The workshop will take place in Don Julián (floor 4).
09:00 - 09:15: Welcome
09:15 - 10:00: Keynote #1: Lydia Chilton
Augmenting Human Creativity: How AI and HCI Combine to Enable Better Design and Innovation
Abstract: One of the central aims of HCI is to augment human intelligence. Using the Design Process as a model for human design and innovation we show how NLP has impressive abilities to automate or augment subtasks in the design process that humans struggle with most. I present three systems that each use a combination of humans and NLP to solve design and creativity challenges: forging connections between products and pop culture, creating illustrations for news articles, and translating news into TikTok reels. We argue that advances in core NLP problems can unleash a wealth of human creativity.
Bio: Lydia Chilton is an Assistant Professor in the Computer Science Department at Columbia University. Her research is in computational design - how computation and AI can help people with design, innovation, and creative problem-solving. Applications include: creating media for journalism, developing technology for public libraries, improving risk communication during hurricanes, helping scientists explain their work, and improving mental health in marginalized communities. Dr. Chilton received her bachelor's degrees economics (2006) in computer science (2007) from MIT, her Master's in Engineering from MIT in 2009 and her PhD from the University of Washington in 2016. She was a post-doc at Stanford before joining Columbia Engineering in 2017.
10:00 - 10:30: Lightning talks #1
10:30 - 11:00: Break
11:00 - 11:45: Lightning talks #2
11:45 - 12:30: Group discussions #1
12:30 - 14:00: Lunch
14:00 - 14:45: Keynote #2: Sherry Tongshuang Wu
Practical AI Systems: From General-Purpose AI to (the Right) Specific Use Cases
Abstract: AI research has made great strides in developing general-purpose models (e.g., LLMs) that can excel across a wide range of tasks, enabling users to explore AI applications tailored to their unique needs without the complexities of custom model training. However, with the opportunities come the challenges — General-purpose models prioritize overall performance, but this can neglect specific user needs. How can we make these models practically usable? In this talk, I will present our recent work on assessing and tailoring general-purpose models for specific use cases. I will first cover methods for evaluating and mapping LLMs to specific usage scenarios, then reflect on the importance of identifying the right tasks for LLMs by comparing how humans and LLMs may perform the same tasks differently. In my final remarks, I will discuss the potential of training humans and LLMs with complementary skill sets.
Bio: Sherry Tongshuang Wu is an Assistant Professor in the Human-Computer Interaction Institute at Carnegie Mellon University. Her research lies at the intersection of Human-Computer Interaction and Natural Language Processing, and primarily focuses on how humans (AI experts, lay users, domain experts) can practically interact with (debug, audit, and collaborate with) AI systems. To this end, she has worked on assessing NLP model capabilities, supporting human-in-the-loop NLP model debugging and correction, as well as facilitating human-AI collaboration. She has authored award-winning papers in top-tier NLP, HCI and Visualization conferences and journals such as ACL, CHI, TOCHI, TVCG, etc. Before joining CMU, Sherry received her Ph.D. degree from the University of Washington and her bachelor degree from the Hong Kong University of Science and Technology, and has interned at Microsoft Research, Google Research, and Apple. You can find out more about her at http://cs.cmu.edu/~sherryw.
14:45 - 16:00: Poster session and break
16:00 - 16:45: Group discussions #2
16:45 - 17:00: Closing