About Me
Hi, this is Mitul Tiwari, until recently I was a Director of AI and Machine Learning Engineering at ServiceNow. Previously, I was the CTO and Cofounder of Passage AI, a conversational AI company. Earlier I was part of Search, Network, and Analytics Group at LinkedIn as Head of People You May Know and Growth Relevance. Previously, I worked at Kosmix as a Member of Technical Staff. I completed my PhD in Computer Science from University of Texas at Austin in 2007. Earlier I received my under graduation as a Bachelor of Technology in Computer Science and Engineering from Indian Institute of Technology, Bombay in Summer 2001. I joined UTCS in Fall 2001, and earned my Master of Science in Computer Science in 2003.
At ServiceNow, I led development of natural language processing driven production features including Conversational AI, Incident Auto Resolution, Question-Answering for Search, and Text2Code for Workflows. We built next generation of Natural Language Processing technologies using some of the latest Language Models and Deep Learning techniques and scaling to hundreds/thousands of large enterprise customers to improve work experience of 70M+ enterprise users.
At Passage AI, I built a conversational AI platform using the latest Deep Learning and Natural Language Processing technologies. Passage.AI's natural language understanding and processing platform can be used to create a intelligent conversational interface for any website or business.
At LinkedIn, I worked on data driven products such as "People You May Know" (PYMK). PYMK is a large-scale social recommendation system that analyzes billions of edges to predict social connections. Using Hadoop, PIG, Clojure, Machine Learning algorithms.
At Kosmix, I worked on document/tweet/query categorization, concept mining, query parsing, query expansion, and relevance of search results to improve the quality of pages generated for any given topic. I also worked on building high performance, scalable systems for data fetching, data storage, and distributed processing.
At UT Austin, I worked on algorithms for emerging network applications. In particular, my research focused on designing self-tuning algorithms for distributed resource allocation, especially for caching, monitoring, and scheduling problems. My advisor at UT Austin was Greg Plaxton. I also interacted with Harrick Vin and Mike Dahlin.
In the past I have worked with Soumen Chakrabarty and Inderjit Dhillon on web mining, clustering, and other data mining problems.
My interests include machine learning, AI, search, distributed systems, and network algorithms.
Recent Blog Posts
- Introducing TapeAgent: A Powerful Framework for Building and Optimizing AI Agents. October 2024.
- AI Agents, Agentic Patterns and DSPy. September, 2024.
- Mixture of experts LLMs. May, 2024.
- Domain Adaptation of Large Language Models and Aligning to Human Preferences. Feb, 2024.
- Large Language Models II: Attention, Transformers and LLMs Architecture. Jan, 2024.
- Highlights of Baylearn 2023. Jan, 2024.
- Exploring Zero-shot and Few-Shot Techniques for Intent Classification using LLMs. August, 2023.
- Using LLMs for Data Augmentation to Recognize Dialog Act. December, 2022.
- Language Models in NLP. October, 2022.
- Five Ways Artificial Intelligence Could Transform The In-Room Hotel Experience. November, 2019.
- Building Intelligent Conversational Interfaces. In InfoQ. October, 2019.
- Four Ways AI Technologies Will Deliver The Best Customer Experiences. June, 2019.
- AI In Retail: How Tech Is Changing The Customer Experience. March, 2019.
- Are You Ready For A Conversation With Your Car? November, 2018.
- How Multilingual Chatbots Will Change The Voice of Business. August, 2018.
- Influence of First Connections for a New Employee on Growth and Retention. June, 2016.
- Reinventing People You May Know at LinkedIn. September, 2015.
- Growth Diffusion at LinkedIn via Cascading Invitations. July, 2015.
- Organization Overlap on Social Networks and its applications to Link Prediction and Community Detection. July 2013.
- Related Searches at LinkedIn. July, 2012.
- Social Networking in Developing Regions. March, 2012.
- Notes from Conference on Recommender Systems 2011. December, 2011.
- Supervised Random Walk for link prediction. May, 2011.
- Summary of Haystack system paper from Facebook. April, 2011.
- Effectiveness of data. April, 2010.
- Organizing the web around concepts. In Altsearchengines.com, September 2009.
- Deep Web: The Hidden Treasure. In Altsearchengines.com, August 2009.
Publications
- TapeAgents: a Holistic Framework for Agent Development and Optimization. With Dzmitry Bahdanau, Nicolas Gontier, Gabriel Huang, Ehsan Kamalloo, Rafael Pardinas, Alex Piché, Jordan Prince Tremblay, Karam Ghanem, Soham Parikh, and Quaizar Vohra. Technical report, October 2024.
- Exploring Zero and Few-shot Techniques for Intent Classification. With Soham Parikh, Prashil Tumbade, and Quaizar Vohra. In Proceedings of ACL (Industry track), July 2023.
- Improving Dialogue Act Recognition with Augmented Data. With Khyati Mahajan, Soham Parikh, Quaizar Vohra, and Samira Shaikh. In Proceedings of EMNLP Gem Workshop, December 2022.
- Automated Utterance Generation. With Soham Parikh and Quaizar Vohra. In Proceedings of AAAI/IAAI, Februrary 2020.
- Dynamics of Large Multi-View Social Networks: Synergy, Cannibalization and Cross-View Interplay. With Yu Shi, Myunghwan Kim, Shaunak Chatterjee, Souvik Ghosh, Romer Rosales. In Proceedings of the 22nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), August 2016.
- BANARAN, with Atef Chaudhury and Myunghwan Kim. In Proceedings of the 25th International Conference Companion on World Wide Web (WWW), April 2016.
- Global Diffusion via Cascading Invitations: Structure, Growth, and Homophily, with Ashton Anderson, Jure Leskovec, Jon Kleinberg, and Daniel Huttenlocker. In Proceedings of the 24th International World Wide Web Conference (WWW), May 2015.
- The Browsemaps: Collaborative Filtering at LinkedIn, Lili Wu, Sam Shah, Sean Choi, Mitul Tiwari, Christian Posse. In Proceedings of the 6th ACM RecSys Workshop on Recommender Systems and the Social Web, October 2014.
- Modeling Impression Discounting in Large-scale Recommender Systems , Pei Li, Laks V.S. Lakshmanan, Mitul Tiwari, Sam Shah. In Proceedings of the 20th ACM Conference on Knowledge Discovery and Data Mining (KDD), August 2014.
- Structural Diversity in Social Recommender Systems, Xinyi Huang, Mitul Tiwari and Sam Shah. In Proceedings of the 5th ACM RecSys Workshop on Recommender Systems and the Social Web, October 2013.
- gate io app. With Digvijay S. Lamba, Nikesh Garera, Xiaoyong Chai, Sanjib Das, Sri Subramaniam, Anand Rajaraman, Venky Harinarayan, AnHai Doan. In Proceedings of the 39th International Conference on Very Large Data Bases (VLDB), August 2013.
- Social Media Analytics: The Kosmix Story. With Xiaoyong Chai, Omkar Deshpande, Nikesh Garera, Wang Lam, Digvijay S. Lamba, Lu Liu, Michel Tourn, Zoheb Vacheri, STS Prasad, Sri Subramaniam, Venky Harinarayan, Anand Rajaraman, Adel Ardalan, Sanjib Das, Paul Suganthan G.C., AnHai Doan. In IEEE Data Engingeering Bullettin, 36 (3), 4-12.
- Organizational Overlap on Social Networks and its Applications, Cho-Jui Hsieh, Mitul Tiwari, Deepak Agarwal, Xinyi (Lisa) Huang, and Sam Shah. In Proceedings of the 22nd International World Wide Web Conference (WWW), May 2013.
- Metaphor: a system for related search recommendations, Azarias Reda, Yubin Park, Mitul Tiwari, Christian Posse, and Sam Shah. In Proceedings of the 21st International Conference on Information and Knowledge Management (CIKM), October 2012.
- Related Searches at Linkedin, Azarias Reda, Yubin Park, Mitul Tiwari, Christian Posse, and Sam Shah. In the 35th Annual SIGIR Conference (Industrial Track), August 2012.
- Social Networking in Developing Regions, Azarias Reda, Sam Shah, Mitul Tiwari, Anita Lillie, and Brian Noble. In Proceedings of the International conference on Information and Communication Technologies and Development (ICTD), March 2012.
- Online Compression Caching, C. Greg Plaxton, Yu Sun, Mitul Tiwari, and Harrick Vin. In Proceedings of the 11th Scandinavian Workshop on Algorithm Theory (SWAT), July 2008.
- Online Aggregation over Trees, C. Greg Plaxton, Mitul Tiwari, and Praveen Yalagandula. In Proceedings of the 21st International Parallel and Distributed Processing Symposium (IPDPS), March 2007.
- Reconfigurable Resource Scheduling with Variable Delay Bounds, C. Greg Plaxton, Yu Sun, Mitul Tiwari, and Harrick Vin. In Proceedings of the 21st International Parallel and Distributed Processing Symposium (IPDPS), March 2007.
- Online Hierarchical Cooperative Caching, Xiaozhou Li, C. Greg Plaxton, Mitul Tiwari, and Arun Venkataramani. Theory of Computing Systems, 39:851-874, 2006. Note: This paper extends the lower bound results in our SPAA paper for any randomized online algorithm.
- Reconfigurable Resource Scheduling, C. Greg Plaxton, Yu Sun, Mitul Tiwari, and Harrick Vin. In Proceedings of the 18th Symposium on Parallelism in Algorithms and Architectures (SPAA), July 2006.
- Online Hierarchical Cooperative Caching, Xiaozhou Li, C. Greg Plaxton, Mitul Tiwari, and Arun Venkataramani. In Proceedings of the 16th Symposium on Parallelism in Algorithms and Architectures (SPAA), June 2004.
- Using Memex to archive and mine community Web browsing experience, Soumen Chakrabarti, Sandeep Srivastava, Mallela Subramanyam, Mitul Tiwari. In Proceedings of the 9th International World Wide Web Conference (WWW), May 2000.
- Memex: A Browsing Assistant for Collaborative Archiving and Mining of Surf Trails, Soumen Chakrabarti, Sandeep Shrivastava, Mallela Subramanyam, Mitul Tiwari. In Proceedings of the Very Large Data Base Conference (VLDB), September 2000.
Recent Presentations
- Lessons Developing Conversational AI Virtual Agents Data Council SF 2020
- Building Bots and Conversational AI, QCon 2017
- Recommendations, Bots and Conversational Interfaces, QCon 2016
- gate.io, Keynote talk at Big 2015.
- Large Scale Social Recommender Systems and their Evaluation, Keynote talk at REDD 2014 - International Workshop on Recommender Systems Evaluation: Dimensions and Design.
- Modeling Impression Discounting in Large-scale Recommender Systems, Paper presentation at 20th ACM Conference on Knowledge Discovery and Data Mining (KDD), August 2014.
- Large-Scale Social Recommender Systems at LinkedIn, Keynote talk in Applied Machine Learning and Data Science track at QCON, San Francisco, November 2013.
- Large-Scale Social Recommendation Systems: Challenges and Opportunities, Keynote talk at 4th International Conference on Social Recommender Systems at WWW, May 2013.
- Structural Diversity in Social Recommender Systems, Paper presentation in the 5th ACM RecSys Workshop on Recommender Systems and the Social Web, October 2013.
- Organizational Overlap on Social Networks and its Applications, at WWW, May 2013.
- Metaphor: a system for related search recommendations. Paper presentation at CIKM, October 2012.
- Related Searches at LinkedIn. Invited talk in the 35th Annual SIGIR Conference, August 2012.
- Social Network Analysis at LinkedIn . At University of Texas, Austin, Sept 2011.
- Building Data Driven Products using Hadoop at LinkedIn. In Big Data and Cloud Computing meetup, Aug 2011.
Recent Professional Activities
- Program Committee member for WSDM 2025, SIGIR 2024, WSDM 2024, SIGIR 2023, The Web 2023, WSDM 2023, SIGIR 2022, The Web 2022, WSDM 2022, The Web 2021, WSDM 2021, RecSys 2021, The Web 2020, WWW 2019, RecSys 2018, WWW Research Track 2018, WWW Demo Track 2018, WWW Research Track 2017, WWW Demo Track 2016, RecSys 2015, WWW Demo Track 2015, RecSys 2014, RecSys 2013, SIGIR Industrial track 2013.
- Co-chair for the 8th Workshop on Social Network Mining and Analysis (held with KDD), SNAKDD 2014.