Events
-
-
Speaker: Xuexin Wei ARNI WG Multi-resource-cost optimization of neural network models
Zuckerman Institute - L5-084 3227 Broadway, New York, NY, United StatesTitle: 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…
-
CTN: Farzaneh Najafi
Zuckerman Institute - L5-084 3227 Broadway, New York, NY, United States -
Speaker: Katherine Xu – Language and Vision Working Group
VirtualTitle: 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…
-
Speaker: Vijay Balasubramanian ARNI WG Multi-resource-cost optimization of neural network models
Zuckerman Institute - L3-079 3227 Broadway, New York, NY, United StatesTitle and Abstract: TBD
-
Lecture Series in AI: Richard Zemel
Davis Auditorium 530 W 120th St, New York, NY 10027, New York, NYGeneral 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 separate training and testing phases, and instead models are evaluated online while learning novel concepts and tasks. The most capable current AI systems struggle to…
-
ARNI Biological Learning Working Group
Continuation of prior meetings. Zoom: Upon request @[email protected]
-
Speaker Josue Ortega Caro: ARNI Frontier Models for Neuroscience and Behavior Working Group
VirtualTime: 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, motivating modeling approaches that can learn representations directly from large-scale data. Inspired by video foundational models, we study how the masked autoencoder training objective can…
-
-
Speaker: Hadi Vafaii ARNI WG Multi-resource-cost optimization of neural network models
Zuckerman Institute - L3-079 3227 Broadway, New York, NY, United StatesLocation: 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…
-
Speaker: Mengye Ren – ARNI Continual Learning Working Group Meeting
CEPSR 620 Schapiro 530 W. 120th StMengye 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…
-
ARNI Biological Learning Working Group
VirtualContinuation of prior meetings. Zoom: Upon request @[email protected]
-
CTN: Jack Lindsey (Anthropic)
Zuckerman Institute - L5-084 3227 Broadway, New York, NY, United StatesTitle: 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…
-
ARNI Continual Learning Working Group Meeting
CEPSR 620 Schapiro 530 W. 120th StContinuation from prior meeting. Zoom link: upon request @ [email protected]