino, T., Watanabe, T., "Soft 2D-to-3D Delivery Using Deep Graph Neural Networks for Holographic-Type Communication", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP49357.2023.10095882, May 2023.
    BibTeX TR2023-031 PDF
    • @inproceedings{Fujihashi2023may,
    • author = {Fujihashi, Takuya and Koike-Akino, Toshiaki and Watanabe, Takashi},
    • title = {Soft 2D-to-3D Delivery Using Deep Graph Neural Networks for Holographic-Type Communication},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2023,
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP49357.2023.10095882},
    • isbn = {978-1-7281-6327-7},
    • url = {https://www.merl.com/publications/TR2023-031}
    • }
  •  Petermann, D., Wichern, G., Subramanian, A.S., Le Roux, J., "Hyperbolic Audio Source Separation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP49357.2023.10094943, May 2023, pp. 1-5.
    BibTeX TR2023-017 PDF Video Software
    • @inproceedings{Petermann2023may,
    • author = {Petermann, Darius and Wichern, Gordon and Subramanian, Aswin Shanmugam and Le Roux, Jonathan},
    • title = {Hyperbolic Audio Source Separation},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2023,
    • pages = {1--5},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP49357.2023.10094943},
    • url = {https://www.merl.com/publications/TR2023-017}
    • }
  •  Tzinis, E., Wichern, G., Smaragdis, P., Le Roux, J., "Optimal Condition Training for Target Source Separation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP49357.2023.10095128, May 2023, pp. 1-5.
    BibTeX TR2023-018 PDF
    • @inproceedings{Tzinis2023may,
    • author = {Tzinis, Efthymios and Wichern, Gordon and Smaragdis, Paris and Le Roux, Jonathan},
    • title = {Optimal Condition Training for Target Source Separation},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2023,
    • pages = {1--5},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP49357.2023.10095128},
    • url = {https://www.merl.com/publications/TR2023-018}
    • }
  •  Vaca-Rubio, C., Wang, P., Koike-Akino, T., Wang, Y., Boufounos, P.T., Popovski, P., "mmWave Wi-Fi Trajectory Estimation with Continuous-Time Neural Dynamic Learning", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP49357.2023.10096474, May 2023, pp. 1-5.
    BibTeX TR2023-033 PDF Video
    • @inproceedings{Vaca-Rubio2023may,
    • author = {Vaca-Rubio, Cristian and Wang, Pu and Koike-Akino, Toshiaki and Wang, Ye and Boufounos, Petros T. and Popovski, Petar},
    • title = {mmWave Wi-Fi Trajectory Estimation with Continuous-Time Neural Dynamic Learning},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2023,
    • pages = {1--5},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP49357.2023.10096474},
    • isbn = {978-1-7281-6327-7},
    • url = {https://www.merl.com/publications/TR2023-033}
    • }
  •  Yen, H., Germain, F., Wichern, G., Le Roux, J., "Cold Diffusion for Speech Enhancement", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP49357.2023.10096064, May 2023, pp. 1-5.
    BibTeX TR2023-020 PDF
    • @inproceedings{Yen2023may,
    • author = {Yen, Hao and Germain, Francois and Wichern, Gordon and Le Roux, Jonathan},
    • title = {Cold Diffusion for Speech Enhancement},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2023,
    • pages = {1--5},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP49357.2023.10096064},
    • url = {https://www.merl.com/publications/TR2023-020}
    • }
  •  Zhao, Q., Ma, Y., Boufounos, P.T., Nabi, S., Mansour, H., "Deep Born Operator Learning for Reflection Tomographic Imaging", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP49357.2023.10095494, May 2023, pp. 1-5.
    BibTeX TR2023-029 PDF Video
    • @inproceedings{Zhao2023may,
    • author = {Zhao, Qingqing and Ma, Yanting and Boufounos, Petros T. and Nabi, Saleh and Mansour, Hassan},
    • title = {Deep Born Operator Learning for Reflection Tomographic Imaging},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2023,
    • pages = {1--5},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP49357.2023.10095494},
    • url = {https://www.merl.com/publications/TR2023-029}
    • }
  •  Cherian, A., Peng, K.-C., Lohit, S., Smith, K., Tenenbaum, J.B., "Are Deep Neural Networks SMARTer than Second Graders?", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), March 2023, pp. 10834-10844.
    BibTeX TR2023-014 PDF Data Software Presentation
    • @inproceedings{Cherian2023mar,
    • author = {Cherian, Anoop and Peng, Kuan-Chuan and Lohit, Suhas and Smith, Kevin and Tenenbaum, Joshua B.},
    • title = {Are Deep Neural Networks SMARTer than Second Graders?},
    • booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    • year = 2023,
    • pages = {10834--10844},
    • month = mar,
    • publisher = {CVF},
    • url = {https://www.merl.com/publications/TR2023-014}
    • }
  •  Kojima, K., Koike-Akino, T., Wang, Y., Jung Minwoo, , Brand, M., "Inverse design of two-dimensional freeform metagrating using an adversarial conditional variational autoencoder", SPIE Photonics West, DOI: 10.1117/​12.2650299, January 2023.
    BibTeX TR2023-004 PDF
    • @inproceedings{Kojima2023jan,
    • author = {Kojima, Keisuke and Koike-Akino, Toshiaki and Wang, Ye and Jung Minwoo and Brand, Matthew},
    • title = {Inverse design of two-dimensional freeform metagrating using an adversarial conditional variational autoencoder},
    • booktitle = {Proc. SPIE 12431, Photonic and Phononic Properties of Engineered Nanostructures XIII},
    • year = 2023,
    • month = jan,
    • publisher = {SPIE},
    • doi = {10.1117/12.2650299},
    • url = {https://www.merl.com/publications/TR2023-004}
    • }
  •  Liu, T., Cherian, A., "Learning a Constrained Optimizer: A Primal Method", AAAI Bridge on Constraint Programming and Machine Learning, January 2023.
    BibTeX TR2023-003 PDF
    • @inproceedings{Liu2023jan,
    • author = {Liu, Tao and Cherian, Anoop},
    • title = {Learning a Constrained Optimizer: A Primal Method},
    • booktitle = {AAAI Bridge on Constraint Programming and Machine Learning},
    • year = 2023,
    • month = jan,
    • url = {https://www.merl.com/publications/TR2023-003}
    • }
  •  Tohme, T., Liu, D., Youcef-Toumi, K., "GSR: A Generalized Symbolic Regression Approach", Transactions on Machine Learning Research, January 2023.
    BibTeX TR2023-002 PDF
    • @article{Tohme2023jan,
    • author = {Tohme, Tony and Liu, Dehong and Youcef-Toumi, Kamal},
    • title = {GSR: A Generalized Symbolic Regression Approach},
    • journal = {Transactions on Machine Learning Research},
    • year = 2023,
    • month = jan,
    • issn = {2835-8856},
    • url = {https://www.merl.com/publications/TR2023-002}
    • }
  •  Wang, Z.-Q., Wichern, G., Watanabe, S., Le Roux, J., "STFT-Domain Neural Speech Enhancement with Very Low Algorithmic Latency", IEEE/ACM Transactions on Audio, Speech, and Language Processing, DOI: 10.1109/​TASLP.2022.3224285, Vol. 31, pp. 397-410, December 2022.
    BibTeX TR2022-166 PDF
    • @article{Wang2022dec2,
    • author = {Wang, Zhong-Qiu and Wichern, Gordon and Watanabe, Shinji and Le Roux, Jonathan},
    • title = {STFT-Domain Neural Speech Enhancement with Very Low Algorithmic Latency},
    • journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing},
    • year = 2022,
    • volume = 31,
    • pages = {397--410},
    • month = dec,
    • doi = {10.1109/TASLP.2022.3224285},
    • issn = {2329-9304},
    • url = {https://www.merl.com/publications/TR2022-166}
    • }
  •  Singla, V., Aeron, S., Koike-Akino, T., Parsons, K., Brand, M., Wang, Y., "Learning with noisy labels using low-dimensional model trajectory", NeurIPS 2022 Workshop on Distribution Shifts (DistShift), December 2022.
    BibTeX TR2022-156 PDF
    • @inproceedings{Singla2022dec,
    • author = {Singla, Vasu and Aeron, Shuchin and Koike-Akino, Toshiaki and Parsons, Kieran and Brand, Matthew and Wang, Ye},
    • title = {Learning with noisy labels using low-dimensional model trajectory},
    • booktitle = {NeurIPS 2022 Workshop on Distribution Shifts: Connecting Methods and Applications},
    • year = 2022,
    • month = dec,
    • publisher = {OpenReview},
    • url = {https://www.merl.com/publications/TR2022-156}
    • }
  •  Shimoya, R., Morimoto, T., van Baar, J., Boufounos, P.T., Ma, Y., Mansour, H., "Learning Occlusion-Aware Dense Correspondences for Multi-Modal Images", IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), DOI: 10.1109/​AVSS56176.2022.9959354, November 2022, pp. 1-8.
    BibTeX TR2022-149 PDF
    • @inproceedings{Shimoya2022nov,
    • author = {Shimoya, Ryosuke and Morimoto, Tahashi and van Baar, Jeroen and Boufounos, Petros T. and Ma, Yanting and Mansour, Hassan},
    • title = {Learning Occlusion-Aware Dense Correspondences for Multi-Modal Images},
    • booktitle = {IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)},
    • year = 2022,
    • pages = {1--8},
    • month = nov,
    • doi = {10.1109/AVSS56176.2022.9959354},
    • isbn = {978-1-6654-6382-9},
    • url = {https://www.merl.com/publications/TR2022-149}
    • }