Events

Title: Constraints of efficient neural computation Abstract: Neural systems adapt to the statistical structure of the environment to support behavior. While it is generally recognized that such adaptation is subject…

Title: Are Vision-Language Models Checking or Looking? Abstract: Today’s AI vision systems are trained on vast amounts of data, yet it remains unclear whether they simply retrieve memorized answers or actively…

Title and Abstract: TBD

General website Title: Integrating Past and Present in Continual Learning Abstract: Continual learning aims to bridge the gap between typical human and machine-learning environments. The continual setting does not have…

Continuation of prior meetings. Zoom: Upon request @[email protected]    

Time: 30th March. 3pm EST Title: Large scale models for spatiotemporal data. Speaker: Josue Ortega Caro https://josueortc.github.io/ Abstract:  Spatiotemporal and multimodal datasets contain structured variability distributed across space, time, and measurement modality,…

Location: ZI L3-079 Time: 1:00pm Title: Metabolic cost of information processing in Poisson variational autoencoders Abstract:Computation in biological systems is fundamentally energy-constrained, yet standard theories of computation treat energy as freely available. Here, we argue that variational free energy minimization under a Poisson assumption offers a principled path toward an energy-aware theory of computation. Our…

Mengye Ren Mengye will also be giving a talk on continual learning at the Zemel group meeting an hour prior (at 2pm) that working group attendees are welcome to join if interested. Here's the abstract of his talk: Today's AI models primarily acquire knowledge through offline, i.i.d. learning. While in-context learning offers some capacity for online…

Continuation of prior meetings. Zoom: Upon request @[email protected]

Title: The inner lives of language models Abstract: In recent years, LLMs have evolved from bad text completion engines, to decent chatbots, to digital genies that work miracles on your computer (while making the occasional catastrophic error). The increasing sophistication of AI models’ behavior has been accompanied by a commensurate enrichment of their internal representations…

Ellie Pavlick (Assistant Professor of Computer Science and Linguistics, Brown University and Director, NSF Institute on Interaction for AI Assistants (ARIA)) Location: ZI Kavli Auditorium 9th Floor Time: 3:00pm Title: (How) Does AI Think? Abstract: The increasingly human-like behavior of AI has led to a fascination with ascribing it human-like internal properties -- notions like…