Resume | Publications | GitHub
Google Scholar | Linkedin | OpenReview
Email amballaavinash[at]gmail.com
Mobile +1 6095054919
Address Sunnyvale, CA, USA
Embedded Files
Welcome! My name is Avinash Amballa. I am a Researcher in the Language Intelligence team at Samsung Research America (SRA), Mountain View, working on On-device Language Intelligence. I got my Masters in Computer Science from University of Massachusetts Amherst , where I was extremely fortunate to be working with Prof Andrew McCallum.
My past research internships were at
- UMASS IESL lab with Prof. Andrew McCallum.
- UMASS BioNLP lab with Prof. Hong Yu.
- Graudate Student Researcher at Google with Dr. Luke Vilnis.
- Senior Reseacher at Bosch with Manoj Kumar Parmar.
During 2021-2023, I was a Senior Researcher at Bosch, Bangalore. I hold a Bacherlors in Electrical Engineering & Computer Science from Indian Institute of Technology (IIT) Hyderabad.
Research Interests: Non Auto Regressive generation, Finetuning, Encoding & Decoding, 3D Vision, Reinforcement Learning, Explainable AI
Publications
Publications
Google Scholar | OpenReview
* = Equal Contributions
Selected Papers
Selected Papers
ICLR / WACV/ COLM are among top 10 conferences in all computer science [Source].
CoPE: A Lightweight Complex Positional Encoding
Avinash Amballa
coming soon
pdf/ code
Insertion Language Models: Sequence Generation with Arbitrary-Position Insertions
Dhruvesh Patel, Aishwarya Sahoo, Avinash Amballa, Tahira Naseem, Tim G. J Rudner, Andrew McCallum
coming soon
pdf/ code
Avinash Amballa, Aditya Parashar, Aditya Vikram Singh, Jinlin Lai, Benjamin Rozonoyer
ICLR 2025 (workshop)
pdf / code
Other Papers
Other Papers
Patents
Patents
A Method of Sponze attack on Deep Learning Models to increase the inference time.
A Method of Sponze attack on Deep Learning Models to increase the inference time.
Avinash Amballa, Yuvaraj Govindarajulu, Manojkumar Parmar
US patent/ link
A method to detect poisoning of an ai model and a system thereof
A method to detect poisoning of an ai model and a system thereof
Avinash Amballa, Yuvaraj Govindarajulu, Manojkumar Parmar
IN patent/ link
A method of assessing vulnerability of an ai system and a framework thereof
A method of assessing vulnerability of an ai system and a framework thereof
Avinash Amballa, Yuvaraj Govindarajulu, Manojkumar Parmar
IN patent/ link
A method of assessing vulnerability of an ai system and a framework thereof
A method of assessing vulnerability of an ai system and a framework thereof
Avinash Amballa, Yuvaraj Govindarajulu, Manojkumar Parmar
IN patent/ link
Page updated
Google Sites
Report abuse