BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Penn Engineering Events - ECPv6.15.18//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Penn Engineering Events
X-ORIGINAL-URL:https://seasevents.nmsdev7.com
X-WR-CALDESC:Events for Penn Engineering Events
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:20230312T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20231105T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20240310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20241103T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20250309T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20251102T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240212T110000
DTEND;TZID=America/New_York:20240212T120000
DTSTAMP:20260403T210333
CREATED:20240201T134202Z
LAST-MODIFIED:20240201T134202Z
UID:10007836-1707735600-1707739200@seasevents.nmsdev7.com
SUMMARY:ESE Spring Seminar - "Physics-inspired Machine Learning"
DESCRIPTION:Combining physics with machine learning is a rapidly growing field of research. Thereby\, most work focuses on leveraging machine learning methods to solve problems in physics. Here\, however\, we focus on the converse\, i.e.\, physics-inspired machine learning\, which can be described as incorporating structure from physical systems into machine learning methods to obtain models with better inductive biases. More concretely\, we propose several physics-inspired deep learning architectures for sequence modelling based on nonlinear coupled oscillators\, Hamiltonian systems and multi-scale dynamical systems. The proposed architectures tackle central problems in the field of recurrent sequence modeling\, namely the vanishing and exploding gradients problem as well as the issue of insufficient expressive power. Moreover\, we discuss physics-inspired learning on graphs\, wherein the dynamics of the message-passing propagation are derived from physical systems. We further prove that these methods mitigate the over-smoothing issue\, thereby enabling the construction of deep graph neural networks (GNNs). We extensively test all proposed methods on a variety of versatile synthetic and real-world datasets\, ranging from image recognition\, speech recognition\, natural language processing (NLP)\, medical applications\, and scientific computing for sequence models\, to citation networks\, computational chemistry applications\, and networks of articles and websites for graph learning models. Finally\, we show how to leverage physics-based inductive biases of physics-inspired machine learning methods to solve problems in the physical sciences.
URL:https://seasevents.nmsdev7.com/event/ese-spring-seminar-tbd/
LOCATION:Glandt Forum\, Singh Center for Nanotechnology\, 3205 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Colloquium
ORGANIZER;CN="Electrical and Systems Engineering":MAILTO:eseevents@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240212T130000
DTEND;TZID=America/New_York:20240212T150000
DTSTAMP:20260403T210333
CREATED:20240112T192252Z
LAST-MODIFIED:20240112T192252Z
UID:10007801-1707742800-1707750000@seasevents.nmsdev7.com
SUMMARY:BE Doctoral Dissertation Defense: "Computational imaging and multiomic biomarkers for precision medicine: characterizing heterogeneity in lung cancer" (Apurva Singh)
DESCRIPTION:The Department of Bioengineering at the University of Pennsylvania and Dr. Despina Kontos are pleased to announce the Doctoral Dissertation Defense of Apurva Singh.\n\nTitle:  “Computational imaging and multiomic biomarkers for precision medicine: characterizing heterogeneity in lung cancer”\nDate: February 12\, 2024\nTime: 1:00 PM\nLocation:  John Morgan Building\, Class of 62 auditorium\n\nZoom link\n\nThe public is welcome to attend.
URL:https://seasevents.nmsdev7.com/event/be-doctoral-dissertation-defense-computational-imaging-and-multiomic-biomarkers-for-precision-medicine-characterizing-heterogeneity-in-lung-cancer-apurva-singh/
LOCATION:Class of 62 Auditorium\, John Morgan Building\, 3620 Hamilton Walk\, Philadelphia\, PA\, 19104
CATEGORIES:Doctoral,Graduate,Student,Dissertation or Thesis Defense
ORGANIZER;CN="Bioengineering":MAILTO:be@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240213T100000
DTEND;TZID=America/New_York:20240213T113000
DTSTAMP:20260403T210333
CREATED:20240207T163149Z
LAST-MODIFIED:20240207T163149Z
UID:10007848-1707818400-1707823800@seasevents.nmsdev7.com
SUMMARY:MEAM Seminar: "AI for Antibiotic Discovery"
DESCRIPTION:Computers can be programmed for superhuman pattern recognition of images and text; however\, their application in biology and medicine is still in its infancy. In this talk\, I will discuss our advances over the past half-decade\, which are accelerating discoveries in the crucial and underinvested area of antibiotic discovery. We developed the first antibiotic designed by a computer with proven efficacy in preclinical animal models\, demonstrating that machines and artificial intelligence (AI) could be used to design therapeutic molecules. Our algorithms have accelerated antibiotic discovery\, and for the first time\, we successfully mined the human proteome for antibiotics. Recently\, we expanded our proteome-mining efforts to explore the proteomes of extinct species. Using AI\, my lab discovered the first therapeutic molecules in extinct organisms\, including Neanderthals and Denisovans\, launching the field of molecular de-extinction. Collectively\, our efforts have dramatically reduced the time needed to discover preclinical antibiotic candidates from years to hours. I believe we are on the cusp of a new era in science where advances enabled by AI will help control antibiotic resistance\, infectious disease outbreaks\, and pandemics.
URL:https://seasevents.nmsdev7.com/event/meam-seminar-ai-for-antibiotic-discovery/
LOCATION:Wu and Chen Auditorium (Room 101)\, Levine Hall\, 3330 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Seminar
ORGANIZER;CN="Mechanical Engineering and Applied Mechanics":MAILTO:meam@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240213T110000
DTEND;TZID=America/New_York:20240213T120000
DTSTAMP:20260403T210333
CREATED:20240201T134437Z
LAST-MODIFIED:20240201T134437Z
UID:10007837-1707822000-1707825600@seasevents.nmsdev7.com
SUMMARY:ESE & CIS Spring Seminar - "Beyond the black box: characterizing and improving how neural networks learn"
DESCRIPTION:The predominant paradigm in deep learning practice treats neural networks as “black boxes”. This leads to economic and environmental costs as brute-force scaling remains the performance driver\, and to safety issues as robust reasoning and alignment remain challenging. My research opens up the neural network black box with mathematical and statistical analyses of how networks learn\, and yields engineering insights that improve the efficiency and transparency of these models. In this talk I will present characterizations of (1) how large language models can learn to reason with abstract symbols\, and (2) how hierarchical structure in data guides deep learning\, and will conclude with (3) new tools to distill trained neural networks into lightweight and transparent models.
URL:https://seasevents.nmsdev7.com/event/ese-spring-seminar-tbd-2/
LOCATION:Raisler Lounge (Room 225)\, Towne Building\, 220 South 33rd Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Colloquium
ORGANIZER;CN="Electrical and Systems Engineering":MAILTO:eseevents@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240214T120000
DTEND;TZID=America/New_York:20240214T131500
DTSTAMP:20260403T210333
CREATED:20230928T142325Z
LAST-MODIFIED:20230928T142325Z
UID:10007713-1707912000-1707916500@seasevents.nmsdev7.com
SUMMARY:ASSET Seminar: "Enforcing Right to Explanation: Algorithmic Challenges and Opportunities" (Himabindu Lakkaraju\, Harvard University)
DESCRIPTION:ABSTRACT: \nAs predictive and generative models are increasingly being deployed in various high-stakes applications in critical domains including healthcare\, law\, policy and finance\, it becomes important to ensure that relevant stakeholders understand the behaviors and outputs of these models so that they can determine if and when to intervene. To this end\, several techniques have been proposed in recent literature to explain these models. In addition\, multiple regulatory frameworks (e.g.\, GDPR\, CCPA) introduced in recent years also emphasized the importance of enforcing the key principle of “Right to Explanation” to ensure that individuals who are adversely impacted by algorithmic outcomes are provided with an actionable explanation. In this talk\, I will discuss the gaps that exist between regulations and state-of-the-art technical solutions when it comes to explainability of predictive and generative models. I will then present some of our latest research that attempts to address some of these gaps. I will conclude the talk by discussing bigger challenges that arise as we think about enforcing right to explanation in the context of large language models and other large generative models. \nZOOM LINK (if unable to attend in-person): https://upenn.zoom.us/j/94929617939
URL:https://seasevents.nmsdev7.com/event/asset-seminar-himabindu-lakkaraju-harvard-university/
LOCATION:Raisler Lounge (Room 225)\, Towne Building\, 220 South 33rd Street\, Philadelphia\, PA\, 19104\, United States
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240214T150000
DTEND;TZID=America/New_York:20240214T160000
DTSTAMP:20260403T210333
CREATED:20240124T151237Z
LAST-MODIFIED:20240124T151237Z
UID:10007822-1707922800-1707926400@seasevents.nmsdev7.com
SUMMARY:Spring 2024 GRASP SFI: Fei Miao\, University of Connecticut\, “Learning and Control for Safety\, Efficiency\, and Resiliency of Embodied AI”
DESCRIPTION:This will be a hybrid event with in-person attendance in Levine 307 and virtual attendance on Zoom. \nABSTRACT\nWith rapid evolution of sensing\, communication\, and computation\, integrating learning and control presents significant Embodied AI opportunities. However\, current decision-making frameworks lack comprehensive understanding of the tridirectional relationship among communication\, learning and control\, posing challenges for multi-agent systems in complex environments. In the first part of the talk\, we focus on learning and control with communication capabilities. We design an uncertainty quantification method for collaborative perception in connected autonomous vehicles (CAVs). Our findings demonstrate that communication among multiple agents can enhance object detection accuracy and reduce uncertainty. Building upon this\, we develop a safe and scalable deep multi-agent reinforcement learning (MARL) framework that leverages shared information among agents to improve system safety and efficiency. We validate the benefits of communication in MARL\, particularly in the context of CAVs in challenging mixed traffic scenarios. We incentivize agents to communicate and coordinate with a novel reward reallocation scheme based on Shapley value for MARL. Additionally\, we present our theoretical analysis of robust MARL methods under state uncertainties\, such as uncertainty quantification in the perception modules or worst-case adversarial state perturbations. In the second part of the talk\, we briefly outline our research contributions on robust MARL and data-driven robust optimization for sustainable mobility. We also highlight our research results concerning CPS security. Through our findings\, we aim to advance Embodied AI and CPS for safety\, efficiency\, and resiliency in dynamic environments.
URL:https://seasevents.nmsdev7.com/event/spring-2024-grasp-sfi-fei-miao/
LOCATION:Levine 307\, 3330 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Seminar
ORGANIZER;CN="General Robotics%2C Automation%2C Sensing and Perception (GRASP) Lab":MAILTO:grasplab@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240214T153000
DTEND;TZID=America/New_York:20240214T163000
DTSTAMP:20260403T210333
CREATED:20240116T180348Z
LAST-MODIFIED:20240116T180348Z
UID:10007807-1707924600-1707928200@seasevents.nmsdev7.com
SUMMARY:CBE Seminar: "Systems Engineering for Addressing Critical Challenges in Viral Vector Manufacturing" (Francesco Destro\, MIT)
DESCRIPTION:Abstract\nThe demand for viral vectors is poised to soon exceed current production capacities\, driven by the surging number of clinical trials for gene and cell therapies. Unfortunately\, current manufacturing processes for viral vectors have high costs and low titers. This talk will demonstrate how process systems engineering tools can be leveraged for addressing the most critical challenges in the manufacturing process for recombinant adeno-associated virus (rAAV)\, the most widely used viral vector in commercial gene therapies. FDA recently approved the first rAAV-based gene therapies manufactured in the Sf9/baculovirus expression vector system (BEVS). Within the BEVS\, Sf9 cells produce rAAV as a result of infection with recombinant baculoviruses that carry the genetic blueprint for vector production. A mechanistic model is developed to identify the bottlenecks to full capsid formation in the intracellular pathway for rAAV production in Sf9 cells. The model indicates genetic modifications to the baculovirus vectors that can enhance the productivity of the platform. Further\, the optimal process conditions to establish continuous rAAV manufacturing in the BEVS are identified through a novel numerical method for solving systems of partial differential equations. Finally\, a powerful machine learning model is introduced for real-time prediction of rAAV titers based on single-cell biophysical signatures.
URL:https://seasevents.nmsdev7.com/event/cbe-seminar-systems-engineering-for-addressing-critical-challenges-in-viral-vector-manufacturing-francesco-destro-mit/
LOCATION:Wu and Chen Auditorium (Room 101)\, Levine Hall\, 3330 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Seminar
ORGANIZER;CN="Chemical and Biomolecular Engineering":MAILTO:cbemail@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240215T110000
DTEND;TZID=America/New_York:20240215T120000
DTSTAMP:20260403T210333
CREATED:20240201T134931Z
LAST-MODIFIED:20240201T134931Z
UID:10007838-1707994800-1707998400@seasevents.nmsdev7.com
SUMMARY:ESE Spring Seminar - "White-Box Computational Imaging: Measurements to Images to Insights"
DESCRIPTION:Computation and machine learning hold tremendous potential to improve the quality and capabilities of imaging methods used across science\, medicine\, engineering\, and art. Despite their impressive performance on benchmark datasets\, however\, deep learning methods are known to behave unpredictably on some real-world data\, which limits their trusted adoption in safety-critical domains. Accordingly\, in this talk I will describe white-box\, interpretable methods for photorealistic volumetric reconstruction that match or exceed the performance of black-box neural alternatives. I will also present recent theoretical results that guarantee correct and efficient reconstruction using our white-box approach in nonlinear computed tomography.
URL:https://seasevents.nmsdev7.com/event/ese-spring-seminar-white-box-computational-imaging-measurements-to-images-to-insights/
LOCATION:Raisler Lounge (Room 225)\, Towne Building\, 220 South 33rd Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Colloquium
ORGANIZER;CN="Electrical and Systems Engineering":MAILTO:eseevents@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240215T153000
DTEND;TZID=America/New_York:20240215T163000
DTSTAMP:20260403T210333
CREATED:20240108T171337Z
LAST-MODIFIED:20240108T171337Z
UID:10007793-1708011000-1708014600@seasevents.nmsdev7.com
SUMMARY:BE Seminar: "Where Do Therapeutic Antibodies Go?: A First-In-Human Journey" (Guolan Lu\, Stanford)
DESCRIPTION:Dr. Lu will introduce a fluorescence molecular imaging method to track therapeutic antibody delivery from cancer patients in vivo\, down to single cells\, through first-in-human clinical trials. She will present a new experimental and AI-powered analytical framework that integrates single-cell drug imaging with spatial omics to decipher drug-target-microenvironment in situ. This work establishes a foundational framework for studying drug pharmacology in the context of tissue biology in serious diseases including cancer\, autoimmunity\, and chronic inflammation.
URL:https://seasevents.nmsdev7.com/event/be-seminar-guolan-lu-stanford/
LOCATION:Raisler Lounge (Room 225)\, Towne Building\, 220 South 33rd Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Student
ORGANIZER;CN="Bioengineering":MAILTO:be@seas.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240215T153000
DTEND;TZID=America/New_York:20240215T163000
DTSTAMP:20260403T210333
CREATED:20240129T171413Z
LAST-MODIFIED:20240129T171413Z
UID:10007833-1708011000-1708014600@seasevents.nmsdev7.com
SUMMARY:CIS Seminar: "Accessible Foundation Models: Systems\, Algorithms\, and Science"
DESCRIPTION:The ever-increasing scale of foundation models\, such as ChatGPT and AlphaFold\, has revolutionized AI and science more generally. However\, increasing scale also steadily raises computational barriers\, blocking almost everyone from studying\, adapting\, or otherwise using these models for anything beyond static API queries. In this talk\, I will present research that significantly lowers these barriers for a wide range of use cases\, including inference algorithms that are used to make predictions after training\, finetuning approaches that adapt a trained model to new data\, and finally\, full training of foundation models from scratch.  For inference\, I will describe our LLM.int8() algorithm\, which showed how to enable high-precision 8-bit matrix multiplication that is both fast and memory efficient. LLM.int8() is based on the discovery and characterization of sparse outlier sub-networks that only emerge at large model scales but are crucial for effective Int8 quantization. For finetuning\, I will introduce the QLoRA algorithm\, which pushes such quantization much further to unlock finetuning of very large models on a single GPU by only updating a small set of the parameters while keeping most of the network in a new information-theoretically optimal 4-bit representation. For full training\, I will present SWARM parallelism\, which allows collaborative training of foundation models across continents on standard internet infrastructure while still being 80% as effective as the prohibitively expensive supercomputers that are currently used. Finally\, I will close by outlining my plans to make foundation models 100x more accessible\, which will be needed to maintain truly open AI-based scientific innovation as models continue to scale.
URL:https://seasevents.nmsdev7.com/event/cis-seminar-accessible-foundation-models-systems-algorithms-and-science/
LOCATION:Wu and Chen Auditorium (Room 101)\, Levine Hall\, 3330 Walnut Street\, Philadelphia\, PA\, 19104\, United States
ORGANIZER;CN="Computer and Information Science":MAILTO:cherylh@cis.upenn.edu
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240216T103000
DTEND;TZID=America/New_York:20240216T114500
DTSTAMP:20260403T210333
CREATED:20240208T161800Z
LAST-MODIFIED:20240208T161800Z
UID:10007851-1708079400-1708083900@seasevents.nmsdev7.com
SUMMARY:Spring 2024 GRASP on Robotics: Guillaume Sartoretti\, National University of Singapore\, “Towards Learned Cooperation at Scale in Robotic Multi-Agent Systems”
DESCRIPTION:This is a hybrid event with in-person attendance in Wu and Chen and virtual attendance on Zoom. \nABSTRACT\nWith the recent advances in sensing\, actuation\, computation\, and communication\, the deployment of large numbers of robots is becoming a promising avenue to enable or speed up complex tasks in areas such as manufacturing\, last-mile delivery\, search-and-rescue\, or autonomous inspection. My group strives to push the boundaries of multi-agent scalability by understanding and eliciting emergent coordination/cooperation in multi-robot systems as well as in articulated robots (where agents are individual joints). Our work mainly relies on distributed (multi-agent) reinforcement learning\, where we focus on endowing agents with novel information and mechanisms that can help them align their decentralized policies towards team-level cooperation. In this talk\, I will first summarize my early work in independent learning\, before discussing my group’s recent advances in convention\, communication\, and context-based learning. I will discuss these techniques within a wide variety of robotic applications\, such as multi-agent path finding\, autonomous exploration/search\, task allocation\, and legged locomotion. Finally\, I will also touch on our recent incursion into the next frontier for multi-robot systems: cooperation learning for heterogeneous multi-robot teams. Throughout this journey\, I will highlight the key challenges surrounding learning representations\, policy space exploration\, and scalability of the learned policies\, and outline some of the open avenues for research in this exciting area of robotics.
URL:https://seasevents.nmsdev7.com/event/spring-2024-grasp-on-robotics-guillaume-sartoretti-national-university-of-singapore-towards-learned-cooperation-at-scale-in-robotic-multi-agent-systems/
LOCATION:Wu and Chen Auditorium (Room 101)\, Levine Hall\, 3330 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Seminar
ORGANIZER;CN="General Robotics%2C Automation%2C Sensing and Perception (GRASP) Lab":MAILTO:grasplab@seas.upenn.edu
END:VEVENT
END:VCALENDAR