no code implementations • 14 May 2024 • Raghuveer Peri, Sai Muralidhar Jayanthi, Srikanth Ronanki, Anshu Bhatia, Karel Mundnich, Saket Dingliwal, Nilaksh Das, Zejiang Hou, Goeric Huybrechts, Srikanth Vishnubhotla, Daniel Garcia-Romero, Sundararajan Srinivasan, Kyu J Han, Katrin Kirchhoff
Despite safety guardrails, experiments on jailbreaking demonstrate the vulnerability of SLMs to adversarial perturbations and transfer attacks, with average attack success rates of 90% and 10% respectively when evaluated on a dataset of carefully designed harmful questions spanning 12 different toxic categories.
no code implementations • 14 May 2024 • Nilaksh Das, Saket Dingliwal, Srikanth Ronanki, Rohit Paturi, Zhaocheng Huang, Prashant Mathur, Jie Yuan, Dhanush Bekal, Xing Niu, Sai Muralidhar Jayanthi, Xilai Li, Karel Mundnich, Monica Sunkara, Sundararajan Srinivasan, Kyu J Han, Katrin Kirchhoff
The models are instruction finetuned using continuous latent representations extracted from the speech foundation model to achieve optimal zero-shot performance on a diverse range of speech processing tasks using natural language instructions.
no code implementations • 11 Feb 2021 • Karel Mundnich, Alexandra Fenster, Aparna Khare, Shiva Sundaram
To better study the task of highlight detection, we run a pilot experiment with highlights annotations for a small subset of video clips and fine-tune our best model on it.
no code implementations • 18 Mar 2020 • Karel Mundnich, Brandon M. Booth, Michelle L'Hommedieu, Tiantian Feng, Benjamin Girault, Justin L'Hommedieu, Mackenzie Wildman, Sophia Skaaden, Amrutha Nadarajan, Jennifer L. Villatte, Tiago H. Falk, Kristina Lerman, Emilio Ferrara, Shrikanth Narayanan
We designed the study to investigate the use of off-the-shelf wearable and environmental sensors to understand individual-specific constructs such as job performance, interpersonal interaction, and well-being of hospital workers over time in their natural day-to-day job settings.
no code implementations • 10 Nov 2019 • Arindam Jati, Amrutha Nadarajan, Karel Mundnich, Shrikanth Narayanan
In this paper, we address the task of characterizing acoustic scenes in a workplace setting from audio recordings collected with wearable microphones.
no code implementations • 2 Apr 2019 • Karel Mundnich, Brandon M. Booth, Benjamin Girault, Shrikanth Narayanan
In this work, we propose a novel annotation approach using triplet embeddings.