BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//events//Events//EN
CALSCALE:GREGORIAN
X-WR-CALNAME:Oct 14 - Advances in AI at SDSU
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-PUBLISHED-TTL:PT1H
BEGIN:VEVENT
UID:event-vp9h3zpn@ontown.app
DTSTAMP:20261008T220547Z
DTSTART:20261014T160000Z
SUMMARY:Oct 14 - Advances in AI at SDSU
LOCATION:San Francisco\, United States
DESCRIPTION:AI Professionals San Francisco Machine Learning & Agentic AI\nJ
 oin our virtual meetup to hear talks from AI researchers at San Diego Stat
 e University.\n\nDate\, Time Location\n\nOct 14\, 2026\n9:00 AM - 11:00 AM
  PST\nOnline. Register for the Zoom! (https://voxel51.com/events/advances-
 in-ai-at-sdsu-october-14-2026)\n\nAgent as Policy for Robotic Manipulation
 \n\nThis talk will introduces how a general-purpose agent can directly dri
 ve a physical robot throughout task execution without any task-specific or
  environment-specific training. We introduce Agent as Policy (AGP)\, which
  places task planning and execution under the agent’s control.\n\nAbout 
 the Speaker\n\nXiaobai Liu (https://www.linkedin.com/in/xiaobai-liu-335983
 36/) is a Professor of Computer Science at San Diego State University (SDS
 U)\, where he directs the Machine Vision and Perception Lab. Prior to join
 ing SDSU in 2015\, he conducted research and taught at UCLA.\n\nGrounding 
 Multimodal Open-World Learning for Physical AI\n\nPhysical AI systems such
  as robots\, unmanned vehicles\, and embodied agents must perceive and rea
 son about a world that is dynamic\, unstructured\, and rarely matches thei
 r training distribution. Yet most multimodal models remain brittle when co
 nfronted with novel objects\, unseen conditions\, and a messy unstructured
  environment.\n\nThis talk develops how grounding perception across modali
 ties and environments can make open-world learning more robust for physica
 lly situated systems. Drawing on our recent work\, I will highlight the co
 re challenges of multimodal open-world learning including out-of-distribut
 ion detection\, distribution shift generalization\, and cascaded semantic 
 grounding and point toward multimodal systems that stay reliable when depl
 oyed in the unpredictable open world.\n\nAbout the Speakers\n\nSalimeh Sek
 eh (https://www.linkedin.com/in/salimeh-sekeh-65473344/) is an Associate P
 rofessor of Computer Science at San Diego State University (SDSU)\, where 
 she directs the Sekeh Laboratory. Her recognition includes an NSF CAREER A
 ward and a Cisco research gift (both 2022)\, and the Maine College of Engi
 neering and Computing Early Career Research Award (2023)\, along with mult
 iple industry and federal research awards.\n\nMary Wisell  (https://www.li
 nkedin.com/in/mary-isabelle-wisell/)is a second-year PhD student in the Se
 keh Lab and leads the lab's work on environment-aware OOD detection and ca
 scaded failure analysis for multimodal intelligence with several publicati
 ons in top-tier Machine Learning and computer vision conferences.\n\nModel
 -Free\, Position-Free Signal Source Seeking Using Unmanned Maritime System
 s\n\nLong-range signal source detection in open-world environments present
 s a significant challenge\, mainly due to the detrimental effects of the e
 nvironment on signals propagation paths and presence of extraneous signal 
 sources. While distributed static sensing systems are often employed\, ach
 ieving scalability and comprehensive coverage across expansive areas is co
 st-prohibitive.\n\nOne affordable solution involves using low-cost autonom
 ous unmanned vehicles (AUVs) that can leverage their mobility and actively
  explore the environment using extremum seeking control (ESC) algorithms. 
 This talk presents novel ESC approaches to steer AUVs to sources of intere
 st in an a priori unknown\, highly non-convex map.\n\nAbout the Speaker\n\
 nZahra Nili Ahmadabadi (https://www.linkedin.com/in/zahra-nili-ahmadabadi-
 phd-29113171) is Associate Professor with the Mechanical Engineering Depar
 tment at San Diego State University (SDSU). She is a recipient of the ASME
  rising star award and ARO Early career award.
URL:https://ontown.app/e/vp9h3zpn-oct-14-advances-in-ai-at-sdsu/
END:VEVENT
END:VCALENDAR