About
Viet Lai is a researcher at Adobe Research. Before that he worked at Kensho Technologies, the AI Research Hub of S&P Global. He completed his Ph.D. in Computer Science at the University of Oregon and his master degree in Computer Science in Computer Science at the Japan Advanced Institute of Science and Technology. He was advised by Prof. Thien Huu Nguyen and Prof. Minh Le Nguyen, respectively.
He was selected as the Adobe Research Award winner in 2022. The other awards he received includes Best paper Runner-up Award (MRL@EMNLP 2022) and Outstanding demo paper award (EACL 2021) for his work in multilingual understanding. He was an organizer of the AAAI Workshops on Scientific Document Understanding and Video Transcript Understanding. He has served as the program committee for ACL Rolling Review, ACL, NAACL, and EMNLP conferences and the Neural Computing and Transactions on Information Systems journals.
He studies effective and efficient methods for advancing AI in the era of multi-modality foundational models. Specifically, he is interested in the following topics:
- Factuality: Effective measuring of factual accuracy in AI-generated contents
- Multilinguality: Develop methods for low-resource languages
- Vision-Language Alignment: Effective and efficient model architectures for vision-language tasks
Contact me
|
daclai at adobe dot com |
|
| Office |
345 Park Avenue, San Jose, CA |
| Other | 
 |
Recent News
- May, 2025 - One paper accepted at CVEU Workshop (CVPR) in image editing.
- May, 2025 - Two papers accepted at ACL in LLM number understanding and GUI Agents.
- April, 2025 - One papers accepted at Reinforcement Learning Conference.
- Sep, 2024 - One paper to appear at EMNLP 2024 on multilingual factuality.
- Jul, 2024 - I joined Adobe Research in San Jose, CA
- May, 2024 - Two papers to appear at ACL 2024
- Sep, 2023 - I joined Kensho Technologies, the AI hub of S&P Global in Cambridge, MA
Mentees
I have been grateful to work with the following mentees:- Kim Trong Vu (Undergrad, KAIST)
Publications
2025
-
Understanding Generative AI Capabilities in Everyday Image Editing Tasks | CVEU Workshop (CVPR)
Mohammad Reza Taesiri, Logan Bolton, Brandon Collins, Viet Dac Lai, Franck Dernoncourt, Trung Bui, Anh Totti Nguyen -
Adaptive Submodular Policy Optimization | RLC
Branislav Kveton, Anup Rao, Viet Dac Lai, Nikos Vlassis, David Arbour -
Language Model Probabilities are Not Calibrated in Numeric Contexts | ACL
Charles Lovering, Michael Krumdick, Viet Dac Lai, Seth Ebner, Nilesh Kumar, Varshini Reddy, Rik Koncel-Kedziorski, Chris Tanner -
LUSIFER: Language Universal Space Integration for Enhanced Multilingual Embeddings with Large Language Models | SIGIR
Hieu Man, Nghia Trung Ngo, Viet Dac Lai, Ryan A Rossi, Franck Dernoncourt, Thien Huu Nguyen -
OWLViz: An Open-World Benchmark for Visual Question Answering | Preprint
Thuy Nguyen, Dang Nguyen, Hoang Nguyen, Thuan Luong, Long Hoang Dang, Viet Dac Lai -
GUI Agents: A Survey | ACL
Dang Nguyen, Jian Chen, Yu Wang, Gang Wu, Namyong Park, Zhengmian Hu, Hanjia Lyu, Junda Wu, Ryan Aponte, Yu Xia, Xintong Li, Jing Shi, Hongjie Chen, Viet Dac Lai, Zhouhang Xie, Sungchul Kim, Ruiyi Zhang, Tong Yu, Mehrab Tanjim, Nesreen K. Ahmed, Puneet Mathur, Seunghyun Yoon, Lina Yao, Branislav Kveton, Thien Huu Nguyen, Trung Bui, Tianyi Zhou, Ryan A. Rossi, Franck Dernoncourt -
SlimLM: An Efficient Small Language Model for On-Device Document Assistance | ACL Demo
Thang M. Pham, Phat T. Nguyen, Seunghyun Yoon, Viet Dac Lai, Franck Dernoncourt, Trung Bui
2024
-
DynaSaur: Large Language Agents Beyond Predefined Actions | Preprint
Dang Nguyen, Viet Dac Lai, Seunghyun Yoon, Ryan A. Rossi, Handong Zhao, Ruiyi Zhang, Puneet Mathur, Nedim Lipka, Yu Wang, Trung Bui, Franck Dernoncourt, Tianyi Zhou -
Taipan: Efficient and Expressive State Space Language Models with Selective Attention | Preprint
Chien Van Nguyen, Huy Huu Nguyen, Thang M. Pham, Ruiyi Zhang, Hanieh Deilamsalehy, Puneet Mathur, Ryan A. Rossi, Trung Bui, Viet Dac Lai, Franck Dernoncourt, Thien Huu Nguyen -
An Analysis of Multilingual FActScore | EMNLP
Kim Trong Vu, Michael Krumdick, Varshini Reddy, Franck Dernoncourt, Viet Dac Lai -
SEC-QA: A Systematic Evaluation Corpus for Financial QA | Preprint
Viet Dac Lai, Michael Krumdick, Charles Lovering, Varshini Reddy, Craig Schmidt, Chris Tanner -
MCECR: A Novel Dataset for Multilingual Cross-Document Event Coreference Resolution | NAACL (Findings)
Amir Pouran Ben Veyseh, Viet Dac Lai, Chien Van Nguyen, Franck Dernoncourt, Thien Huu Nguyen -
CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages | LREC-COLING
Thuat Nguyen, Chien Van Nguyen, Viet Dac Lai, Hieu Man, Nghia Trung Ngo, Franck Dernoncourt, Ryan A. Rossi, Thien Huu Nguyen -
CAMAL: A Novel Dataset for Multi-label Conversational Argument Move Analysis | LREC-COLING
Viet Dac Lai, Duy Pham, Jonathan Steinberg, Jamie Mikeska, Thien Huu Nguyen -
DocFinQA: A Long-Context Financial Reasoning Dataset | ACL
Varshini Reddy, Rik Koncel-Kedziorski, Viet Dac Lai, Chris Tanner -
BizBench: A Quantitative Reasoning Benchmark for Business and Finance | ACL
Rik Koncel-Kedziorski, Michael Krumdick, Viet Dac Lai, Varshini Reddy, Charles Lovering, Chris Tanner -
Using Machine Learning to Detect Student Learning Levels along a Learning Progression | NCME 2024
Duy Pham, Viet Dac Lai
2023
-
Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback | EMNLP Demo
Viet Dac Lai, Chien Van Nguyen, Nghia Trung Ngo, Thuat Nguyen, Franck Dernoncourt, Ryan A. Rossi, Thien Huu Nguyen -
Boosting Punctuation Restoration with Data Generation and Reinforcement Learning | INTERSPEECH
Viet Dac Lai, Abel Salinas, Hao Tan, Trung Bui, Quan Tran, Seunghyun Yoon, Hanieh Deilamsalehy, Franck Dernoncourt, Thien Huu Nguyen -
ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning | EMNLP (Findings)
Viet Dac Lai, Nghia Trung Ngo, Amir Pouran Ben Veyseh, Hieu Man, Franck Dernoncourt, Trung Bui, Thien Huu Nguyen -
Automated scoring of argumentation-focused teaching transcripts: Challenges and added value of human annotations | NCME
Duy Pham, Viet Dac Lai, Jamie Mikeska, Jonathan Steinberg, Heather Howell, Thien Huu Nguyen
2022
-
Few-Shot Cross-Lingual Learning for Event Detection | MRL@EMNLP 2022
Luis Guzman Nateras, Viet Dac Lai, Franck Dernoncourt and Thien Huu Nguyen -
Multilingual SubEvent Relation Extraction: A Novel Dataset and Structure Induction Method | Findings of EMNLP 2022
Viet Dac Lai, Hieu Man, Linh Ngo, Franck Dernoncourt and Thien Huu Nguyen -
MECI: A Multilingual Dataset for Event Causality Identification | COLING 2022
Viet Dac Lai, Amir Pouran Ben Veyseh, Minh Van Nguyen, Franck Dernoncourt and Thien Huu Nguyen -
Event Extraction in Video Transcripts | COLING 2022
Amir Pouran Ben Veyseh, Viet Dac Lai, Franck Dernoncourt and Thien Huu Nguyen -
SemEval 2022 Task 12: Symlink - Linking Mathematical Symbols to their Descriptions | SemEval 2022 @ NAACL
Viet Dac Lai, Amir Pouran Ben Veyseh, Franck Dernoncourt, and Thien Huu Nguyen -
BehancePR: A Punctuation Restoration Dataset for Livestreaming Video Transcript | Findings of NAACL 2022
Viet Dac Lai, Amir Pouran Ben Veyseh, Franck Dernoncourt, and Thien Huu Nguyen -
Event Detection for Suicide Understanding | Findings of NAACL 2022
Luis Guzman-Nateras, Viet Dac Lai, Amir Pouran Ben Veyseh, Franck Dernoncourt, and Thien Huu Nguyen -
BehanceCC: A ChitChat Detection Dataset For Livestreaming Video Transcripts | LREC 2022
Viet Dac Lai, Amir Pouran Ben Veyseh, Franck Dernoncourt, and Thien Huu Nguyen -
BehanceQA: A New Dataset for Identifying Question-Answer Pairs in Video Transcripts | LREC 2022
Amir Pouran Ben Veyseh, Viet Dac Lai, Franck Dernoncourt, and Thien Huu Nguyen
2021
-
Learning Prototype Representations Across Few-Shot Tasks for Event Detection | EMNLP 2021
Viet Dac Lai, Franck Dernoncourt, Thien Huu Nguyen -
Event Extraction from Historical Texts: A New Dataset for Black Rebellions | ACL-IJCNLP 2021
Viet Dac Lai, Minh Nguyen, Heidi Kaufman, Thien Huu Nguyen -
Unleash GPT-2 Power for Event Detection | ACL-IJCNLP 2021 (Findings)
Amir Pouran Ben Veyseh, Viet Dac Lai, Franck Dernoncourt, Thien Huu Nguyen -
Graph Learning Regularization and Transfer Learning for Few-Shot Event Detection | SIGIR 2021
Viet Dac Lai, Minh Nguyen, Thien Huu Nguyen, Franck Dernoncourt -
Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing | EACL 2021
Minh Van Ngo, Viet Dac Lai, Amir Pouran Ben Veyseh, Thien Huu Nguyen -
Cross-Task Instance Representation Interactions and Label Dependencies for Joint Information Extraction with Graph Convolutional Networks | NAACL-HLT 2021
Minh Van Nguyen, Viet Dac Lai, Thien Huu Nguyen
2020
-
Event Detection: Gate Diversity and Syntactic Importance Scores for Graph Convolution Neural Networks | EMNLP 2020
Viet Dac Lai, Tuan Ngo Nguyen and Thien Huu Nguyen -
Extensively Matching for Few-shot Learning Event Detection | NUSE@ACL 2020
Viet Dac Lai, Franck Dernoncourt, Thien Huu Nguyen -
Exploiting the Matching Information in the Support Set for Few Shot Event Classification | PAKDD 2020
Viet Dac Lai, Franck Dernoncourt, Thien Huu Nguyen
2019 and before
-
Extending Event Detection to New Types with Learning from Keywords | W-NUT@EMNLP 2019
Viet Dac Lai, Thien Huu Nguyen -
TSix: A Human-involved-creation Dataset for Tweet Summarization | LREC 2018
Minh-Tien Nguyen, Viet Dac Lai, Huy-Tien Nguyen and Minh-Le Nguyen -
Deletion-based sentence compression using Bi-enc-dec LSTM | PACLING 2017
Viet Dac Lai, Nguyen Truong Son, Nguyen Le Minh -
VSoLSCSum: Building a vietnamese sentence-comment dataset for social context summarization | ALR@COLING 2016
Minh-Tien Nguyen, Viet Dac Lai, Phong-Khac Do, Duc-Vu Tran, Minh-Le Nguyen
Patents
[12299026] Low Resource Event Understanding (US)
Improved Training Methods For Language Models Using Data Generation And Reinforcement Learning (US, pending)
SubEvent Relation Extraction (US, pending)
Reinforced Learning Approach To Generate Training Data (US, pending)
Awards
Best paper Runner-up Award, MRL@EMNLP, 2022
Erwin & Gertrude Juilfs Scholarship, CIS, UOregon, 2022
Adobe Research Fellowship, 2022
Outstanding demo paper award, EACL 2021
Best Graduate Teaching Assitant, CIS, UOregon, 2021
Services
Reviewer:
- ACL Rolling Review (Nov, Dec 2021)
- Neurocomputing, Transactions on Information Systems
- COLING(2020), SDU@AAAI (2021), NLPCC (2021)
Organizer: