| 1 |
Large Language Models Do Multi-Label Classification Differently |
Marcus Ma |
Marcus Ma, Georgios Chochlakis, Niyantha Pandiyan, Jesse Thomason, Shrikanth Narayanan |
| 2 |
Tracing Moral Foundations in Large Language Models |
Bowen Yi |
Bowen Yi*, Chenxiao Yu*, Shrikanth Narayanan, Morteza Dehghani, et al. |
| 3 |
Few-Shot Personalization of Self-Supervised Wearable Biosignal Models |
Emily Zhou |
Emily Zhou, Aditya Kommineni, Marcus Ma, Kaitlin Zareno, Kleanthis Avramidis, Tiantian Feng, Shrikanth Narayanan |
| 4 |
Evaluating User and Attribute Privacy in Speech via Membership Inference Attacks |
Efthymios Tsaprazlis |
Efthymios Tsaprazlis, Thanathai Lertpetchpun, Tiantian Feng, Sai Praneeth Karimireddy, Shrikanth Narayanan |
| 5 |
Neural Codecs as Biosignal Tokenizers |
Kleanthis Avramidis |
Kleanthis Avramidis, Tiantian Feng, Woojae Jeong, Jihwan Lee, Wenhui Cui, Richard Leahy, Shrikanth Narayanan |
| 6 |
Identifying Factors that Limit Discriminative EEG Task Performance |
Aditya Kommineni |
Aditya Kommineni, Emily Zhou, Shrikanth Narayanan |
| 7 |
Learning Context-Aware Physiological Baselines from Wearable Data |
Kait Zareno |
Kait Zareno, Emily Zhou, Aditya Kommineni, Kleanthis Avramidis, Tiantian Feng, Shrikanth Narayanan |
| 8 |
Neural Audio Codecs as Zero-Shot Defenses Against Adversarial ASR Attacks |
Jordan Prescott |
Jordan Prescott, Thanathai Lertpetchpun, Shrikanth Narayanan |
| 9 |
A Long-Form Single-Speaker Real-Time MRI Speech Dataset and Benchmark |
Sean Foley |
Sean Foley, Jihwan Lee, Kevin Huang, Xuan Shi, Yoonjeong Lee, Louis Goldstein, Shrikanth Narayanan |
| 10 |
Large Language Models Based ASR Error Correction for Child Conversations |
Anfeng Xu |
Anfeng Xu, Tiantian Feng, So Hyun Kim, Somer Bishop, Catherine Lord, Shrikanth Narayanan |
| 11 |
Human-Centered Speech Computing Across Life Span |
Tiantian Feng |
Tiantian Feng, Shrikanth Narayanan |
| 12 |
Subjective Label Verifiers |
Georgios Chochlakis |
Georgios Chochlakis, P. Wu, A. Bedi, M. Ma, K. Lerman, Shrikanth Narayanan |
| 13 |
Quantifying Speaker Embedding Phonological Rule Interactions in Accented Speech Synthesis |
Thanathai Lertpetchpun |
Thanathai Lertpetchpun, Yoonjeong Lee, Shrikanth Narayanan, et al. |
| 14 |
Proof-of-Concept: Simultaneous Acquisition of Real-Time MRI Video, EEG, and Surface EMG During Speech Production |
Jihwan Lee |
Jihwan Lee, Parsa Razmara, Kevin Huang, Sean Foley, Shrikanth Narayanan, et al. |
| 15 |
Speech Acoustics to rt-MRI Articulatory Dynamics Inversion with Video Diffusion Model |
Xuan Shi |
Xuan Shi, Tiantian Feng, Jay Park, Christina Hagedorn, Louis Goldstein, Shrikanth Narayanan |
| 16 |
Applications and Challenges in Modeling Articulatory Dynamics |
Kevin Huang |
Kevin Huang, Sean Foley, Jihwan Lee, Yoonjeong Lee, Dani Byrd, Shrikanth Narayanan |
| 17 |
Detection of Intracranial Hypertension Using Optic Disc Photographs Under Severe Data Imbalance |
Sajjad Shahabi |
Sajjad Shahabi |
| 18 |
Multimodal Learning for Understanding and Classifying Stress |
Andreas Peter Juhl Hansen, Jeppe Roden Münster |
Andreas Peter Juhl Hansen, Jeppe Roden Münster |
| 19 |
Synergy Identification via Network Clustering |
Simon Bock Segaard |
Simon Bock Segaard |
| 20 |
Smiling Back: Modeling and Evaluating Facial Reciprocity in Conversational Agents |
Daniel Yang |
Daniel Yang, Hirofumi Inaguma, Jason Zheng, Tu Anh Nguyen, Xutai Ma |
| 21 |
Interpreting Accented Speech in Foundation Models via Sparse Autoencoders |
Shih-Heng (Stan) Wang |
Shih-Heng (Stan) Wang, Shrikanth Narayanan |
| 22 |
Novel Death Association-Reaction Score Measure from Sentence Task to Predict Depression and Suicidal Ideation |
Sudarsana Reddy Kadiri |
Sudarsana Reddy Kadiri, PRECOG Team, Shrikanth Narayanan |
| 23 |
Interpretable Modeling of Articulatory Temporal Dynamics from Real-Time MRI for Phoneme Recognition |
Jay Park |
Jay Park, Hong Nguyen, Sean Foley, Jihwan Lee, Yoonjeong Lee, Dani Byrd, Shrikanth Narayanan |
| 24 |
VELUTI: AI-Powered Precision Therapist Matching |
Huang-Cheng Chou |
Huang-Cheng Chou, Shrikanth Narayanan |
| 25 |
Understand and Predict Human Social Signals in Videos |
Hong Nguyen |
Hong Nguyen, Shrikanth Narayanan |
