Selected Publications & Patents

Maohao Shen, Tejas Jayashankar, Osama Hanna, Naoyuki Kanda, Yancheng Wang, Kateřina Žmolíková, Ruiming Xie, Niko Moritz, Anfeng Xu, Yashesh Gaur, Gregory Wornell, Qing He, Jilong Wu (2026). GSRM: Generative Speech Reward Model for Speech RLHF. arXiv preprint.

arXiv Link PDF

Tejas Jayashankar^*, Jongha J. Ryu^*, Gregory W. Wornell (2025). Score-of-Mixture Training: One-Step Generative Model Training Made Simple via Score Estimation of Mixture Distributions. Spotlight Proceedings of the 42nd International Conference on Machine Learning (ICML 2025).

arXiv Link Openreview Link Code

Tejas Jayashankar (2025). Score Estimation for Generative Modeling. Massachusetts Institute of Technology.

Thesis

Tejas Jayashankar, Jongha J. Ryu, Xiangxiang Xu, Gregory W. Wornell (2024). Lifted Residual Score Estimation. 2024 ICML SPIGM Workshop.

Paper

Tejas Jayashankar, Gregory W. Wornell (2024). Model-Code Separation Architecture for Data Compression Using Sum-Product Networks. US Patent App (US20260017501A1).

Link

Tejas Jayashankar, Gary C.F. Lee, Alejandro Lancho, Amir Weiss, Yury Polyanksiy, Gregory Wornell (2023). Score-based Source Separation with Applications to Digital Communication Signals. 37th Conference on Neural Information Processing Systems (NeurIPS 2023).

arXiv Link Openreview Link Project Webpage Code

Tejas Jayashankar, Jilong Wu, Leda Sari, David Kant, Vimal Manohar, Qing He (2023). Self-Supervised Representations for Singing Voice Conversion. 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Paper Audio Samples

Jonathan Le Roux, Tejas Jayashankar, Pierre Moulin (2022). System and Method for Detecting Adversarial Attacks. US Patent App.

Link

Tejas Jayashankar, Thilo Koehler, Kaustubh Kalgaonkar, Zhiping Xiu, Jilong Wu, Ju Lin, Prabhav Agrawal, Qing He (2022). Architecture for Variable Bitrate Neural Speech Codec with Configurable Computation Complexity. 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Paper

Tejas Jayashankar (2022). Image Compression using Sum-Product Networks. Massachusetts Institute of Technology.

Thesis

Tejas Jayashankar, Jonathan Le Roux, Pierre Moulin (2020). Detecting Audio Attacks on ASR Systems with Dropout Uncertainty. INTERSPEECH 2020.

arXiv Link Conference Link

Tejas Jayashankar, Pierre Moulin, Thierry Blu, Chris Gilliam" (2019). LAP-based Video Frame Interpolation. 2019 IEEE International Conference on Image Processing (ICIP).

Paper