1005 Alcyon Dr Bellmawr NJ 08031
+1 484-446-2566
support@bmcpros.com
Imagine a boom that can track your every move and suggest music to match your personal dance style. That’s the idea behind “Be the Beat,” one of several projects from MIT course 4.043/4.044 (Interaction Intelligence), taught by Marcelo Coelho in the Department of Architecture, that were presented at the 38th annual NeurIPS (Neural Information Processing Systems) conference in December 2024. With over 16,000 attendees converging in Vancouver, NeurIPS is a competitive and prestigious conference dedicated to research and science in the field of artificial intelligence and machine learning, and the main venue for showing cutting-edge development.
The course investigates emerging areas of large language objects and how artificial intelligence can be extended into the physical world. While “Be Be The Beat” transforms the creativity of dance, other students’ submissions cover subjects such as music, storytelling, critical thinking and memory, creating generated experiences and new forms of human computer interaction. To sum up, these projects illustrate a broader vision for artificial intelligence: a vision that goes beyond automation and cannot catalyze creativity, reshapes education and reimagines social interactions.
Become a beat
MIT mechanical engineering and design student Ethan Chang and MIT mechanical engineering and music student Zhixing Chen is “Be Be Beat”, an AI-powered Boombox that hints at the music of dancers’ movement. Traditionally, dance is guided by music throughout history and throughout culture, but the concept of dance creating music is rarely explored.
“Becoming a Beat” creates a space for freestyle dance human collaboration, giving dancers the ability to rethink the traditional dynamics between dance and music. It uses POSENET to describe the movements of large language models, allowing it to analyze dance styles and query APIs to find music with similar styles, energy, and rhythms. Dancers who interact with Boombox report more control over artistic expression and describe Boombox as a novel approach to creatively discover dance genres and choreography.
Mystery for you
“The Mystery to You” by Mrinalini Singha SM ’24, he is the latest graduate of the Arts, Culture, and Technology program, while Haoheng Tang, the latest graduate of Harvard Graduate School of Design, is an educational game designed to develop the critical thinking and fact-checking skills of young learners. The game uses large language models (LLM) and tangible interfaces to create an immersive investigation experience. Players act as citizen fact inspectors in response to AI-generated “news alerts” printed on the game interface. By inserting the cartridge combination to prompt a follow-up “news update”, they browse ambiguous scenarios, analyzing evidence and weighing conflicting information to make informed decisions.
This interactive experience of human computers challenges our news consumption habits by eliminating the touch screen interface and replacing permanent scrolling and degreased readings with rich analog devices. By combining the affordability of slow media with new generative media, the game promotes thoughtful, embodied interactions while providing players with a better understanding and challenge today’s polarized media landscape, in which false information and manipulative narratives flourish.
memorandum
“Memorscope” created by MIT Media Lab research collaborator Keunwook Kim is a device that creates collective memory through in-depth human face-to-face interaction with advanced AI technology. Inspired by how we use microscopes and telescopes to examine and discover hidden and invisible details, MemorsCope allows two users to “investigate” each other’s faces and use this intimate interaction as a portal to create and explore their shared memories.
The device uses AI models such as Openai and Midjourney to introduce different aesthetic and emotional interpretations, thus bringing dynamic and collective memory space. This space goes beyond the limitations of traditional shared albums and provides a smooth interactive environment in which memory is not only a static snapshot, but also a life, evolving narrative shaped by the ongoing relationship between users.
Naratrang
“Narratron” by Harvard design students xiying (Aria) Bao and Yubo Zhao is an interactive projector that uses large language models to create and co-create children’s stories through Shadow Puppetry. Users can press the shutter to the “capture” protagonist they want to be in the story and use handmade shadows (such as animal shapes) as input to the main character. Then, the system develops the storyline as new shadow characters are introduced. The story appears through a projector as the background of the shadow puppet, and is told through the speaker, when the user sets the crank to “play” in real time. By combining visual, auditory, and body interactions in one system, the project aims to inspire the creativity of shadow drama storytelling and enable multimodal human AI collaboration.
Perfect syntax
Karyn Nakamura ’24’s “Perfect Grammar” is a video artwork that studies the syntactic logic behind movement and video. The project uses AI to manipulate video clips and explores how the fluidity of motion and time can be simulated and reconstructed by machines. Nakamura’s work draws inspiration from philosophical inquiry and artistic practice, inquiring about the relationship between perception, technology and the movements that shape our experience of the world. By reconceiving the video through a computational process, Nakamura examines how machines understand and represent the complexity of time and motion.