Yash Kumar Atri

University of Virginia

atri [at] virginia.edu

News

Oct 2024 – Selected as DAAD AInet fellow 2024.
June 2024 – Joined UVA as a postdoc.
Feb 2024 – Presented at the ACM ARCS symposium at NISER Bhubaneswar.
Dec 2023 – Gave tutorial at ICON 2023.
Nov 2023 – Microsoft Travel Grant for EMNLP.
Aug 2023 – Microsoft Travel Grant for SIGKDD.
Apr 2023 – Webchair for Intl. Conf. on Big Data & AI.

About Me

Hi! I am a postdoc at the University of Virginia, working with Prof. Tom Hartvigsen. Before joining UVA, I completed my PhD in Computer Science and Engineering at IIIT Delhi, India, where I was advised by Prof. Vikram Goyal and Prof. Tanmoy Chakraborty. My research focuses on understanding and enhancing neural language generation models, particularly large language models (LLMs), and their applications in natural language processing tasks such as abstractive text summarization.

Resume

Research Interests

I am interested in enabling language models to continuously learn and adapt beyond their initial pretraining. My current research explores model editing, developing methods to update models efficiently with new information and corrections. I build modular systems that apply each change locally, allowing the model to evolve while retaining its existing knowledge. My long-term vision is to create models that learn like humans: accumulating knowledge over time, refining their understanding, and remaining robust as language, technology, and societal values change. Such systems could become trusted AI partners in critical areas like healthcare, education, and policy, where outdated information is not just inconvenient but potentially harmful. Such systems could become trustworthy AI partners in critical domains like healthcare, education, and policy, where being outdated is not just a limitation but a serious risk.

Publications

Model Editing with Graph-Based External Memory

Yash Kumar Atri, Ahmed Alaa, Thomas Hartvigsen
Preprint

Preprint 2025
Continually Self-Improving Language Models for Bariatric Surgery Question Answering

Yash Kumar Atri, Thomas H Shin, Thomas Hartvigsen
Preprint

Preprint 2025
Promoting Topic Coherence and Inter-Document Consorts in Multi-Document Summarization via Simplicial Complex and Sheaf Graph

Yash Kumar Atri, Arun Iyer, Tanmoy Chakraborty, Vikram Goyal
Paper

EMNLP 2023
Exploiting Representation Bias for Data Distillation in Abstractive Text Summarization

Yash Kumar Atri, Tanmoy Chakraborty, Vikram Goyal
Paper

Arxiv 2023
Multi-Document Summarization using Selective Attention Span and Reinforcement Learning

Yash Kumar Atri, Tanmoy Chakraborty, Vikram Goyal
Paper

TASL 2023
Fusing Multimodal Signals on Hyper-complex Space for Extreme Abstractive Text Summarization (TL;DR) of Scientific Contents

Yash Kumar Atri, Tanmoy Chakraborty, Vikram Goyal
Paper

SIGKDD 2023
Inline Citation Classification using Peripheral Context and Time-evolving Augmentation

Priyanshi Gupta, Yash Kumar Atri, Apurva Nagvenkar, Sourish Dasgupta, Tanmoy Chakraborty
Paper

PAKDD 2023
See, Hear, Read: Leveraging Multimodality with Guided Attention for Abstractive Text Summarization

Yash Kumar Atri^*, Shraman Pramanick^*, Vikram Goyal, Tanmoy Chakraborty
Paper

KBS 2021
Assessing the Quality of the Datasets by Identifying Mislabeled Samples

Vaibhav Pulastya, Gaurav Nuti, Yash Kumar Atri, Tanmoy Chakraborty
Paper

ASONAM 2021
Corpora Evaluation and System Bias detection in Multi Document Summarization

Alvin Dey^*, Tanya Chowdhury^*, Yash Kumar Atri^*, Tanmoy Chakraborty
Paper

EMNLP (Findings) 2020

Patents

SYSTEM AND METHOD FOR TEXT SUMMARIZATION, Application Number 202311015836, Publication Number 37/2024

Simran Kalra, Yash Kumar Atri, Tanmoy Chakraborty
Patent

2024

Tutorials

Building Blocks of AI-Driven Mental Health Counseling

Aseem Srivastava, Neeraj, Yash Kumar Atri, Shivani Kumar, Shad Akhtar, Tanmoy Chakraborty
Website

2023

Teaching

CSE557 - Big Data Analytics (Winter 2020), CSE506 - Data Mining (Monsoon 2020), CSE557 (Winter 2021), CSE506 (Monsoon 2021)

Head TA (Class of 300+ students)
TechTree

'20-21

Invited Talks

Lamarr Institute NLProc Colloquium at UBonn, Germany - title: Waking LLMs from CryoSleep with Continual Learning
ACM-India's Symposium for Academic Research and Careers for Students 2023, NISER Bhubhaneswar, India - title: Fairness in Abstractive Text Summarization
RIISE 2024, IIIT Delhi - Poster Presentation

Program Committees

Reviewer - ARR25, ICLR25, ARR24, EMNLP23, ACL23, BDA23, ICON22, EMNLP22, ASONAM22
Organizer & Coordinator - BDA 2023 conf, ICON 2023 conf, ACSS 2022, 2021, 2020, Cofad 2020 Workshops

Awards and Achievements

DAAD AInet Fellow 2025 - Postdoc-NeT-AI, Germany
Microsoft Travel Grant, iHub-Anubhuti Travel Grant - For Travel to Singapore for EMNLP 2023
Microsoft Travel Grant, iHub-Anubhuti Travel Grant, ACM-India Travel Grant (IARCS) - For Travel to Long Beach, USA for KDD 2023

Education

Ph.D. CSE, IIIT Delhi, India, 2020-2024
B. Tech. CSE, Jaypee University, India 2014-2018

Professional Experience

Research Associate at LCS2-IIITD, Sep. 2019-Aug. 2019
Software Engineer (Data Science) at Lumiq.ai, July 2018-Aug. 2019
AI Engineer (Intern) at Lumiq.ai, Feb. 2018-Jun. 2019
Data Scientist (Intern) at Primelite Technologies, May 2017-July 2017
Android Developer (Intern) at Trignosoft Technologies, May 2017-June 2017

Contact

Email: yashkumaratri [at] gmail.com Work Email: atri [@] virginia.edu Phone: +1 (434)-**6-1**1 (Please drop an email)