Puneet Mathur I am a Research Scientist at Adobe. I completed my Ph.D. in CS at the University of Maryland, College Park, advised by Dr. Dinesh Manocha in Fall 2023. My research was focused on document understanding, information extraction, and long-context multimodal understanding (documents, language, audio, video). My work spanned machine learning, natural language processing, speech processing, video understanding, and multimodal deep learning. I did my Masters in Computer Science from UMD in 2021 and Bachelors in Engineering (B.E.) in Computer Engineering from Netaji Subhas Institute of Technology. I did AI research at MIDAS Labs at IIIT-Delhi in 2018-20. Email  /  CV  /  Google Scholar  /  LinkedIn

I was a research scientist intern at:

• [Summer 2023] Microsoft Research, Redmond with Dinei Florencio multimodal document information extraction.


• [Fall+Spring 2022] Facebook AI (now Meta), Menlo Park with Zhe Liu on long-context neural language modeling.


• [Summer 2022] Adobe Research, San Jose with Vlad Morariu and Rajiv Jain on language-guided document intelligence.


• [Spring 2021] Verisk AI, New Jersey (remote) with Maneesh Singh and Manish Shrivastava on document-level NLI.


• [Summer 2021] Adobe Research, San Jose (remote) with Vlad Morariu and Rajiv Jain on document hierarchy generation.


• [Summer 2020] Dataminr with Alejandro Jaimes and Joel Tetreault on duplicate event detection on social media.

Conference Papers

• MATSA: Multi-Agent Table Structure Attribution
  EMNLP 2024
  Puneet Mathur, Alexa Siu, Nedim Lipka, Tong Sun
  [Paper]
  


• DocEdit-v2: Document Structure Editing Via Multimodal LLM Grounding
  EMNLP 2024
  Manan Suri, Puneet Mathur, Franck Dernoncourt, Rajiv Jain, Vlad I Morariu, Ramit Sawhney, Preslav Nakov, Dinesh Manocha
  [Paper]
  


• Agent-DocEdit: Language-Instructed LLM Agent for Content-Rich Document Editing
  COLM 2024
  Te-Lin Wu, Rajiv Jain, Yufan Zhou, Puneet Mathur, Vlad I Morariu
  [Paper]
  


• DocPilot: Copilot for Automating PDF Edit Workflows in Documents
  ACL 2024
  Puneet Mathur, Alexa Siu, Varun Manjunatha, Tong Sun
  [Paper]
  


• DOC-RAG: ASR Language Model Personalization with Domain-Distributed Co-occurrence Retrieval Augmentation
  COLING 2024
  Puneet Mathur, Zhe Liu, Ke Li, Yingyi Ma, Gil Keren, Zeeshan Ahmed, Dinesh Manocha, Xuedong Zhang
  [Paper]
  


• Saliency-Aware Interpolative Augmentation for Multimodal Financial Prediction
  COLING 2024
  Samyak Jain, Parth Chhabra, Atula Neerkaje, Puneet Mathur, Ramit Sawhney, Shivam Agarwal, Preslav Nakov, Sudheer Chava and Dinesh Manocha
  [Paper]
  


• DocScript: Document-level Script Event Prediction
  COLING 2024
  Puneet Mathur, Rajiv Jain, Vlad Morariu, Aparna Garimella, Franck Dernoncourt, Jiuxiang Gu, Ramit Sawhney, Preslav Nakov, and Dinesh Manocha
  [Paper]
  


• PersonaLM: Language Model Personalization via Domain-distributed Span Aggregated K-Nearest N-gram Retrieval Augmentation
  EMNLP 2023
  Puneet Mathur, Zhe Liu, Ke Li, Yingyi Ma, Gil Keren, Zeeshan Ahmed, Dinesh Manocha, Xuedong Zhang
  [Paper]
  


• DocEdit: Language-guided Document Editing
  AAAI 2023
  Puneet Mathur, Rajiv Jain, Jiuxiang Gu, Franck Dernoncourt, Dinesh Manocha, Vlad Morariu
  [Paper]
  


• DocInfer: Document-level Natural Language Inference using Optimal Evidence Selection
  EMNLP 2022
  Puneet Mathur, Gautam Kunapuli, Riyaz Ahmad Bhat, Manish Shrivastava, Dinesh Manocha, Maneesh Singh
  [Paper]
  


• DocFin: Multimodal Financial Prediction and Bias Mitigation using Semi-structured Documents
  EMNLP 2022 (Findings)
  Puneet Mathur, Mihir Goyal, Ramit Sawhney, Ritik Mathur, Jochen L. Leidner, Franck Dernoncourt and Dinesh Manocha
  [Paper]
  


• LayerDoc: Layer-wise Extraction of Spatial Hierarchical Structure in Visually-Rich Documents
  WACV 2023
  Puneet Mathur, Rajiv Jain, Ashutosh Mehra, Jiuxiang Gu, Franck Dernoncourt, Anandhavelu N, Quan Tran, Verena Kaynig-Fittkau, Ani Nenkova, Dinesh Manocha, Vlad Morariu
  [Paper]
  


• MONOPOLY: Financial Prediction from MONetary POLicY Conference Videos Using Multimodal Cues
  ACM Multimedia 2022
  Puneet Mathur, Atula Tejaswi Neerkaje, Malika Chhibber, Ramit Sawhney, Fu-Ming Guo, Franck Dernoncourt, Sanghamitra Dutta, Dinesh Manocha
  [Paper]
  


• DocLayoutTTS: Dataset and Baselines for Layout-informed Document-level Neural Speech Synthesis
  Interspeech 2022
  Puneet Mathur, Franck Dernoncourt, Quan Hung Tran, Jiuxiang Gu, Ani Nenkova, Vlad Morariu, Rajiv Jain and Dinesh Manocha
  [Paper]
  


• PISA: PoIncaré Saliency-Aware Interpolative Augmentation
  Interspeech 2022
  Ramit Sawhney, Megh Thakkar, Vishwa Shah, Puneet Mathur, Vasu Sharma and Dinesh Manocha
  [Paper]
  


• DocTime: A Document-level Temporal Dependency Graph Parser
  NAACL 2022
  Puneet Mathur, Vlad I Morariu, Verena Kaynig-Fittkau, Jiuxiang Gu, Franck Dernoncourt, Quan Hung Tran, Ani Nenkova, Dinesh Manocha, Rajiv Jain
  [Paper]
  


• 3MASSIV: Multilingual, Multimodal and Multi-Aspect dataset of Social Media Short Videos
  CVPR 2022
  Vikram Gupta, Trisha Mittal, Puneet Mathur, Vaibhav Mishra, Mayank Maheshwari, Aniket Bera, Debdoot Mukherjee and Dinesh Manocha
  [Paper][Dataset]
  


• TIMERS: Document-level Temporal Relation Extraction
  ACL 2021
  Puneet Mathur, Rajiv Jain, Franck Dernoncourt, Vlad Morariu, Quan Hung Tran and Dinesh Manocha
  [Paper]
  


• Multimodal Multi-Speaker Merger & Acquisition (M3A) Financial Forecasting: A New Task, Dataset, and Neural Baselines
  ACL 2021
  Ramit Sawhney, Mihir Goyal, Prakhar Goel, Puneet Mathur, Rajiv Ratn Shah
  [Paper]
  


• Affect2MM: Affective Analysis of Multimedia Content Using Emotion Causality
  CVPR 2021
  Trisha Mittal, Puneet Mathur, Aniket Bera, Dinesh Manocha
  [Paper]
  


• Multitask Learning for Emotionally Analyzing Sexual Abuse Disclosures
  NAACL 2021
  Ramit Sawhney, Puneet Mathur, Taru Jain, Akash Kumar Gautam, Rajiv Ratn Shah
  [Paper]
  


• Dynamic Graph Modeling of Simultaneous EEG and Eye-tracking Data For Reading Task Identification
  ICASSP 2021
  Puneet Mathur, Trisha Mittal, Dinesh Manocha
  [Paper]
  


• Meta learning for Low Resource Speech Emotion Recognition
  ICASSP 2021
  Suransh Chopra*, Puneet Mathur*, Ramit Sawhney, Rajiv Ratn Shah
  [Paper]
  


• Multimodal Multitask Financial Risk Forecasting
  ACM Multimedia 2020 (Oral)
  Ramit Sawhney, Puneet Mathur, Piyush Khanna, Ayush Mangal, Rajiv Ratn Shah
  [Paper]
  


• VolTAGE: Volatility Forecasting via Text Audio Fusion with Graph Convolution Networks for Earnings Calls
  EMNLP 2020
  Ramit Sawhney, Arshiya Aggarwal, Piyush Khanna, Taru Jain, Puneet Mathur, Rajiv Ratn Shah
  [Paper]
  


• Risk Forecasting from Earnings Calls Acoustics and Network Correlations
  Interspeech 2020
  Ramit Sawhney, Arshiya Aggarwal, Piyush Khanna, Puneet Mathur, Taru Jain, Rajiv Ratn Shah
  [Paper]
  


• Mixup Multi-Attention Multi-Tasking Model for Early-Stage Leukemia Identification
  ICASSP 2020
  Puneet Mathur*, Mehak Piplani*, Ramit Sawhney, Rajiv Ratn Shah
  [Paper]
  


• Rethinking Retinal Landmark Localization as Pose Estimation: Naive Single Stacked Network for Optic Disk and Fovea Detection
  ICASSP 2020
  Shishira Maiya*, Puneet Mathur*
  [Paper]
  


• Utilizing Temporal Psycholinguistic Cues for Suicidal Intent Estimation
  ECIR 2020 (Short)
  Puneet Mathur, Ramit Sawhney, Shivang Chopra and Rajiv Ratn Shah
  [ Paper ]
  


• #MeTooMA: Multi-Aspect Annotations of Tweets Related to the MeToo Movement
  ICWSM 2020
  Akash Gautam*, Puneet Mathur*, Rakesh Gosangi, Debanjan Mahata, Ramit Sawhney and Rajiv Ratn Shah
  [Paper][Dataset]
  


• Hindi-English Hate Speech Detection: Author Profiling, Debiasing, and Practical Perspectives
  AAAI 2020 (Oral)
  Shivang Chopra, Ramit Sawhney, Puneet Mathur and Rajiv Ratn Shah
  [ Paper ]
  


• Exploring Classification of Histological Disease Biomarkers from Renal Biopsy Images
  IEEE Winter Conference on Applications of Computer Vision (WACV) 2019
  Puneet Mathur*, Meghna P. Ayyar*, Rajiv Ratn Shah and Shree G Sharma
  [ Paper] [ Poster] [ Video Presentation ]
  

Workshop Papers

• Suicide Risk Assessment via Temporal Psycholinguistic Modeling
  AAAI Student Abstract and Poster 2020
  Puneet Mathur, Ramit Sawhney and Rajiv Ratn Shah
  [ Paper ]
  


• An Iterative Approach for Identifying Complaint Based Tweets in Social Media Platforms
  AAAI Student Abstract and Poster 2020
  Gyanesh Anand, Akash Kumar Gautam, Puneet Mathur, Debanjan Mahata, Rajiv Ratn Shah and Ramit Sawhney
  [ Paper ]
  


• SNAP-BATNET: Cascading Author Profiling and Social Network Graphs for Suicide Ideation Detection on Social Media
  NAACL Student Research Workshop 2019
  Rohan Mishra∗, Pradyumna Prakhar Sinha∗, Ramit Sawhney, Debanjan Mahata, Puneet Mathur, Rajiv Ratn Shah
  [ Paper]
  


• Speak Up, Fight Back! Detection of Social Media Disclosures of Sexual Harassment
  NAACL Student Research Workshop 2019
  Arijit Ghosh Chowdhury∗, Ramit Sawhney∗, Puneet Mathur, Rajiv Ratn Shah
  [ Paper]
  


• Identification of Emergency Blood Donation Request on Twitter
  Social Media Mining for Health Applications Workshop (SMM4H), EMNLP 2018
  Puneet Mathur, Meghna Ayyar, Sahil Chopra, Simra Shahid, Laiba Mehnaz and Rajiv Shah
  [ Paper] [ Poster] [ Dataset ] [ Demo ]
  


• Did You Offend Me? Classification of Offensive Tweets in Hinglish Language
  Abusive Language Workshop (ALW2), EMNLP 2018
  Puneet Mathur, Ramit Sawhney, Meghna Ayyar and Rajiv Shah
  [ Paper] [ Poster] [ Dataset ]
  


• Exploring and Learning Suicidal Ideation Connotations on Social Media with Deep Learning
  WASSA, EMNLP 2018
  Ramit Sawhney, Prachi Manchanda, Puneet Mathur, Rajiv Shah and Raj Singh
  [ Paper] [ Poster]
  


• Detecting Offensive Tweets in Hindi-English Code-Switched Language
  Workshop on Natural Language Processing for Social Media (Social NLP), ACL 2018
  Puneet Mathur, Rajiv Shah, Ramit Sawhney, and Debanjan Mahata
  [ Paper] [ Video Presentation ]