Welcome π Let’s sit for a βοΈ and discuss anything interesting.
I’m Nikhil Saini, a Lead Engineer in the Language AI Team at Samsung Research Institute Bangalore.
My research interests include AI/ML π€ applied on Natural Language.
Currently, researching on Generative AI (LLMs) applied to natural language. Some of these are around Data generation (using Prompt Engineering), LLM Finetuning (LoRA), Model Compression π (QLorA, GPTQ …), Model Selection, Evaluation, Ondevice execution of LLMs (Tflite), and for more let’s get in touch π
Previouslyπ: I’ve worked at CFILT and CSALT lab with Prof. Pushpak Bhattacharyya and Prof. Preethi Jyothi on problems involving Speech and NLP during post-graduation π¨βπ.
M.Tech (Research), 2021
IIT Bombay
B.E, 2018
MSU Baroda
Domain:
Domain:
Responsibilities include:
Using denoising auto-encoder and backtranslation, this work beats a baseline model by a margin of 4.21 and 3.11 BLEU points where the baseline uses disfluent and fluent references, respectively, without an access to disfluent-to-fluent parallel corpus.