BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//ARNI - ECPv6.17.4//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://arni-institute.org
X-WR-CALDESC:Events for ARNI
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20250309T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20251102T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20260308T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20261101T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20270314T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20271107T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260802T100000
DTEND;TZID=America/New_York:20260802T180000
DTSTAMP:20260610T192956Z
CREATED:20260610T192956Z
LAST-MODIFIED:20260610T192956Z
UID:2563-1785664800-1785693600@arni-institute.org
SUMMARY:CCN 2026 Satelite Event: Modeling and Understanding Human Brain Computation at Scale
DESCRIPTION:Location: Zuckerman Institute (room TBD)\nDate and Time: August 2nd\, 10am to 6pm \nAbout:  \nRecent advances in deep learning and improvements in the quantity and quality of available human brain-activity data (including functional MRI\, EEG\, MEG\, and intracranial recordings) have made it possible to build accurate encoding models of the human brain that can predict neural activity for new visual and auditory stimuli in individual people\, even with generalization to new individuals. In parallel\, recent decoding models leverage prior information from generative multimodal models to extract rich perceptual and semantic content from brain activity with increasing fidelity. It remains unclear\, however\, how these technical advances can best be translated into theoretical advances (a better scientific understanding of human brain computation) and impactful applications for the benefit of humanity. \nOne important goal is to build human brain foundation models that are constrained simultaneously by rich stimulus data\, large-scale diverse brain-activity data\, and task performance requirements\, so as to capture the computations performed by the human brain. This satellite event “Modeling and Understanding Human Brain Computation at Scale” brings together researchers who build neural network models that capture shared structure in neural responses across the human population at scale and use the models to drive theoretical progress on the computations underlying human cognition and perception. A central theme is methodology: What mapping functions\, architectures\, and training regimes achieve strong generalization and enable interpretation? The event aims to foster dialogue between those collecting and modeling large-scale human brain data and those asking what such models can tell us about how the brain works and how human brain foundation models might be applied for human benefit.
URL:https://arni-institute.org/event/ccn-2026-satelite-event-modeling-and-understanding-human-brain-computation-at-scale/
LOCATION:To Be Determined
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260825T150000
DTEND;TZID=America/New_York:20260825T160000
DTSTAMP:20260824T214814Z
CREATED:20260824T214814Z
LAST-MODIFIED:20260824T214814Z
UID:2640-1787670000-1787673600@arni-institute.org
SUMMARY:ARNI Continual Learning Working Group Meeting
DESCRIPTION:Our discussion will focus on the Day in the Life benchmark. We’re aiming to submit a proposal to the ICLR workshops once the timing is confirmed (and potentially an ICLR paper as well\, with the deadline a month out)\, so we’d like to accelerate the push towards a working benchmark. \nZoom Link: Upon request @ arni@collumbia.edu
URL:https://arni-institute.org/event/arni-continual-learning-working-group-meeting-5/
LOCATION:Virtual
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260909T150000
DTEND;TZID=America/New_York:20260909T160000
DTSTAMP:20260527T143526Z
CREATED:20260501T134305Z
LAST-MODIFIED:20260527T143526Z
UID:2476-1788966000-1788969600@arni-institute.org
SUMMARY:Speaker: Alexandre Pouget - ARNI Distinguish Seminar Series
DESCRIPTION:Alexandre Pouget \nDate and Time: May 21st at 3pm \nLocation: Zuckerman Institute Kavli Auditorium 9th Floor \nTitle: Neural Models of Compositionality \nAbstract: Compositionality is widely regarded as one of the cornerstones of general intelligence. It refers to the ability to rapidly generate or learn new concepts by combining simpler ones according to an underlying syntax\, as exemplified in natural language. Compositionality was long thought to be primarily a human capacity and widely considered incompatible with artificial neural networks. Recent neural models\, however\, have begun to challenge this view. I will present two such models: one focused on simple cognitive tasks\, the other on the control of complex motor trajectories. In both cases\, few-shot learning emerges through the discovery of compositional solutions. Remarkably\, the latter approach captures key\, and often counterintuitive\, aspects of rodent behavior in escape tasks\, precisely the kind of setting in which animals exhibit near zero-shot learning. I will also discuss how these findings connect naturally to more sophisticated forms of compositionality in humans\, particularly the use of language to support zero-shot learning and inference. \nZoom link: Upon request @ arni@columbia.edu
URL:https://arni-institute.org/event/speaker-alexandre-pouget-arni-distinguish-seminar-series/
LOCATION:Zuckerman Institute- Kavli Auditorium 9th Fl\, 3227 Broadway\, NY
ORGANIZER;CN="ARNI":MAILTO:arni@columbia.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260914T150000
DTEND;TZID=America/New_York:20260914T160000
DTSTAMP:20260908T134304Z
CREATED:20260708T151148Z
LAST-MODIFIED:20260908T134304Z
UID:2573-1789398000-1789401600@arni-institute.org
SUMMARY:Speaker:Jarod Lévy and Lucy Zhang– ARNI Frontier Models for Neuroscience and Behavior Working Group
DESCRIPTION:Title: Brain2Qwerty: Noninvasive decoding of typed sentences from human brain activity \nAbstract: Restoring communication for people who have lost the ability to speak or move after a brain injury is a major challenge. While intracranial implants now enable high-performing brain-computer-interfaces\, non-invasive alternatives are still lagging behind. Here\, we present Brain2Qwerty v2\, a model that can decode the production of natural sentences solely from real-time magnetoencephalography (MEG) recordings. By collecting 22\,000 sentences typed by nine subjects\, each recorded for 10 hours\, our model leverages character\, word and sentence-level representations to achieve an average word error rate (WER) of 39%. For our best participant\, the model accurately decodes half of the sentences with one word error or less. Critically\, decoding accuracy log-linearly improves with data volume\, suggesting that the performance gap with intracranial approaches could be partially bridged through data scaling. We show that AI enables this performance in three main ways: the substitution of hand-crafted pipelines for event detection with deep learning\, the finetuning of large language models to extract semantic representations\, and the deployment of AI agents to iteratively refine our decoding pipeline via automated code development. Together\, these results show that non-invasive brain-to-text decoding starts to operate at a level of accuracy previously thought exclusive to surgical implants\, opening a path toward safe and efficient brain-computer-interfaces. \nZoom: Upon request @arni@columbia.edu
URL:https://arni-institute.org/event/speakerjarod-levy-meta-fair-paris-and-inria-mind-arni-frontier-models-for-neuroscience-and-behavior-working-group/
LOCATION:Virtual
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260917T140000
DTEND;TZID=America/New_York:20260917T170000
DTSTAMP:20260908T192821Z
CREATED:20260908T192800Z
LAST-MODIFIED:20260908T192821Z
UID:2647-1789653600-1789664400@arni-institute.org
SUMMARY:Speaker: Pratik Chaudhari ARNI WG Multi-resource-cost optimization of neural network models
DESCRIPTION:Pratik Chaudhari \n\n\n\n\n\n\nPratik Chaudhari is an Associate Professor in Electrical and Systems Engineering and Computer and Information Science at the University of Pennsylvania. He is also a Scholar at Amazon Web Services. Pratik is a core member of the GRASP Laboratory. From 2018-19\, he was a Senior Applied Scientist at Amazon Web Services and a Postdoctoral Scholar in Computing and Mathematical Sciences at Caltech. He received his PhD in Computer Science from UCLA\, and his Master’s and Engineer’s degrees in Aeronautics and Astronautics from MIT. Pratik was a part of NuTonomy Inc. (now Hyundai-Aptiv Motional) from 2014-16. He is the recipient of the Amazon Machine Learning Research Award\, NSF CAREER award and the Intel Rising Star Faculty Award.\n\n\n\n\n\n\nDate: September 17\, 2026 \nLocation: ZI L7-119 \nTime: 2:00pm \nTitle: How Has Learning Shaped Our World? \nAbstract: \nAlmost every sub-field of science\, engineering and business is rapidly adopting deep learning technology. I will argue that it is really the properties of natural data derived from the physical world that makes deep networks so effective. Correlations of typical inputs (images\, text\, sounds\, and even tabular data) are “sloppy”\, i.e.\, they exhibit geometric decay. Sloppy systems are neither perfectly robust nor perfectly tuned but instead exhibit a wide range of sensitivities that allows them to strike a balance between robustness and adaptability. This is what enables deep networks to generalize to new data. \nI will show that the training process in deep learning explores a remarkably low dimensional manifold\, as low as three. Networks with a wide variety of architectures\, sizes\, optimization and regularization methods lie on the same manifold. Networks being trained on different tasks (e.g.\, different subsets of ImageNet) using different methods (e.g.\, supervised\, transfer\, meta\, semi and self-supervised learning) also lie on the same low-dimensional manifolds. This is proof that there exist neural architectures with extremely few parameters—as few as 50—that can reproduce the predictions of networks with millions of weights. Architectures that exploit this phenomenon can reduce the energy required to build deep learning systems by multiple orders of magnitude. \nI will show that typical tasks that we perform with deep learning are highly redundant functions of their inputs. Many perception tasks\, from visual recognition\, semantic segmentation\, optical flow\, depth estimation\, to vocalization discrimination\, can be predicted extremely well regardless of whether data is projected in the principal subspace where it varies the most\, some intermediate subspace with moderate variability—or the bottom subspace where data varies the least. Any feature set is near-sufficient for most tasks. Ontogenetic learning refines neural circuitry to improve this feature set. I will argue that this redundancy could be—the serendipitous—consequence of the sensory apparatus of an organism adapting to a changing stream of ecological tasks. \nPrinciples that inform learning in artificial agents can also shed light upon learning in biological organisms. To that end\, I will describe results on developing visual perception for autonomous robots (flying platforms and quadrupeds) that operate in different environments (harsh daylight as well as night-time\, indoors and outdoors)\, at very high speeds (without motion blur) and with very little energy. \nZoom Link: Upon request @ arni@columbia.edu
URL:https://arni-institute.org/event/speaker-pratik-chaudhari-arni-wg-multi-resource-cost-optimization-of-neural-network-models/
LOCATION:Zuckerman Institute – L7-119\, 3227 Broadway\, New York\, NY\, 10027\, United States
END:VEVENT
END:VCALENDAR