BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Department of Computer Science - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Department of Computer Science
X-ORIGINAL-URL:https://www.cs.jhu.edu
X-WR-CALDESC:Events for Department of Computer Science
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:20260423T103000
DTEND;TZID=America/New_York:20260423T120000
DTSTAMP:20260422T155715
CREATED:20260410T143619Z
LAST-MODIFIED:20260410T143619Z
UID:1994265-1776940200-1776945600@www.cs.jhu.edu
SUMMARY:CS & ISI Seminar Series: From Dashboards to Labels: Helping Users Manage and Make Decisions about Privacy
DESCRIPTION:Refreshments are available starting at 10:30 a.m. The seminar will begin at 10:45 a.m. \nAbstract\nThe surveillance economy\, in which tracking and collecting data are used for the purpose of advertising and other actions\, is central to many of the money- making enterprises of the modern technology ecosystem. Due to regulations and other factors\, some of the largest companies—such as Google and Apple—have prioritized mechanisms that allow users to better manage and understand the data being collected about them. In this talk\, Adam Aviv will explore how effective these mechanisms are and ask who they ultimately serve. He will present recent experiments his team has performed on Google’s data dashboards and their effectiveness\, and will also present ongoing work on Apple’s app-based privacy nutrition labels\, which describe apps’ functionality with relation to privacy. \nSpeaker Biography\nAdam J. Aviv is an associate professor of computer science at the George Washington University. He has broad research interests in computer and cyber- security and privacy\, including network security\, mobile security\, applied cryptography\, and usable security and privacy. Most recently\, he has focused on human factors in mobile device security and authentication\, considering how human choices\, perceptions\, and actions influence system security. \nZoom link »
URL:https://www.cs.jhu.edu/event/cs-isi-seminar-series-from-dashboards-to-labels-helping-users-manage-and-make-decisions-about-privacy/
LOCATION:228 Malone Hall
CATEGORIES:Seminars and Lectures
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260427T120000
DTEND;TZID=America/New_York:20260427T131500
DTSTAMP:20260422T155715
CREATED:20260413T184729Z
LAST-MODIFIED:20260416T173939Z
UID:1994346-1777291200-1777295700@www.cs.jhu.edu
SUMMARY:CS & CLSP Seminar Series: Making LLMs Reason Better\, Faster\, and Longer
DESCRIPTION:Abstract\nRecent “reasoning models” improve LLM performance by generating chains of thought before producing an answer\, with the reasoning process itself optimized through reinforcement learning. This paradigm has delivered impressive results on math and coding benchmarks\, but three fundamental challenges limit its broader applicability. First\, most RL methods require a verifiable reward\, which is easy when there is a single correct answer\, but far less clear for open-ended tasks like writing or summarization. Second\, reasoning traces are expensive: Longer chains mean slower training and slower inference\, and models often overthink simple problems. Third\, many real-world tasks involve very long inputs such as entire books or scientific papers\, yet current reasoning methods were designed for short contexts. In this talk\, Mirella Lapata argues that a single principle\, reasoning by proxy\, can address all three challenges. When a reward cannot be verified directly\, a frozen language model’s perplexity reduction can serve as a proxy reward\, enabling RL-trained reasoning for open-ended generation without any human labels. When full reasoning traces are too costly\, compact latent embeddings can serve as proxy thoughts\, enabling the model to “think silently” and nearly match full RL performance with 70–92% fewer tokens. And when the input is too long to reason over efficiently\, a minimal informational subset can serve as a proxy context on which reasoning is learned and then transferred to the full input\, allowing a small model to match one 10× its size. In each case\, the key insight is the same: By learning on something cheaper that preserves the essential signal\, we can bring RL-based reasoning to settings where direct approaches are intractable. \nSpeaker Biography\nMirella Lapata is a professor of natural language processing in the School of Informatics at the University of Edinburgh. Her research focuses on getting computers to understand\, reason with\, and generate natural language. She is the recipient of the 2025 British Computer Society (BCS) Lovelace Medal for Computing Research and was the inaugural winner of its Karen Spärck Jones Award. Lapata is a Fellow of the Royal Society of Edinburgh\, the Association for Computational Linguistics (ACL)\, and Academia Europaea. She has received a European Research Council Consolidator Grant\, a Royal Society Wolfson Research Merit Award\, and a Turing AI World-Leading Researcher Fellowship. She served as president of the ACL Special Interest Group on Linguistic Data and Corpus-Based Approaches to Natural Language Processing in 2018 and has received multiple Best Paper Awards at leading NLP venues. \nZoom link »
URL:https://www.cs.jhu.edu/event/cs-clsp-seminar-series-making-llms-reason-better-faster-and-longer/
LOCATION:216 Hodson Hall
CATEGORIES:Seminars and Lectures
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260429T100000
DTEND;TZID=America/New_York:20260429T153000
DTSTAMP:20260422T155715
CREATED:20260414T141233Z
LAST-MODIFIED:20260414T141233Z
UID:1994217-1777456800-1777476600@www.cs.jhu.edu
SUMMARY:2026 OlympiCS & Department Awards Ceremony
DESCRIPTION:Join the Department of Computer Science\, Women in Computer Science at Johns Hopkins\, and the Johns Hopkins Chapter of the Association for Computing Machinery for the annual OlympiCS event\, featuring games\, prizes\, and a free lunch! \nThe Computer Science Department Awards Ceremony will take place during lunch at the beginning of the event at 11 a.m. Please join us to celebrate the accomplishments of the exceptional individuals in our department! \nSign up to compete in the OlympiCS here.
URL:https://www.cs.jhu.edu/event/2026-olympics-department-awards-ceremony/
LOCATION:Keyser Quad
CATEGORIES:Graduate Events,Undergraduate Events
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260430T130000
DTEND;TZID=America/New_York:20260430T143000
DTSTAMP:20260422T155715
CREATED:20260413T194940Z
LAST-MODIFIED:20260413T195002Z
UID:1994379-1777554000-1777559400@www.cs.jhu.edu
SUMMARY:2026 CS Senior Thesis Presentations
DESCRIPTION:Please RSVP here. \nZoom link » \nThis year’s theses include: \nCombinatorics on Counterpoint\nBy Alex Ma\, advised by Mike Dinitz.\n\nThis work deals with questions of counting and construction in music theory. We open with problems of harmony\, melody\, and form before describing a central contribution for first species counterpoint. In first species counterpoint\, one is presented with a challenge melody (cantus firmus) and must respond with a valid countermelody (counterpoint) that adheres to certain rules. Many approaches to counterpoint generation have been studied. However\, each of them exhibits one of the following qualities: (a) they are fast but inexact\, (b) they are exact but exponential-time\, (c) they do not account for variation in rulesets between authors\, and (d) they cannot efficiently count the number of solution melodies. We resolve these issues by demonstrating a ruleset-agnostic encoding of first species counterpoint as a regular language. This has several nice properties. Given a length-n cantus firmus\, one can count the number of valid counterpoints in O(n). Given a ruleset for cantus firmi generation\, one can count the number of valid cantus-counterpoint pairs of length n in O(log n). On the generative side\, it also suggests a cost-function-agnostic method for finding an optimal response in O(n2). We close with suggestions for applying and generalizing these results. \nSAW: Toward a Surgical Action World Model via Controllable and Scalable Video Generation\nBy Sampath Rampuri\, advised by Mathias Unberath.\n \nA surgical world model capable of generating realistic surgical action videos with precise control over tool-tissue interactions can address fundamental challenges in surgical AI and simulation—from data scarcity and rare event synthesis to bridging the sim-to-real gap for surgical automation. However\, current video generation methods\, the very core of such surgical world models\, require expensive annotations or complex structured intermediates as conditioning signals at inference\, limiting their scalability. Other approaches exhibit limited temporal consistency across complex laparoscopic scenes and do not possess sufficient realism. We propose Surgical Action World (SAW)\, a step toward surgical action world modeling through video diffusion conditioned on four lightweight signals: language prompts encoding tool-action context\, a reference surgical scene\, tissue affordance mask\, and 2D tool-tip trajectories. We design a conditional video diffusion approach that reformulates video-to-video diffusion into trajectory-conditioned surgical action synthesis. The backbone diffusion model is fine-tuned on a custom-curated dataset of 12\,044 laparoscopic clips with lightweight spatiotemporal conditioning signals\, leveraging a depth consistency loss to enforce geometric plausibility without requiring depth at inference. SAW achieves state-of-the-art temporal consistency (CD-FVD: 199.19 vs. 546.82) and strong visual quality on held-out test data. Furthermore\, we demonstrate its downstream utility for (a) surgical AI\, where augmenting rare actions with SAW-generated videos improves action recognition (clipping F1-score: 20.93% to 43.14%; cutting: 0.00% to 8.33%) on real test data\, and (b) surgical simulation\, where rendering tool-tissue interaction videos from simulator-derived trajectory points toward a visually faithful simulation engine. \nVascular Atlas based on Neural Template Aligned Graph Encodings\nBy Edmund Sumpena\, advised by Craig Jones.\n\nNumerous systemic and ocular diseases affect the vasculature in the retina\, a piece of neural tissue at the back of the eye that is essential for human vision and accessible through non-invasive fundus imaging. In neuroscience\, standardized heathy brains\, also known as an atlas\, have been constructed for standardization\, anatomical mapping\, disease identification\, and a variety of other applications. Despite the importance of retinal vascular architecture in diagnosing and monitoring disease\, no comprehensive spatial atlas of retinal vasculature currently exists due to high intersubject variability\, making standardization across a population exceptionally challenging. To address this gap\, we propose VANTAGE (Vascular Atlas based on Neural Template Aligned Graph Encodings)\, an end-to-end deep learning framework for constructing the first global vascular atlas of the superficial retina\, presented as an initial proof of concept. Inspired by the success of AlphaFold\, VANTAGE leverages known healthy vasculature templates to generate graph encodings of the vasculature and constructs an atlas by minimizing the deformation energy to each sample using a spectrally regularized multilayer perceptron. Experimental results demonstrate that the VANTAGE atlas identifies subjects with diabetic retinopathy\, a disease that commonly disrupts retinal vasculature\, significantly above chance by detecting deviations from the healthy atlas. We further demonstrate population-level standardization and generalizability of the atlas by transferring anatomical labels of the four major vascular arcades onto arbitrary subjects with moderate accuracy. Additional validation confirms that the atlas is spatially centered and faithfully reproduces the vessel tortuosity\, radius\, and length distributions of the training dataset used in its construction.
URL:https://www.cs.jhu.edu/event/2026-cs-senior-thesis-presentations/
LOCATION:228 Malone Hall
CATEGORIES:Undergraduate Events
END:VEVENT
END:VCALENDAR