Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Paper: DPO Learning with LLMs-Judge Signal for Computer Use Agents
- Paper: SK-VQA accepted to ICML 2025 Oral Presentation (less than 1% acceptance rate)
- Paper: Revolve accepted to ICML 2025
- Paper: FiVL: A Framework for Improved Vision-Language Alignment
- Paper: EMRank accepted to IEEE Big Data for Healthcare
- Paper: SA-OcrPaint accepted to WACV 2025
- Survey paper: Ret-ICL accepted to TMLR
- Paper: SK-VQA released
- Book: Advances in Multimodal Information Retrieval and Generation published
- Paper: LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models
- Multimodal-query retriever dataset publicly available on GitHub
- Paper: commonsense assumption of language models available on arXiv
- Paper: Dr.ICL: Demonstration-Retrieved In-context Learning available on arXiv
- Paper: end-to-end multimodal retriever accepted to ACL 23
- Paper: hybrid efficient retriever accepted to ACL 23
- Successfully defended Ph.D. dissertation: Neural Retrieval and Reader for Information Retrieval and Question Answering
- Invited talk at SERUM @ WACV 2023
- Two papers accepted to NAACL 2022 SRW
- One paper accepted to NAACL 2022 Finding
- One paper accepted to ACL 2022
Research Experience
- AI Research Scientist at Intel Lab, multimodal cognitive AI team
- Research Fellow at Mayo Clinic
- Interned at Salesforce, Meta, and Google, collaborating with industry researchers
Education
- Earned a Ph.D. in 2023 from Arizona State University under the supervision of Dr. Chitta Baral
- Worked as a research fellow at Mayo Clinic, AZ, collaborating closely with Dr. Imon Banerjee and Dr. Bhavik Patel
Background
- Currently an AI Research Scientist at Intel Lab, multimodal cognitive AI team
- Research interests include post-training of multimodal and language models, multimodal retrieval and generation, synthetic data pipelines, computer use agents, and multimodal applications in healthcare