Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Indurthi, Sathish"'
Autor:
Wu, Tong, Zhang, Shujian, Song, Kaiqiang, Xu, Silei, Zhao, Sanqiang, Agrawal, Ravi, Indurthi, Sathish Reddy, Xiang, Chong, Mittal, Prateek, Zhou, Wenxuan
Large Language Models (LLMs) are susceptible to security and safety threats, such as prompt injection, prompt extraction, and harmful requests. One major cause of these vulnerabilities is the lack of an instruction hierarchy. Modern LLM architectures
Externí odkaz:
http://arxiv.org/abs/2410.09102
Autor:
Indurthi, Sathish Reddy, Zhou, Wenxuan, Chollampatt, Shamil, Agrawal, Ravi, Song, Kaiqiang, Zhao, Lingxiao, Zhu, Chenguang
Advancements in Large Language Models (LLMs) have significantly enhanced instruction-following capabilities. However, most Instruction Fine-Tuning (IFT) datasets are predominantly in English, limiting model performance in other languages. Traditional
Externí odkaz:
http://arxiv.org/abs/2407.01853
Autor:
Zhou, Wenxuan, Agrawal, Ravi, Zhang, Shujian, Indurthi, Sathish Reddy, Zhao, Sanqiang, Song, Kaiqiang, Xu, Silei, Zhu, Chenguang
Reinforcement learning from human feedback (RLHF) is a promising solution to align large language models (LLMs) more closely with human values. Off-policy preference optimization, where the preference data is obtained from other models, is widely ado
Externí odkaz:
http://arxiv.org/abs/2406.11827
Simultaneous neural machine translation(SNMT) models start emitting the target sequence before they have processed the source sequence. The recent adaptive policies for SNMT use monotonic attention to perform read/write decisions based on the partial
Externí odkaz:
http://arxiv.org/abs/2109.03121
Autor:
Han, Hyojung, Indurthi, Sathish, Zaidi, Mohd Abbas, Lakumarapu, Nikhil Kumar, Lee, Beomseok, Kim, Sangha, Kim, Chanwoo, Hwang, Inchul
Recently, simultaneous translation has gathered a lot of attention since it enables compelling applications such as subtitle translation for a live event or real-time video-call translation. Some of these translation applications allow editing of par
Externí odkaz:
http://arxiv.org/abs/2012.14681
In this paper, we present a Small Energy Masking (SEM) algorithm, which masks inputs having values below a certain threshold. More specifically, a time-frequency bin is masked if the filterbank energy in this bin is less than a certain energy thresho
Externí odkaz:
http://arxiv.org/abs/2002.06312
Autor:
Indurthi, Sathish, Han, Houjeung, Lakumarapu, Nikhil Kumar, Lee, Beomseok, Chung, Insoo, Kim, Sangha, Kim, Chanwoo
End-to-end Speech Translation (ST) models have several advantages such as lower latency, smaller model size, and less error compounding over conventional pipelines that combine Automatic Speech Recognition (ASR) and text Machine Translation (MT) mode
Externí odkaz:
http://arxiv.org/abs/1911.04283
We describe the problem of aggregating the label predictions of diverse classifiers using a class taxonomy. Such a taxonomy may not have been available or referenced when the individual classifiers were designed and trained, yet mapping the output la
Externí odkaz:
http://arxiv.org/abs/1512.00355