|
I work as an ML Engineer at Apple in the Siri And Language Technologies team. I completed Masters in Computer Science from University of Illinois at Urbana-Champaign (UIUC), advised by Prof. David Forsyth. I completed Bachelors in Computer Science from IIT Kanpur, India. I have been fortunate to work with inspiring researchers.
Awards and Scholarships:
I am interested in building fair and impactful solutions using Machine Learning. Particularly, I aim to develop technology at the intersection of Natural Language and Computer Vision to assist the society. |
|
|
Email / Google Scholar / LinkedIn
|
|
|
|
|
|
|
|
|
| ML Engineer Apple Inc. 2019 - |
MS, CS University of Illinois, Urbana-Champaign 2017 - 2019 |
Intern Apple Inc. Summer 2018 |
Research Assistant Coordinated Science Lab Fall 2017 |
Research Intern Microsoft Research Summer 2016 |
Research Fellow Max Planck Institute for Informatics Summer 2015 |
BTech, CS IIT Kanpur 2013 - 2017 |
|
|
|
Data generation framework that can efficiently generate synthetic data for dialogue schemas using countable templates. This bridges the gap between zero-shot and training data based few-shot prompting for dialog state tracking with LLMs. |
|
A benchmark by adapting four tasks and nine existing datasets, featuring prompts designed to assess the context-understanding abilities of LLMs. In the ICL setting, models struggle with understanding nuanced contextual signals compared to SOTA fine-tuned models. Assessment of quantized models provides promising insights on the 3-bit post-training quantization. |
|
Novel experience for users to refer to data-detectable entities on their phone screens when interacting with voice assistants. Screen reference resolution data strategy and a lightweight, general-purpose model that only uses the text extracted from the UI. The proposed model is modular, offering flexibility, better interpretability, and efficient run-time performance. |
|
Resolving references and understanding ellipses are crucial for dialogue agents to generate coherent responses. A joint benchmark for the two tasks by annotating the dialogue-based coreference dataset, MuDoCo, with rewritten queries. A novel joint learning framework that boosts query rewrite and outperforms SOTA for coreference resolution. |
|
Fresh perspective on dialog state tracking as a semantic parsing task over hierarchical representations, with compositionality, cross-domain knowledge sharing, and coreference. We present TreeDST, a dataset of 27k conversations with tree-structured states and system acts. Our encoder-decoder model leads to a 20% improvement over SOTA. |
|
The task of image captioning implicitly involves gender identification. MS COCO dataset contains blatant gender bias in captions, arising from two main sources: statistical variation in data and flawed annotations. Biased data leads to concerning predictions by models. We propose a novel framework for gender-neutral captioning and independent gender classification using masking, reducing contextual bias. On an anti-stereotypical dataset, our approach outperforms the SOTA gender-based approaches. |
|
Bitcoin's networking stack is shown to have anonymity vulnerabilities owing to the mechanism for broadcasting transactions, leading to large-scale deanonymization attacks. We present Dandelion++, a first-principles defense with near-optimal information-theoretic guarantees. |
|
I have been a Teaching Assistant for the following courses:
|