Xin Luna Dong
lunadong@meta.com
9845 Willows Rd.
Redmond, WA 98052
Tel: (650) 788-0228

Xin Luna Dong

I lead machine-learning efforts for building intelligent personal assistants for Wearables at Meta Reality Labs, innovating on contextual AI, multi-modal conversations, search & QA, recommendation, and knowledge mining. Before Meta I spent nearly a decade on knowledge graphs at Amazon and Google, and another decade on data integration at AT&T Labs and the University of Washington, where I received my Ph.D. I am an ACM Fellow and IEEE Fellow for contributions to "knowledge graph construction and data integration", a recipient of the VLDB Women in Database Research Award and the VLDB Early Career Research Award, and an ACM Distinguished Speaker.

Google Scholar DBLP C.V. Resume ACM Speaker

Research Areas

CRAG multi-modal benchmark

Intelligent Assistants

2022–Present

Building trustworthy, multi-modal, and personalized AI assistants for wearable devices like Ray-Ban Meta smart glasses. Core work on RAG factuality, visual question answering, and personal memory search.

  • SCRIBES — Semi-structured extraction via RL (ICLR 2026)
  • CRAG — Comprehensive RAG Benchmark (NeurIPS 2024)
  • VisualLens — Personalization via visual history (NeurIPS 2025)
  • Head-to-Tail — LLM knowledge evaluation (NAACL 2024)

Recent papers below →

Knowledge Vault visualization

Knowledge Graphs

2013–2022

A decade of work on knowledge extraction, fusion, and evaluation — from Amazon Product Graph to Google Knowledge Vault and Knowledge-Based Trust.

  • Knowledge Vault — Web-scale knowledge fusion (KDD 2014)
  • AutoKnow — Self-driving product KG (KDD 2020)
  • Ceres — Semi-structured web extraction (VLDB 2018)
  • KBT — Source trustworthiness evaluation (VLDB 2015)

All KG papers →

Solomon project

Data Integration

2002–2015

Foundational research on truth discovery, copy detection, record linkage, and schema mapping. Includes the Solomon, Chronos, and Semex projects.

  • Truth discovery & copy detection (VLDB 2009–2013)
  • Data Integration with Uncertainties (Best of VLDB 2007)
  • Semex — Personal info management (Sigmod'05 Best Demo)
  • Deep transfer entity linkage (VLDB 2022)

All integration papers →

Resources

Wearables Benchmarks

A comprehensive suite of benchmarks open-sourced for evaluating Wearable AI—-spanning voice and vision, memory and retrieval, and tasks ranging from simple interactions to complex multimodal reasoning.

Hugging Face →

View all benchmarks →

📡 Paper Radar

Tracking research frontiers in LLM, RAG, Agents, Factuality, and more. Browse curated Scholar Picks, Paper of the Day, and topic-based exploration across 15+ research areas — from Pretraining and Reasoning to Knowledge Graphs, Multimodal, and Speech.

Explore Paper Radar →

🎓 From Zero to Research Frontier

A 4-week course pathway designed to take you from foundational concepts to the cutting edge of AI research. Includes curated reading lists, area surveys across key topics, and guided progression through landmark papers in each field.

Start the course →

View more resources → · View more services →

Recent Keynotes & Invited Talks

View all talks →

Media & Interviews

Books

Machine Knowledge

Machine Knowledge

Gerhard Weikum, Xin Luna Dong, Simon Razniewski & Fabian Suchanek.
Foundations and Trends in Databases, 2021.

Barnes & Noble →

Big Data Integration

Big Data Integration

Xin Luna Dong & Divesh Srivastava.
Morgan Claypool Publishers, 2015.

Publisher →

Recent Papers on Intelligent Assistants

Trustworthy Assistants, RAG & Factuality

  • Shicheng Liu, Kai Sun, Lisheng Fu, Xilun Chen, Xinyuan Zhang, Zhaojiang Lin, Rulin Shao, Yue Liu, Anuj Kumar, Wen-tau Yih, Xin Luna Dong. SCRIBES: Web-Scale Script-Based Semi-Structured Data Extraction with Reinforcement Learning. ICLR, 2026. [Link]
  • Kai Sun, Yin Huang, Srishti Mehra, Mohammad Kachuee, Xilun Chen, Renjie Tao, Zhaojiang Lin, Andrea Jessee, Nirav Shah, Alex L Betty, Yue Liu, Anuj Kumar, Wen-tau Yih, Xin Luna Dong. Knowledge Extraction on Semi-Structured Content: Does It Remain Relevant for Question Answering in the Era of LLMs? EACL, 2026. [Link]
  • Siddhant Arora, Haidar Khan, Kai Sun, Xin Luna Dong, Sajal Choudhary, Seungwhan Moon, Xinyuan Zhang, Adithya Sagar, Surya Teja Appini, Kaushik Patnaik, Sanat Sharma, Shinji Watanabe, Anuj Kumar, Yue Liu, Florian Metze, Zhaojiang Lin. Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage. arXiv, 2025. [Link]
  • Zhepei Wei, Xiao Yang, Kai Sun, Jiaqi Wang, Rulin Shao, Jingxiang Chen, Mohammad Kachuee, Teja Gollapudi, Yiwei Liao, Nicolas Scheffer, Rakesh Wanga, Anuj Kumar, Yu Meng, Wen-tau Yih, Xin Luna Dong. TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning. arXiv, 2025. [Link]
  • Yin Huang, Yifan Ethan Xu, Kai Sun, Vera Yan, Alicia Yi Sun, Haidar Khan, Jimmy Nguyen, Mohammad Kachuee, Zhaojiang Lin, Yue Liu, Aaron Colak, Anuj Kumar, Wen-tau Yih, Xin Luna Dong. ConfRAG: Confidence-Guided Retrieval-Augmented Generation. arXiv, 2025. [Link]
  • Mohammad Kachuee, Teja Gollapudi, Minseok Kim, Yin Huang, Kai Sun, Xiao Yang, Jiaqi Wang, Nirav Shah, Yue Liu, Aaron Colak, Anuj Kumar, Wen-tau Yih, Xin Luna Dong. PrismRAG: Boosting RAG Factuality with Distractor Resilience and Strategized Reasoning. EMNLP, 2025. [Link]
  • Yushi Sun, Kai Sun, Yifan Ethan Xu, Xiao Yang, Xin Luna Dong, Nan Tang, Lei Chen. KERAG: Knowledge-Enhanced Retrieval-Augmented Generation for Advanced Question Answering. EMNLP, 2025. [Link]
  • Aidan Hogan, Xin Luna Dong, Denny Vrandecic, Gerhard Weikum. Large Language Models, Knowledge Graphs and Search Engines: A Crossroads for Answering Users' Questions. arXiv, 2025. [Link]
  • Xiao Yang, Yifan Ethan Xu, Kai Sun, Jiaqi Wang, Lingkun Kong, Wen-tau Scott Yih, Xin Luna Dong. KDD Cup CRAG Competition: Systems, Finding, and Learning. IEEE Data Engineering Bulletin "Special Issue on RAG", 48(4), 2024. [Link]
  • Xiao Yang, Kai Sun, Hao Xin, Yushi Sun, Nikita Bhalla, Xiangsen Chen, Sajal Choudhary, Rongze Daniel Gui, Ziran Will Jiang, Ziyu Jiang, Lingkun Kong, Brian Moran, Jiaqi Wang, Yifan Ethan Xu, An Yan, Chenyu Yang, Eting Yuan, Hanwen Zha, Nan Tang, Lei Chen, Nicolas Scheffer, Yue Liu, Nirav Shah, Rakesh Wanga, Anuj Kumar, Wen-tau Scott Yih, Xin Luna Dong. CRAG — Comprehensive RAG Benchmark. NeurIPS, 2024. [Link][Hugging Face Daily Papers][Poster]
  • Yushi Sun, Hao Xin, Kai Sun, Yifan Ethan Xu, Xiao Yang, Xin Luna Dong, Nan Tang, Lei Chen. Are Large Language Models A Good Replacement of Taxonomies? PVLDB, 2024. [Link]
  • Kai Sun, Yifan Ethan Xu, Hanwen Zha, Yue Liu, Xin Luna Dong. Head-to-Tail: How Knowledgeable Are Large Language Models? A.K.A. Will LLMs Replace Knowledge Graphs? NAACL, 2024. [Link]

Multi-modal Assistants

  • Jeonghwan Kim, Renjie Tao, Sanat Sharma, Jiaqi Wang, Kai Sun, Zhaojiang Lin, Seungwhan Moon, Lambert Mathias, Anuj Kumar, Heng Ji, Xin Luna Dong. PixSearch: Pixel-Grounded Retrieval for Knowledgeable Large Multimodal Models. arXiv, 2026. [Link]
  • Jiaqi Wang, Xiao Yang, Kai Sun, Parth Suresh, Sanat Sharma, Adam Czyzewski, Derek Andersen, Surya Teja Appini, Arkav Banerjee, Sajal Choudhary, Shervin Ghasemlou, Ziqiang Guan, Akil Iyer, Haidar Khan, Lingkun Kong, Roy Luo, Tiffany Ma, Zhen Qiao, Tammy Stark, David Tran, Wenfang Xu, Skyler Yeatman, Chen Zhou, Gunveer Gujral, Yinglong Xia, Seungwhan Moon, Nicolas Scheffer, Nirav Shah, Eun Chang, Yue Liu, Florian Metze, Zhaleh Feizollahi, Andrea Jessee, Mangesh Pujari, Ahmed A Aly, Babak Damavandi, Rakesh Wanga, Anuj Kumar, Rohit Patel, Wen-tau Yih, Xin Luna Dong. CRAG-MM: Multi-modal Multi-turn Comprehensive RAG Benchmark. arXiv, 2025. [Link]
  • Eun Chang, Zhuangqun Huang, Yiwei Liao, Sagar Ravi Bhavsar, Amogh Param, Tammy Stark, Adel Ahmadyan, Xiao Yang, Jiaqi Wang, Ahsan Abdullah, Giang Nguyen, Akil Iyer, David Hall, Elissa Li, Shane Moon, Nicolas Scheffer, Kirmani Ahmed, Babak Damavandi, Rakesh Wanga, Anuj Kumar, Rohit Patel, and Xin Luna Dong. WearVQA: A Visual Question Answering Benchmark for Wearables in Egocentric Authentic Real-world Scenarios. NeurIPS, 2025. [Link]
  • Yichi Zhang, Xin Luna Dong, Zhaojiang Lin, Andrea Madotto, Anuj Kumar, Babak Damavandi, Joyce Chai, Shane Moon. Proactive Assistant Dialogue Generation from Streaming Egocentric Videos. EMNLP, 2025. [Link]
  • Xindi Wu, Uriel Singer, Zhaojiang Lin, Xide Xia, Andrea Madotto, Yifan Ethan Xu, Paul A. Crook, Xin Luna Dong, Shane Moon. Corgi: Cached Memory Guided Video Generation. WACV, 2025. [Link]
  • Jielin Qiu, Andrea Madotto, Zhaojiang Lin, Paul A. Crook, Yifan Ethan Xu, Xin Luna Dong, Christos Faloutsos, Lei Li, Babak Damavandi, Seungwhan Moon. SnapNTell: Enhancing Entity-Centric Visual Question Answering with Retrieval Augmented Multimodal LLM. EMNLP, 2024. [Link]
  • Ashish Shenoy, Yichao Lu, Srihari Jayakumar, Debojeet Chatterjee, Mohsen Moslehpour, Pierce Chuang, Abhay Harpale, Vikas Bhardwaj, Di Xu, Shicong Zhao, Longfang Zhao, Ankit Ramchandani, Xin Luna Dong, Anuj Kumar. Lumos: Empowering Multimodal LLMs with Scene Text Recognition. SigKDD, 2024. [Link]

Personal Memory & Personalization

  • Kai Zhang, Xinyuan Zhang, Ejaz Ahmed, Hongda Jiang, Caleb Kumar, Kai Sun, Zhaojiang Lin, Sanat Sharma, Shereen Oraby, Aaron Colak, Ahmed A Aly, Anuj Kumar, Xiaozhong Liu, Xin Luna Dong. AssoMem: Scalable Memory QA with Multi-Signal Associative Retrieval. ICLR, 2026. [Link]
  • Wang Bill Zhu, Deqing Fu, Kai Sun, Yi Lu, Zhaojiang Lin, Seungwhan Moon, Kanika Narang, Mustafa Canim, Yue Liu, Anuj Kumar, Xin Luna Dong. VisualLens: Personalization through Visual History. NeurIPS, 2025. [Link][Hugging Face Daily Papers]
  • Hongda Jiang, Xinyuan Zhang, Siddhant Garg, Rishab Arora, Shiun-Zu Kuo, Jiayang Xu, Ankur Bansal, Aaron Colak, Yue Liu, Ahmed Aly, Anuj Kumar, Xin Luna Dong. Memory-QA: Answering Recall Questions Based on Multimodal Memories. EMNLP, 2025. [Link]

General Voice Assistants

  • Zhaojiang Lin, Yong Xu, Kai Sun, Jing Zheng, Yin Huang, Surya Teja Appini, Krish Narang, Renjie Tao, Ishan Kapil Jain, Siddhant Arora, Ruizhi Li, Yiteng Huang, Kaushik Patnaik, Wenfang Xu, Suwon Shon, Yue Liu, Ahmed A Aly, Anuj Kumar, Florian Metze, Xin Luna Dong. WearVox: An Egocentric Multichannel Voice Assistant Benchmark for Wearables. ICLR, 2026. [Link]
  • Zekun Li, Zhiyu Zoey Chen, Mike Ross, Patrick Huber, Seungwhan Moon, Zhaojiang Lin, Xin Luna Dong, Adithya Sagar, Xifeng Yan, Paul A. Crook. Large Language Models as Zero-shot Dialogue State Tracker through Function Calling. ACL, 2024. [Link]