BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Events - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Events
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: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
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20270314T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20271107T090000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20260526T070000
DTEND;TZID=America/Los_Angeles:20260526T090000
DTSTAMP:20260601T095850
CREATED:20260515T203009Z
LAST-MODIFIED:20260515T203009Z
UID:10014648-1779778800-1779786000@events.ucsc.edu
SUMMARY:Chou\, Y. (CM) - Exploring Future AI-Mediated Health Creator–Audience Interactions on Social Media: Transparency\, Care\, and Accountability
DESCRIPTION:Health and wellness content creators play an important role in shaping how people receive and engage with health information on social media. Beyond delivering information\, they also convey care\, build trust\, and sustain relationships with audiences. As generative AI (GenAI) becomes increasingly integrated into creator work\, existing research has examined AI disclosure\, AI-mediated communication\, and health communication more broadly\, but less is known about how AI should be integrated into health creator–audience interactions\, where informational support\, emotional care\, accountability\, and relational meaning are often intertwined. My dissertation examines AI-mediated health creator–audience interaction through four connected studies. Study 1 used mock-up interfaces and semi-structured interviews with 16 Instagram users who interact with health and wellness creators to examine audience perceptions of GenAI use disclosure. Study 2 conducts co-design sessions with social media health creators to explore how creators might communicate human labor and personal contribution in a future social media environment where AI-generated content is widespread. Study 3 extends the focus to audience-invoked AI in public comment sections by scraping and analyzing comment data from platfrom X\, examining how audiences invoke AI agents through @-mentions in response to health creator posts\, and how these public AI invocations may shape information credibility\, accountability\, community discussion\, and social dynamics. Finally\, Study 4 will synthesize insights from the first three studies and translate them into interactive prototypes. By examining how audiences and health creators interact with these prototypes\, this study will explore future forms of AI-mediated health creator–audience interaction and broader community engagement on social media. \n  \nEvent Host: Yuling Ruby Chou\, Ph.D. Student\, Computational Media \nAdvisor: Christina Chung \nZoom: https://ucsc.zoom.us/j/94127645445?pwd=dmlMkwbknDZE9pbklAC9jhwDTZPbVL.1 \nPasscode: 190739
URL:https://events.ucsc.edu/event/chou-y-cm-exploring-future-ai-mediated-health-creator-audience-interactions-on-social-media-transparency-care-and-accountability/
LOCATION:
CATEGORIES:Ph.D. Presentations
ATTACH;FMTTYPE=image/jpeg:https://events.ucsc.edu/wp-content/uploads/2026/04/ph.d.-presentation-graphic-option-1.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20260526T093000
DTEND;TZID=America/Los_Angeles:20260526T113000
DTSTAMP:20260601T095850
CREATED:20260519T162948Z
LAST-MODIFIED:20260519T162948Z
UID:10014713-1779787800-1779795000@events.ucsc.edu
SUMMARY:Weber\, Z. (ECE) - Sustainable Bioinspired Polymer–Mineral Composites for Adaptable Repair in Conservation Applications
DESCRIPTION:Every year\, tens of thousands of tons of plaster-based materials are used in restoration and conservation applications\, many of which are derived from non-renewable sources and discarded at the end of their service life. Here\, we introduce a biodegradable\, bio-derived composite based on chitosan and calcium carbonate that is composed of simple\, widely available constituents and designed for adaptable repair applications. By varying polymer molecular weight\, concentration\, and mineral content\, the composite can be formulated to span injectable\, paste-like\, and putty-like behaviors\, enabling accommodation of diverse structural filling and stabilization needs. We examine relationships between composition\, flow behavior\, and mechanical performance through rheological characterization of the wet composite and measurements of bulk density\, porosity\, and compressive strength in the hardened state. Rather than targeting a single optimized formulation\, this work demonstrates a tunable material platform in which relationships between composition\, flow behavior and mechanical performance guide selection of material behavior based on application requirements. Future applications of this approach include sustainable repair and conservation materials for exhibits\, architectural restoration\, and other contexts where adaptable handling\, mechanical integrity\, and biodegradability are desired. \nEvent Host: Zoë Weber\, Ph.D. Student\, Electrical & Computer Engineering  \nAdvisor: Marco Rolandi \nZoom: https://ucsc.zoom.us/j/96509847894?pwd=Q5w4oFaXQQD4rbEehZHxuevh12Piar.1 \nPasscode: 324003
URL:https://events.ucsc.edu/event/weber-z-ece-sustainable-bioinspired-polymer-mineral-composites-for-adaptable-repair-in-conservation-applications/
LOCATION:Jack Baskin Engineering\, Baskin Engineering 1156 High Street\, Santa Cruz\, CA\, 95064
CATEGORIES:Ph.D. Presentations
ATTACH;FMTTYPE=image/png:https://events.ucsc.edu/wp-content/uploads/2026/04/ph.d.-presentation-graphic-option-3.png
GEO:37.000369;-122.0632371
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=Jack Baskin Engineering Baskin Engineering 1156 High Street Santa Cruz CA 95064;X-APPLE-RADIUS=500;X-TITLE=Baskin Engineering 1156 High Street:geo:-122.0632371,37.000369
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20260526T100000
DTEND;TZID=America/Los_Angeles:20260526T110000
DTSTAMP:20260601T095850
CREATED:20260518T185313Z
LAST-MODIFIED:20260518T190031Z
UID:10014653-1779789600-1779793200@events.ucsc.edu
SUMMARY:Harsh\, B. (CSE) - SUPERSCALAR\, MULTIPLE TAKEN BRANCH PREDICTOR
DESCRIPTION:This work addresses improvements in branch prediction mechanism to support high perfor-\nmance processors. The state of the art aims to balance the prediction latency and prediction\naccuracy using multi level correcting predictors [27]. Prior published work focusses on scalar\ndesigns and prediction accuracy improvement for hard to predict branches employing tailor\nmade\, non generic and non transferrable solutions [8]. Recent work also proposes ahead pre-\ndiction [42–44] to solve the problem of low accuracy of L0 predictor. \nThis work proposes efficent\, generic and transferrable solutions to reduce mispredic-\ntions and to use the fetch bandwidth more efficiently. This includes a biased overriding multi-\nlevel hierarchy with three predictor levels (L0\, L1\, L2). L0 uses a High-Confidence-Only Taken\n(HOTP) predictor that only predicts high-confidence taken control-flow instructions. This work\nfurther uses L1-L2 biased training to decrease mispredictions by L2 while it trains on branches\non which L1 has reached high confidence. This work proposes a superscalar predictor built\nusing the state of the art scalar predictor. Superscalar predictor is implemented by sizing a su-\nperscalar TAGE variant (BATAGE) using Optuna-based search. with varying table sizes and\naspect ratios. The work further proposes a branch predictor frontend design (nTakenBP) to de-\nliver multiple taken branch predictions per cycle. Unlike prior work\, nTakenBP achieves this by\nextending the existing BTB and TAGE tag-comparison logic rather than deepening lookahead. \n  \nEvent Host: Bhawandeep Singh Harsh\, Ph.D. Candidate\, Computer Science & Engineering \nAdvisor: Jose Renau \nZoom: https://ucsc.zoom.us/j/4166778865?pwd=cS9NcnVjRjArYlRRcDcrY3d5N0ZKQT09
URL:https://events.ucsc.edu/event/harsh-b-cse-superscalar-multiple-taken-branch-predictor/
LOCATION:Engineering 2\, Engineering 2 1156 High Street\, Santa Cruz\, CA\, 95064
CATEGORIES:Ph.D. Presentations
ATTACH;FMTTYPE=image/jpeg:https://events.ucsc.edu/wp-content/uploads/2026/04/ph.d.-presentation-graphic-option-1.jpg
GEO:37.0009723;-122.0632371
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=Engineering 2 Engineering 2 1156 High Street Santa Cruz CA 95064;X-APPLE-RADIUS=500;X-TITLE=Engineering 2 1156 High Street:geo:-122.0632371,37.0009723
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20260526T103000
DTEND;TZID=America/Los_Angeles:20260526T123000
DTSTAMP:20260601T095850
CREATED:20260512T164007Z
LAST-MODIFIED:20260512T164007Z
UID:10014630-1779791400-1779798600@events.ucsc.edu
SUMMARY:Castro\, S. (CSE) - Agentic AI for Security: Adversarial Foundations for Autonomous Cyber Operations
DESCRIPTION:Autonomous Cyber Operations (ACO) agents promise effective security automation with minimal human intervention\, yet their deployment raises three interconnected challenges: agents must be realistic (reproducing diverse attacker sophistication)\, secure (preventing autonomy from becoming an attack surface)\, and feasible (safely replicating human behavior at full autonomy). \nWe argue that these three properties are requirements for ACO agents. Existing approaches do not address them together and lack diverse adversarial coverage\, formal threat models for attacks against the agents themselves\, and systematic evaluation of multi-agent topologies. \nWe advance all three ACO properties: (1) For realism\, we establish adversarial foundations by discovering Windows OS vulnerabilities and releasing two exploits reliable across XP through 11. (2) For security\, we formalize ACO meta-attacks and meta-defenses\, propose the first invariant-based Meta-IDS detecting both sensor and actuator meta-attacks\, and introduce the first hybrid LLM–RL ACO integration for defense with a novel inter-agent communication protocol. (3) For feasibility\, we present MaLO\, the first dynamic-topology multi-agent ACO system\, achieving a 78.6\% success rate across a new 42-task security benchmark and solving operations up to 40× faster than human experts. We further propose the Security Operation Complexity Index (SOCX) classification and the T×V×O taxonomy as the first objective-driven evaluation methodology for coding-agent attacks. \nTogether\, these contributions demonstrate that ACO agents can match real-world adversarial sophistication\, resist meta-attacks\, and outperform human operators on complex security tasks. Open challenges remain in adaptive adversaries\, LLM–RL co-training\, dynamic topology selection\, and deployment beyond simulated environments. \n  \nEvent Host:  Sebastián R. Castro\, PhD Candidate\, Computer Science & Engineering \nAdvisor: Alvaro A. Cárdenas \nZoom: https://ucsc.zoom.us/j/2267557290?pwd=S0dNTTV3emZGUzlqV3dLbTg3a0NFUT09&omn=92791061627 \nPasscode: G20c06
URL:https://events.ucsc.edu/event/castro-s-cse-agentic-ai-for-security-adversarial-foundations-for-autonomous-cyber-operations/
LOCATION:Engineering 2\, Engineering 2 1156 High Street\, Santa Cruz\, CA\, 95064
CATEGORIES:Ph.D. Presentations
ATTACH;FMTTYPE=image/jpeg:https://events.ucsc.edu/wp-content/uploads/2026/04/ph.d.-presentation-graphic-option2.jpg
GEO:37.0009723;-122.0632371
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=Engineering 2 Engineering 2 1156 High Street Santa Cruz CA 95064;X-APPLE-RADIUS=500;X-TITLE=Engineering 2 1156 High Street:geo:-122.0632371,37.0009723
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20260526T110000
DTEND;TZID=America/Los_Angeles:20260526T130000
DTSTAMP:20260601T095850
CREATED:20260515T173857Z
LAST-MODIFIED:20260515T174024Z
UID:10014644-1779793200-1779800400@events.ucsc.edu
SUMMARY:Liu\, P. (CM) - Reimagining Workplace Concern Reporting: From Emotional Harm to Co-Designed Futures
DESCRIPTION:Workplace concern reporting infrastructure\, including human resources (HR) portals\, grievance procedures\, and whistleblower hotlines\, is the formal channel through which employees in most organizations raise concerns about harassment\, discrimination\, and retaliation. Yet existing research consistently finds that these systems fail the employees they are meant to protect: reports stall\, concerns get filtered\, retaliation occurs\, and marginalized employees face disproportionate risk. This dissertation examines workplace concern reporting as relational\, emotional\, and processual rather than procedural and discrete\, and pursues this account through three studies. Study 1\, drawing on semi-structured interviews with 12 HR professionals and 10 employees in California\, develops the concept of emotional re-victimization to describe how reporting infrastructure produces additional harm at multiple stages of the reporting process. Study 2 returns to the same corpus with a different theoretical lens to develop the concept of buffer spaces: intermediary practices through which employees navigate the gap between informal sense-making and formal escalation. Study 3 will move the dissertation from diagnostic to practical work in two phases. Phase 1 uses speculative co-design with employees and HR professionals to surface what each group would build if they could redesign concern reporting infrastructure together. Phase 2 translates design directions from Phase 1 into prototypes\, iterated with participants across both groups to develop design artifacts that have been shaped by the people who would use them. The dissertation as a whole moves from documenting harm\, through identifying workarounds\, to imagining redesign\, contributing to HCI/CSCW scholarship on workplace technology\, labor studies on employee voice and accountability\, and methodological work on cross-stakeholder speculative design. \nEvent Host: Peiyao Liu\, Ph.D. Student\, Computational Media \nAdvisor: Norman Makoto Su \nZoom: https://ucsc.zoom.us/j/99335305923?pwd=xP6QlNwzobLNQqnCxG3muuZD36C4rn.1 \nPasscode: 946352 \n 
URL:https://events.ucsc.edu/event/liu-p-cm-reimagining-workplace-concern-reporting-from-emotional-harm-to-co-designed-futures/
LOCATION:
CATEGORIES:Ph.D. Presentations
ATTACH;FMTTYPE=image/png:https://events.ucsc.edu/wp-content/uploads/2026/04/ph.d.-presentation-graphic-option-3.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20260527T090000
DTEND;TZID=America/Los_Angeles:20260527T110000
DTSTAMP:20260601T095850
CREATED:20260515T163555Z
LAST-MODIFIED:20260515T163555Z
UID:10014642-1779872400-1779879600@events.ucsc.edu
SUMMARY:Baskaran\, D. (CM) - More than Just Fun: Exploring Meaningful Play\, Communities of Play\, and Relatedness of Play
DESCRIPTION:Play is often seen as a form of entertainment\, leisure\, or childhood development. However\, it also acts as a meaningful experience that shapes how people connect with others and interact with the world around them throughout their lives. Prior work on meaningful play and communities of play has mainly focused on individual experiences and participation\, giving less attention to how meaning is socially co-constructed through playful interactions and to how these experiences contribute to relatedness\, or the human need to feel connected to and belong with others\, across physical\, digital\, and hybrid environments. \nUsing qualitative methods\, this dissertation proposal explores how meaningful play is collectively constructed within communities of play and how it shapes relatedness among members. This work positions meaningful play as a socially and technologically embedded relational phenomenon rather than solely an individual experience. Across case studies of PlayStation trophy hunting\, Pokémon Nuzlocke\, LEGO\, and theme park communities of play\, this research explores how meaningful play within these communities contributes to relatedness among members. Ultimately\, this dissertation proposal aims to advance a more holistic understanding of play as a process through which people build shared meaning\, connection\, and belonging in increasingly digital and hybrid social spaces. \n  \nEvent Host: Derusha Baskaran\, Ph.D. Student\, Computational Media \nAdvisor: Kathryn Ringland \n  \nZoom: https://ucsc.zoom.us/j/96290198842?pwd=xtoEw1aIa2fciTbhr6eB9s3PqbWGdF.1 \nPasscode: 404425
URL:https://events.ucsc.edu/event/baskaran-d-cm-more-than-just-fun-exploring-meaningful-play-communities-of-play-and-relatedness-of-play/
LOCATION:
CATEGORIES:Ph.D. Presentations
ATTACH;FMTTYPE=image/jpeg:https://events.ucsc.edu/wp-content/uploads/2026/04/ph.d.-presentation-graphic-option-1.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20260527T090000
DTEND;TZID=America/Los_Angeles:20260527T110000
DTSTAMP:20260601T095850
CREATED:20260518T163634Z
LAST-MODIFIED:20260518T163634Z
UID:10014652-1779872400-1779879600@events.ucsc.edu
SUMMARY:Tu\, H. (CSE) - From Evaluation to Adaptation: Building Reliable Multimodal Intelligence
DESCRIPTION:Multimodal large language models (MLLMs) are rapidly becoming general-purpose AI systems\, yet their capabilities are advancing faster than our ability to evaluate\, improve\, and validate their reliability in realistic use. Standard benchmarks mainly measure in-distribution final-answer accuracy\, leaving critical gaps in safety\, robustness\, fine-grained reasoning evaluation\, and reliability in real-world agentic settings. My research proposes an evaluation-to-adaptation framework for building reliable multimodal intelligence: developing rigorous evaluations that expose failures beyond conventional benchmarks\, learning feedback models that guide inference-time reasoning\, and studying how multimodal systems can adapt through experience. We instantiate this agenda through two completed works and two proposed directions. Unicorn evaluates safety and robustness under out-of-distribution and adversarial conditions\, revealing substantial vulnerabilities across 22 vision-language models. ViLBench studies vision-language process reward modeling as both an evaluation challenge and a mechanism for inference-time improvement\, showing that process-guided reasoning selection can improve reliability. Building on these foundations\, we further study test-time experience accumulation and explore reliable multimodal agents for GUI and computer-use tasks. Together\, my research aims to move beyond capability-driven progress alone\, toward multimodal AI systems whose reliability can be evaluated\, improved\, and tested in realistic deployment settings. \nEvent Host: Haoqin Tu\, Ph.D. Student\, Computer Science & Engineering \nAdvisor: Cihang Xie \nZoom: 964 1355 0550 \nPasscode: zWxU8A
URL:https://events.ucsc.edu/event/tu-h-cse-from-evaluation-to-adaptation-building-reliable-multimodal-intelligence/
LOCATION:
CATEGORIES:Ph.D. Presentations
ATTACH;FMTTYPE=image/jpeg:https://events.ucsc.edu/wp-content/uploads/2026/04/ph.d.-presentation-graphic-option2.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20260527T120000
DTEND;TZID=America/Los_Angeles:20260527T140000
DTSTAMP:20260601T095850
CREATED:20260518T162624Z
LAST-MODIFIED:20260518T162624Z
UID:10014651-1779883200-1779890400@events.ucsc.edu
SUMMARY:Zheng\, Y. (CSE) - Extending eBPF Beyond Kernel Extensions: Verified Interfaces for Runtime System Extensibility
DESCRIPTION:Modern system software increasingly needs runtime extensibility: userspace applications need safe ways to expose domain-specific extension points\, GPU resource management needs workload-specific memory and scheduling policies\, and kernel eBPF JIT compilers need different runtime optimizations as workloads and hardware vary. However\, built-in policies are safe but difficult to specialize across rapidly changing workloads and hardware environments\, limiting efficiency\, while code modifications are flexible but difficult to deploy safely. This dissertation argues that verified eBPF interfaces can turn eBPF from a kernel-extension mechanism into a general substrate for safe runtime extensibility. In this model\, trusted mechanisms expose narrow\, constrained programmable hooks; extensions declare their requirements; verifier-enforced checks preserve safety; and execution remains low-overhead. \nI develop this thesis through three systems spanning userspace applications\, heterogeneous GPU subsystems\, and the kernel eBPF compiler itself. EIM\, implemented in bpftime\, applies verified eBPF interfaces to userspace applications\, allowing application behavior to be extended through explicit constraints and efficient userspace eBPF execution. gpu_ext extends the same idea to heterogeneous systems by exposing programmable resource management hooks for GPU memory and scheduling policy across driver and device. BpfReJIT with kinsn makes the eBPF JIT compiler itself extensible: it enables runtime-guided optimization through dynamic recompilation and extends eBPF bytecode to express diverse hardware capabilities. Together\, these systems show how verified eBPF interfaces can support safe programmability\, separation of policy and mechanisms\, and runtime specialization across applications\, GPU subsystems\, and the kernel JIT infrastructure. \nEvent Host: Yusheng Zheng\, Ph.D. Student\, Computer Science & Engineering \nAdvisor: Andi Quinn \nZoom: 504 350 0245 \nPasscode: 521336
URL:https://events.ucsc.edu/event/zheng-y-cse-extending-ebpf-beyond-kernel-extensions-verified-interfaces-for-runtime-system-extensibility/
LOCATION:
CATEGORIES:Ph.D. Presentations
ATTACH;FMTTYPE=image/png:https://events.ucsc.edu/wp-content/uploads/2026/04/ph.d.-presentation-graphic-option-3.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20260528T110000
DTEND;TZID=America/Los_Angeles:20260528T120000
DTSTAMP:20260601T095850
CREATED:20260522T165248Z
LAST-MODIFIED:20260522T165248Z
UID:10014863-1779966000-1779969600@events.ucsc.edu
SUMMARY:Oh\, S. (CSE) - Efficient Instruction Supply for Datacenter Processors
DESCRIPTION:Modern datacenter CPUs lose 25–66% of execution cycles to instruction-delivery stalls. This bottleneck persists\, despite the recent trend towards accelerators and GPUs\, as there is continuing demand by applications that only execute on CPUs. Two workload classes dominate today’s datacenter execution cycles: hyperscale server software (databases\, build systems\, and content stores)\, whose large instruction footprints create severe frontend pathologies; and agentic AI systems\, in which large-language-model agents plan\, dispatch tools\, and maintain growing conversational contexts\, causing CPUs to account for up to 88% of end-to-end agent latency. Reflecting this shift\, major CPU vendors have publicly repositioned the CPU as the orchestration layer of the AI stack and have begun shipping processors optimized for agent-centric workloads. \nThis dissertation argues that instruction delivery is the dominant CPU bottleneck across both workload classes and that the recent trend towards agentic AI further exacerbates this challenge. In hyperscale server binaries\, the primary pathologies are wrong-path prefetch pollution and post-recovery instruction-delivery gaps across large\, irregular call graphs. In agentic AI systems\, the bottleneck shifts to an orchestration substrate composed of protocol stacks\, dynamic-runtime dispatch\, and agent-specific extensions that is even more frontend-bound than traditional warehouse-scale workloads. \nTo address these bottlenecks\, this dissertation presents three technical contributions\, together with a companion infrastructure contribution. First\, Utility-Driven Prefetching (UDP) extends fetch-directed instruction prefetching (FDIP) with a learned per-prefetch utility model that admits candidates based on their historical contribution to demand-fetch hits\, including those reached along wrong-path execution. Second\, Junction-based Unified Miss-point Prefetching (JUMP) addresses the post-recovery instruction-delivery gap that UDP and prior FDIP optimizations cannot reach by launching a lightweight secondary FDIP thread at a learned miss point following each branch-prediction failure. Across a suite of datacenter workloads\, UDP improves IPC by 3.6% on average (up to 16.1%) over a state-of-the-art FDIP baseline\, while JUMP improves IPC by 2.0% on average (up to 14.9%). Combined\, the two mechanisms substantially close the gap between FDIP and a perfect L1 instruction cache at a storage cost of only a few tens of kilobytes.\nThird\, this dissertation introduces the Agentic Tax\, the first CPU characterization study of agentic AI workloads across three runtime families. The study is packaged as a deterministic-replay benchmark infrastructure that enables repeatable\, cycle-level evaluation under controlled conditions. The characterization shows that the orchestration substrate of agentic AI workloads is significantly more frontend-bound than the hyperscale datacenter workloads examined in prior work\, and that it introduces new dominant function families with no analog in traditional warehouse-scale systems. These findings motivate two architectural directions proposed as future work: extending UDP and JUMP to optimize the orchestration substrate itself\, and designing heterogeneous CPU cores that allocate frontend resources according to the execution phase. \nEvent Host: Surim Oh\, Ph.D. Candidate\, Computer Science & Engineering  \nAdvisor: Heiner Litz \nZoom: https://ucsc.zoom.us/j/94753352649?pwd=7vQxlnSJkUb0KfG3t6STo639LhRv7j.1 \nPasscode: 205162
URL:https://events.ucsc.edu/event/oh-s-cse-efficient-instruction-supply-for-datacenter-processors/
LOCATION:Engineering 2\, Engineering 2 1156 High Street\, Santa Cruz\, CA\, 95064
CATEGORIES:Ph.D. Presentations
ATTACH;FMTTYPE=image/jpeg:https://events.ucsc.edu/wp-content/uploads/2026/04/ph.d.-presentation-graphic-option-1.jpg
GEO:37.0009723;-122.0632371
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=Engineering 2 Engineering 2 1156 High Street Santa Cruz CA 95064;X-APPLE-RADIUS=500;X-TITLE=Engineering 2 1156 High Street:geo:-122.0632371,37.0009723
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20260528T120000
DTEND;TZID=America/Los_Angeles:20260528T140000
DTSTAMP:20260601T095850
CREATED:20260526T163353Z
LAST-MODIFIED:20260526T163353Z
UID:10014868-1779969600-1779976800@events.ucsc.edu
SUMMARY:Ortiz Barbosa\, D. (CSE) - HARDENING AUTONOMOUS CYBER-PHYSICAL SYSTEMS AGAINST ADVERSARIAL CONDITIONS
DESCRIPTION:Autonomous systems\, such as Autonomous Vehicles (AVs) and drones\, are increasingly\ndeployed across a wider array of contexts for both civilian and military use. As these\nsystems become more common\, they may be targeted by malicious actors seeking to\nexploit and abuse them\, compromising safety-critical operations. Among the ways to\nprotect these systems simulation based testing frameworks have been developed. How-\never\, existing testing frameworks primarily focus on identifying logical flaws or system\nvulnerabilities\, often emphasizing static scenarios and paying less attention to an adap-\ntive intelligent adversary.\nTo help reduce this gap\, this dissertation develops and applies adaptive\, adversary-\naware methodologies to discover\, formalize\, and mitigate security vulnerabilities in au-\ntonomous systems spanning vehicle platooning\, drone swarms\, and vision-based drone\nrecovery. We first apply NLP techniques to discover and formalize driving rules across\nNorth American and Australian jurisdictions\, identifying possible restriction that an\nadversary can exploit. Likewise\, these rules can be used to test the adaptability of AVs\nto new contexts and to establish a formal basis for context-aware AV testing. Next\,\nwe apply optimization-based adversarial search to both ACC-controlled vehicle pla-\ntoons and obstacle-avoiding drone swarms. We uncover maneuvers that an adversary\ncan use against the system that range from crash-inducing patterns against platooning\ncontrollers to herding strategies that divert swarms from their objectives. Finally\, to\naddress the gap regarding the possible solutions to an adversarial attack we explore how\na drone can recover from it by using LVLMs to understand its context and select a safe\nlanding surface. \nEvent Host: Diego Ortiz Barbosa\, Ph.D. Candidate\, Computer Science & Engineering  \nAdvisor: Alvaro A Cardenas
URL:https://events.ucsc.edu/event/ortiz-barbosa-d-cse-hardening-autonomous-cyber-physical-systems-against-adversarial-conditions/
LOCATION:Engineering 2\, Engineering 2 1156 High Street\, Santa Cruz\, CA\, 95064
CATEGORIES:Ph.D. Presentations
ATTACH;FMTTYPE=image/jpeg:https://events.ucsc.edu/wp-content/uploads/2026/04/ph.d.-presentation-graphic-option2.jpg
GEO:37.0009723;-122.0632371
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=Engineering 2 Engineering 2 1156 High Street Santa Cruz CA 95064;X-APPLE-RADIUS=500;X-TITLE=Engineering 2 1156 High Street:geo:-122.0632371,37.0009723
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20260528T130000
DTEND;TZID=America/Los_Angeles:20260528T150000
DTSTAMP:20260601T095850
CREATED:20260514T160341Z
LAST-MODIFIED:20260514T160625Z
UID:10014635-1779973200-1779980400@events.ucsc.edu
SUMMARY:Yang\, D. (CSE) - Inner Monologue: a Pathway to Human-Like Reasoning for Complex Tasks
DESCRIPTION:A central goal on the path toward general AI is to build systems capable of deliberative reasoning before action. Such systems should inspect what they know\, identify what they need\, seek or construct useful information\, and revise their reasoning through intermediate cognitive states. This dissertation studies this goal through the lens of Inner Monologue (IM)\, a mechanism that enables AI systems to coordinate internal components\, acquire external information\, and reason through structured intermediate states. \nI will first introduce IM as a mechanism for internal coordination in static information systems\, where multiple models collaborate within one AI system to solve reasoning tasks. I will then extend IM to dynamic information systems\, where AI system is learned to retrieve external information. Finally\, I will present how IM can move beyond verbal reasoning toward multimodal thinking\, where generated visual states represent the system’s current understanding and support iterative refinement. \nTogether\, this dissertation demonstrates the success and potential of human-inspired Inner Monologue mechanisms for improving complex multi-step reasoning in AI systems. \nEvent Host: Diji Yang\, Ph.D. Candidate\, Computer Science & Engineering \nAdvisor: Yi Zhang \nZoom: https://ucsc.zoom.us/j/99915235963?pwd=7Jqo6fc83LWobTEYRZCUzbrWbeov3Y.1 \nPasscode: 7Jqo6fc83LWobTEYRZCUzbrWbeov3Y.1
URL:https://events.ucsc.edu/event/yang-d-cse-inner-monologue-a-pathway-to-human-like-reasoning-for-complex-tasks/
LOCATION:Silicon Valley Campus\, 3175 Bowers Avenue\, Santa Clara\, CA\, 95054\, United States
CATEGORIES:Ph.D. Presentations
ATTACH;FMTTYPE=image/png:https://events.ucsc.edu/wp-content/uploads/2026/04/ph.d.-presentation-graphic-option-3.png
GEO:37.3796975;-121.9765484
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=Silicon Valley Campus 3175 Bowers Avenue Santa Clara CA 95054 United States;X-APPLE-RADIUS=500;X-TITLE=3175 Bowers Avenue:geo:-121.9765484,37.3796975
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20260529T110000
DTEND;TZID=America/Los_Angeles:20260529T123000
DTSTAMP:20260601T095850
CREATED:20260515T164420Z
LAST-MODIFIED:20260515T164420Z
UID:10014643-1780052400-1780057800@events.ucsc.edu
SUMMARY:Zhou\, K. (CSE) - Toward Safer Frontier AI: From Evaluation and Red-Teaming to Alignment and Oversight
DESCRIPTION:This dissertation investigates how to make modern AI systems safer as they grow more capable. It addresses two central sources of risk: malicious misuse\, in which adversarial users coerce models into harmful behavior\, and internal misalignment\, in which models themselves pursue goals that diverge from human intent through deception\, sandbagging\, or other covert behaviors. The dissertation identifies novel safety risks in frontier multimodal large language models and AI agents\, introduces a black-box red-teaming framework for AI agents\, proposes new safety alignment algorithms\, and builds the first probe-based misalignment monitoring system\, developing practical approaches for evaluating\, red-teaming\, aligning\, and overseeing frontier language models and agents. The central conclusion is that responsible AI cannot rest on any single guardrail: capability-scaled evaluation\, active red-teaming\, training-time alignment\, and scalable monitoring together form a coordinated stack for frontier AI safety. \nEvent Host: Kaiwen Zhou\, Ph.D. Candidate\, Computer Science & Engineering  \nAdvisor: Xin Wang \nZoom: https://ucsc.zoom.us/j/94196702062?pwd=b9LJMfL232ixG2THMab8XuJ32a4FVD.1 \nPasscode:  584794
URL:https://events.ucsc.edu/event/zhou-k-cse-toward-safer-frontier-ai-from-evaluation-and-red-teaming-to-alignment-and-oversight/
LOCATION:
CATEGORIES:Ph.D. Presentations
ATTACH;FMTTYPE=image/jpeg:https://events.ucsc.edu/wp-content/uploads/2026/04/ph.d.-presentation-graphic-option2.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20260529T113000
DTEND;TZID=America/Los_Angeles:20260529T133000
DTSTAMP:20260601T095850
CREATED:20260522T161630Z
LAST-MODIFIED:20260522T161630Z
UID:10014862-1780054200-1780061400@events.ucsc.edu
SUMMARY:Qureshi\, A. (ECE) - ISoC: A Universal Impedance Spectroscopy Instrument-on-Chip in SKY130 130 nm CMOS
DESCRIPTION:Electrochemical impedance spectroscopy (EIS) is the workhorse measurement behind lithium-ion battery diagnostics\, biosensing\, and corrosion science — yet no integrated circuit has ever delivered the complete capability of a benchtop analyzer on a single die. \nThis dissertation presents ISoC\, the first universal Impedance Spectroscopy instrument-on-chip. Designed in SkyWater 130 nm CMOS process\, ISoC supports all four standard electrochemical measurement modes and performs Fourier analysis\, calibration\, and model fitting directly on-chip. The work introduces a new delta-sigma transimpedance amplifier that breaks a long-standing sensitivity–bandwidth tradeoff in current measurement. It also presents the first application of digital predistortion — a technique borrowed from wireless transmitter design — to electrochemical instrumentation\, reducing calibration error by more than an order of magnitude. The design is validated through a ten-level verification methodology spanning from transistor-level simulation to FPGA emulation — an approach that uncovered silicon-critical bugs prior to fabrication. \nEvent Host: Azzam Qureshi\, Ph.D. Candidate\, Electrical & Computer Engineering \nAdvisor: Ken Pedrotti \nZoom: https://ucsc.zoom.us/j/93312223921?pwd=jzCP7f8gbzqbkFGabEd4wM7O5TgHIH.1 \nPasscode: 342251
URL:https://events.ucsc.edu/event/qureshi-a-ece-isoc-a-universal-impedance-spectroscopy-instrument-on-chip-in-sky130-130-nm-cmos/
LOCATION:
CATEGORIES:Ph.D. Presentations
ATTACH;FMTTYPE=image/jpeg:https://events.ucsc.edu/wp-content/uploads/2026/04/ph.d.-presentation-graphic-option2.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20260529T140000
DTEND;TZID=America/Los_Angeles:20260529T160000
DTSTAMP:20260601T095850
CREATED:20260512T162505Z
LAST-MODIFIED:20260512T163221Z
UID:10014627-1780063200-1780070400@events.ucsc.edu
SUMMARY:Zhu\, R. (ECE) - From Neuromorphic Principles to Efficient Neural Language Architectures
DESCRIPTION:This dissertation investigates how neuromorphic and brain-inspired principles can guide the design of efficient neural language architectures. It addresses two central limitations of modern Transformer-based language models: memory growth with context length and high computational cost from dense matrix multiplication. Through studies of spiking neural networks\, linear-recurrent language models\, hybrid attention architectures\, MatMul-free models\, and looped language models\, the dissertation develops practical approaches for bounded-memory and bounded-compute language modeling. The central conclusion is that recurrent state\, temporal decay\, sparse computation\, and parameter reuse can provide useful design principles for scalable language models\, even when they are abstracted beyond literal biological spiking. \nEvent Host: Ridger Zhu\, Ph.D. Candidate\, Electrical & Computer Engineering  \nAdvisor: Jason Eshraghian \nZoom: https://ucsc.zoom.us/j/96672322005?pwd=3MSitgbm5WboIENbf1hKpxwXnt9VXh.1
URL:https://events.ucsc.edu/event/zhu-r-ece-from-neuromorphic-principles-to-efficient-neural-language-architectures/
LOCATION:Engineering 2\, Engineering 2 1156 High Street\, Santa Cruz\, CA\, 95064
CATEGORIES:Ph.D. Presentations
ATTACH;FMTTYPE=image/jpeg:https://events.ucsc.edu/wp-content/uploads/2026/04/ph.d.-presentation-graphic-option2.jpg
GEO:37.0009723;-122.0632371
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=Engineering 2 Engineering 2 1156 High Street Santa Cruz CA 95064;X-APPLE-RADIUS=500;X-TITLE=Engineering 2 1156 High Street:geo:-122.0632371,37.0009723
END:VEVENT
END:VCALENDAR