BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Events - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://events.ucsc.edu
X-WR-CALDESC:Events for Events
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20240310T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20241103T090000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20250309T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20251102T090000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20260308T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20261101T090000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20250818T103000
DTEND;TZID=America/Los_Angeles:20250818T103000
DTSTAMP:20260426T175900
CREATED:20250814T070000Z
LAST-MODIFIED:20250925T231431Z
UID:10000103-1755513000-1755513000@events.ucsc.edu
SUMMARY:Vats\, V. (CSE) - Learning to Remember: Multi-Agent Self-Refinement toward Persistent Machine Perception
DESCRIPTION:Modern machine perception is powerful yet brittle: failing in response to subtle data adversaries and lacking mechanisms to learn from their errors. We address this challenge by progressing from diagnosing such failures to developing a framework for persistent learning. We first investigate the sources of this fragility\, demonstrating how both naturally occurring adversarial artifacts\, like specular highlights\, and conditions of data scarcity fundamentally limit model robustness. We then replace a passive reliance on quality data curation with active\, multi-agent refinement: a Worker-Supervisor loop that iteratively critiques and corrects outputs to meet complex\, rule-rich guidelines at inference time. While this system achieves dynamic error correction\, it rarely remembers what was learned. We thus plan to tackle this problem of non-remembrance by proposing an experience memory that records validated fixes as reusable insights\, retrieves them when similar contexts recur\, and\, where available\, grounds them across viewpoints and time. Together\, these components turn momentary fixes into long-term skills\, paving the way for more capable and reliable perception in fields like augmented reality and robotics. \nEvent Host: Vanshika Vats\, PhD Student\, Computer Science & Engineering \nAdvisor: James Davis
URL:https://events.ucsc.edu/event/vats-v-cse-learning-to-remember-multi-agent-self-refinement-toward-persistent-machine-perception/
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20250818T180000
DTEND;TZID=America/Los_Angeles:20250818T180000
DTSTAMP:20260426T175900
CREATED:20250807T070000Z
LAST-MODIFIED:20250925T231429Z
UID:10000096-1755540000-1755540000@events.ucsc.edu
SUMMARY:Model Context Protocol: Why It Matters
DESCRIPTION:The Impact of Model Context Protocol \nJoin us for an engaging exploration of the Model Context Protocol—a groundbreaking framework designed to improve communication and context-sharing across AI agents. As AI systems become more modular and collaborative\, MCP offers a powerful solution for maintaining continuity across tasks\, tools\, and models. This free\, online event is sponsored by the AI Program at UCSC Silicon Valley Extension. \n\nTopics \n\nThe origins and motivations behind MCP\nHow MCP structures and preserves context\nThe growing importance of MCP in the development of scalable\, interoperable AI agent systems\nReal-world use cases\nCurrent limitations of MCP\nHow MCP is shaping the future of AI infrastructure\nHow to advance your knowledge and skills in this frontier technology.\n\n\nSpeaker \nPraveen Krishna\, AI Program chair and platform architect for Audio AI/ML Solutions\, Performance & Power\, Intel\, teaches AI Essentials\, Deep Learning and Artificial Intelligence\, Open Computer AI Agent by Hugging Face\, Practical uses of DeepSeek/Llama\, Computer Vision and Image Processing\, and Capstone Building Integrated AI Applications. \n\nInterested in a deeper dive into this topic? \nAI Technology Workshop Series: Model Context Protocol (Aug. 29)\nA one-day workshop held in person at the Silicon Valley Campus or online.
URL:https://events.ucsc.edu/event/model-context-protocol-what-you-need-to-know-why-it-matters/
CATEGORIES:Lectures & Presentations,Training
END:VEVENT
END:VCALENDAR