- 'Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agents'
- 'Grounding Multilingual Multimodal LLMs With Cultural Knowledge' (Oral at EMNLP 2025)
- 'Synthetic Socratic Debates: Examining Persona Effects on Moral Decision and Persuasion Dynamics'
- 'FieldWorkArena: Agentic AI Benchmark for Real Field Work Tasks'
- 'VisualPuzzles: Decoupling Multimodal Reasoning Evaluation from Domain Knowledge'
- 'SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills'
- 'Beyond Browsing: API-Based Web Agents' (Findings at ACL 2025)
- 'Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia' (ACL 2025)
Awards:
- Best Paper Award at EMNLP 2024 for work on image transcreation in November 2024.
Research Experience
Interned as a software engineer in the AI/ML team at Intuit and as a software developer at PreVeil; Started research at CMU NeuLab as a BS/MS student in August 2024.
Education
First-year PhD student at Carnegie Mellon University (CMU) in Natural Language Processing; BS/MS dual degree in Computer Science and Statistics & Machine Learning from CMU; Advised by Professor Graham Neubig.
Background
Research Interests: Natural Language Processing (NLP), including Multimodal LLM, Web Agents, Multi-Agents, Multilingual NLP, and benchmarking.