Zobrazeno 1 - 10
of 34
pro vyhledávání: '"Das, Nilaksh"'
Autor:
Peri, Raghuveer, Jayanthi, Sai Muralidhar, Ronanki, Srikanth, Bhatia, Anshu, Mundnich, Karel, Dingliwal, Saket, Das, Nilaksh, Hou, Zejiang, Huybrechts, Goeric, Vishnubhotla, Srikanth, Garcia-Romero, Daniel, Srinivasan, Sundararajan, Han, Kyu J, Kirchhoff, Katrin
Integrated Speech and Large Language Models (SLMs) that can follow speech instructions and generate relevant text responses have gained popularity lately. However, the safety and robustness of these models remains largely unclear. In this work, we in
Externí odkaz:
http://arxiv.org/abs/2405.08317
Autor:
Das, Nilaksh, Dingliwal, Saket, Ronanki, Srikanth, Paturi, Rohit, Huang, Zhaocheng, Mathur, Prashant, Yuan, Jie, Bekal, Dhanush, Niu, Xing, Jayanthi, Sai Muralidhar, Li, Xilai, Mundnich, Karel, Sunkara, Monica, Srinivasan, Sundararajan, Han, Kyu J, Kirchhoff, Katrin
Large language models (LLMs) have shown incredible proficiency in performing tasks that require semantic understanding of natural language instructions. Recently, many works have further expanded this capability to perceive multimodal audio and text
Externí odkaz:
http://arxiv.org/abs/2405.08295
Autor:
Das, Nilaksh, Sunkara, Monica, Bodapati, Sravan, Cai, Jinglun, Kulshreshtha, Devang, Farris, Jeff, Kirchhoff, Katrin
End-to-end ASR models trained on large amount of data tend to be implicitly biased towards language semantics of the training data. Internal language model estimation (ILME) has been proposed to mitigate this bias for autoregressive models such as at
Externí odkaz:
http://arxiv.org/abs/2305.03837
Autor:
Zhou, Zhiyan, Li, Kevin, Park, Haekyu, Dass, Megan, Wright, Austin, Das, Nilaksh, Chau, Duen Horng
We present our ongoing work NeuroMapper, an in-browser visualization tool that helps machine learning (ML) developers interpret the evolution of a model during training, providing a new way to monitor the training process and visually discover reason
Externí odkaz:
http://arxiv.org/abs/2210.12492
Hear No Evil: Towards Adversarial Robustness of Automatic Speech Recognition via Multi-Task Learning
Autor:
Das, Nilaksh, Chau, Duen Horng
As automatic speech recognition (ASR) systems are now being widely deployed in the wild, the increasing threat of adversarial attacks raises serious questions about the security and reliability of using such systems. On the other hand, multi-task lea
Externí odkaz:
http://arxiv.org/abs/2204.02381
Person tracking using computer vision techniques has wide ranging applications such as autonomous driving, home security and sports analytics. However, the growing threat of adversarial attacks raises serious concerns regarding the security and relia
Externí odkaz:
http://arxiv.org/abs/2204.00734
Autor:
Park, Haekyu, Lee, Seongmin, Hoover, Benjamin, Wright, Austin P., Shaikh, Omar, Duggal, Rahul, Das, Nilaksh, Li, Kevin, Hoffman, Judy, Chau, Duen Horng
We present ConceptEvo, a unified interpretation framework for deep neural networks (DNNs) that reveals the inception and evolution of learned concepts during training. Our work addresses a critical gap in DNN interpretation research, as existing meth
Externí odkaz:
http://arxiv.org/abs/2203.16475
Autor:
Park, Haekyu, Das, Nilaksh, Duggal, Rahul, Wright, Austin P., Shaikh, Omar, Hohman, Fred, Chau, Duen Horng
Existing research on making sense of deep neural networks often focuses on neuron-level interpretation, which may not adequately capture the bigger picture of how concepts are collectively encoded by multiple neurons. We present NeuroCartography, an
Externí odkaz:
http://arxiv.org/abs/2108.12931
Autor:
Shaikh, Omar, Saad-Falcon, Jon, Wright, Austin P, Das, Nilaksh, Freitas, Scott, Asensio, Omar Isaac, Chau, Duen Horng
The advent of larger machine learning (ML) models have improved state-of-the-art (SOTA) performance in various modeling tasks, ranging from computer vision to natural language. As ML models continue increasing in size, so does their respective energy
Externí odkaz:
http://arxiv.org/abs/2103.16435
Training deep neural networks for automatic speech recognition (ASR) requires large amounts of transcribed speech. This becomes a bottleneck for training robust models for accented speech which typically contains high variability in pronunciation and
Externí odkaz:
http://arxiv.org/abs/2103.05834