אירועים והרצאות בפקולטה למדעי המחשב ע"ש הנרי ומרילין טאוב

In this talk, I present an approach for interpreting the internal computation in deep vision models. I show that these interpretations can be used to detect model bugs and to improve the performance of pre-trained deep neural networks (e.g., reducing hallucinations from image captioners and detecting and removing spurious correlations in CLIP) without any additional training. Moreover, the obtained understanding of deep representations can unlock new model capabilities (e.g., novel identity e...
[ לנוסח המלא ]

Image generative models are advancing rapidly, producing images of remarkable realism and fidelity. However, existing models often lack precise control over the generated content, limiting their image editing capabilities and the integration of real content into synthesized imagery. In this talk, I will demonstrate how a deep understanding of the inner mechanisms of large-scale pretrained generative models enables the design of powerful techniques for a variety of image manipulation tasks. By...
[ לנוסח המלא ]

ממשיכים במרתון סדנאות הקריירה! אחרי שהכרתם את סוגי המשרות הקיימות, הגיע הזמן לשדרג את קורות החיים שלכם.אנו מזמינים אתכם לסדנת הקו"ח הראשון שלי – איך הופכים דף ריק להזדמנות בהנחיית בר יעקבי, בוגרת הפקולטה יום שלישי, 21.1, החל מהשעה 17:30 בטאוב 33...
[ לנוסח המלא ]

Language models (LMs) are increasingly used to assist users in day to day tasks such as programming (Github Copilot) or search (Google's AI Overviews). But can we build language model systems that are able to autonomously complete entire tasks end-to-end? In this talk I'll discuss our efforts to build autonomous LM systems, focusing on the software engineering domain. I'll present SWE-bench, our novel method for measuring the performance of automatic programming systems on their abilities to ...
[ לנוסח המלא ]

Digital pathology has emerged as a transformative field, enabling automated imaging and computational analysis of thin tissue biopsy slices or body fluids. These samples are typically stained to enhance contrast in biological structures and reveal their morphology under microscopic magnification. Digitally scanning these stained samples produces gigapixel-scale images, known as whole slide images (WSIs), which pose significant challenges for computational analysis using deep learning techniqu...
[ לנוסח המלא ]

How can we trust the correctness of a learned model on a particular input of interest? Model accuracy is typically measured on average over a distribution of inputs, giving no guarantee for any specific input. This talk introduces Self-Proving models, a new class of models that formally prove the correctness of their outputs via an Interactive Proof system. We will formally define Self-Proving models and their per-input (worst-case) guarantees. We will then present algorithms for learning the...
[ לנוסח המלא ]

המהפכה של הבינה המלאכותית מתרחבת מעולם הענן הישר למחשבים האישיים שלנו, ואתם מוזמנים להצטרף לסדנה מעשית בת 3 שעות בה תוכלו לחוות את ההתקדמות והיכולות האחרונות...
[ לנוסח המלא ]

In a recent work, Cormode, Dall'Agnol, Gur and Hickey (CCC, 2024) introduced the model of Zero-Knowledge Streaming Interactive Proofs (zkSIPs). Loosely speaking, such proof-systems enable a prover to convince a streaming verifier that the input x, to which it has read-once streaming access, satisfies some property, in such a way that nothing beyond the correctness of the claim is revealed. Cormode et al. also gave constructions of zkSIPs to some specific and notable p...
[ לנוסח המלא ]

Over the past decade, several studies have shown that DNA-based storage systems can potentially become the standard for data archival due to their high data density and durability. However, the current bottleneck involves the synthesis and sequencing costs, along with a lack of coding solutions to address the unique error characteristics of DNA-based systems. This work tackles multiple challenges that hinder the practical implementation of DNA storage. First, we explore theoretical as...
[ לנוסח המלא ]

 Over the past decade, an increasing number of systems and devices have gained Internet connectivity and been enhanced with sensing capabilities and AI. While these advancements have created a world of smarter, more automated, and highly connected devices, they have also introduced significant security and privacy challenges that cannot be effectively addressed with traditional countermeasures. In the first part of this talk, we will explore the security and privacy concerns of c...
[ לנוסח המלא ]

אנו שמחים להזמינכם לכנס Tech.AI Robotics– אשר יתקיים ב-5 בפברואר 2025 ויעסוק בצומת הקריטי שבין בינה מלאכותית ורובוטיקה: ממערכות ביתיות חכמות למכוניות אוטונומיות, פסי ייצור מתקדמים וניתוחים רפואיים - הטכנולוגיות הללו מחוללות מהפכה �...
[ לנוסח המלא ]

Edge computing extends cloud capabilities to the proximity of end-users, offering ultra-low latency, which is essential for real-time applications. Unlike traditional cloud systems that suffer from latency and reliability constraints due to distant datacenters, edge computing employs a distributed model, leveraging local edge datacenters to process and store data. This talk explores key challenges in edge computing across three domains: workloads, storage, and service allocation. ...
[ לנוסח המלא ]

Labeling schemes are a prevalent paradigm in various computing settings. In such schemes, an oracle is given an input graph and produces a label for each of its nodes, enabling the labels to be used for various tasks. In this talk, I will address the question of what happens in a labeling scheme if some labels are erased, e.g., due to communication loss with the oracle or hardware errors. I will present a new resilient labeling scheme which improves upon the state of the art in several comput...
[ לנוסח המלא ]

A myriad of authentication mechanisms embody a continuous evolution from verbal passwords in ancient times to contemporary multi-factor authentication: Cryptocurrency wallets advanced from a single signing key to using a handful of well-kept credentials, and for online services, the infamous “security questions” were all but abandoned. Nevertheless, digital asset heists and numerous identity theft cases illustrate the urgent need to revisit the fundamentals of user authentication....
[ לנוסח המלא ]

In the field of video compression, the pursuit for better quality at lower bit rates remains a long-lasting goal. Recent developments have demonstrated the potential of Implicit Neural Representation (INR) as a promising alternative to traditional transform-based methodologies. Video INRs can be roughly divided into frame-wise and pixel-wise methods according to the structure the network outputs. While the pixel-based methods are better for upsampling and parallelization, frame-wise methods d...
[ לנוסח המלא ]

When learning is used to inform decisions about humans, such as for loans, hiring, or admissions, this can incentivize users to strategically modify their features to obtain positive predictions. A key assumption is that modifications are costly, and are governed by a cost function that is exogenous and predetermined. We challenge this assumption, and assert that the deployment of a classifier is what creates costs. Our idea is simple: when users seek positive predictions, this creates d...
[ לנוסח המלא ]

Constraint satisfaction problems (CSPs in short) are among the most important computational problems studied in TCS. This talk will focus on a recent line of study addressing the complexity of approximating satisfiable instances of CSPs, and  connections of this study to multi-player parallel repetition theorems, property testing and extremal combinatorics. Based mostly on joint works with Amey Bhangale, Subhash Khot and Yang P. Liu....
[ לנוסח המלא ]

חברת פיינאל מגיעה לפקולטה ליום זרקור והרצאה טכנולוגיתיום רביעי הבא 15/1 בצה"ד החל מהשעה 12:30 בטאוב מחפשים את הצעד הבא שלכם? רוצים לשמוע על אלגו-טריידינג, אופציות והסתברויות?חברת פיינאל מגיעה עם צוותי גיוס ומהנדסים שיספרו לכם הכול – מקריירה ועד טכנ�...
[ לנוסח המלא ]

Deduplication is widely utilized in many modern large scale storage systems and provide an effective solution for both secondary and primary storage. Therefore, there is a rising need for deduplication storage to support advanced features such as data indexing for information retrieval. To our knowledge, no indexing solution for deduplicated storage utilizes the deduplication and current indexing methods process duplicates. In this work, we propose IDEA, Inverted Dedupl...
[ לנוסח המלא ]

Tuesday, January 14, 2025 at 11:30Meyer Building Room 1061 & Zoom This talk will explore advances in 3D scene reconstruction, focusing on approaches ...
[ לנוסח המלא ]

Computational analogs of information-theoretic notions have given rise to some of the most intriguing phenomena in theoretical computer science. For example, pseudorandomness allows us to bypass Shannon's lower bounds on the key length of encryption schemes. Moreover, computational analogs of entropy and randomness are key tools in the construction of pseudorandom generators and have become foundational concepts in complexity theory and cryptography.One such computational analog is time-b...
[ לנוסח המלא ]

זה הזמן לקחת את הקריירה שלכם צעד קדימה! מרתון קריירה יוצא לדרך, ואתם מוזמנים למפגש הראשון שלנו – סדנת חשיפה למשרות בתעשייה - עושים סדר בBuzz Words -יום שני, 13.1, בשעה 17:30 באודיטוריום פסנתר רוצים להבין מה עומד מאחורי הטייטלים הנחשקים בתעשייה?...
[ לנוסח המלא ]

מוזמנים לערב  "מחקר על הבר" - שלושה חברי סגל בהרצאות TED בגובה העיניים.  אל תפספסו את ההזדמנות להכיר את החוקרים וקבוצות המחקר החדשות, באווירה פתוחה עם בירות ונשנושים.  יום רביעי, 8/1 החל מהשעה 18:30 בטאוב 2. ד"ר ברית יונגמן - שים מבטחך בנתונים...
[ לנוסח המלא ]

The Huge Object model is a distribution testing model in which we are given access to independent samples from an unknown distribution over the set of strings {0,1}^n, but are only allowed to query a few bits from the samples. We investigate the problem of testing whether a distribution is supported on m elements in this model. It turns out that the behavior of this property is surprisingly intricate, especially when also considering the question of adaptivity. We prove lower and upper bounds...
[ לנוסח המלא ]

Join us for our Internship Spotlight Day, where we’ll introduce the TII AI/IR Research Center recently established in Haifa, discuss our work in Generative AI and share details about our 2025 Internship Program. Date: Wednesday, January 8 Time: 12:30–14:15 Agenda: 12:30-13:00: Get-together 13:00-13:50 : Introduction & Tech Talk &...
[ לנוסח המלא ]

בואו להיות חלק מקבוצת Capture The Flag-CTF של הטכניון!  והשבוע: הרצאת אורח בנושא אבטחת בינה מלאכותית! Building and Breaking AI Security בהנחיית עמית לוי ורום הימלשטיין – חוקרי אבטחת AI בטכניון “The Model They Told You Not to Worry About” איך חולשות במודלים של שפה עלולות לגרום לקריסת מערכות ...
[ לנוסח המלא ]

Developing better Language Models would benefit a myriad of communities. However, it is prohibitively costly. The talk would describe collaborative approaches to pretraining such as model merging, allowing combining several specialized models into one. Then introduce efficient evaluation to reduce overheads and touch on other accessible and collaborative aspects that best harness the expertise and diversity in Academia....
[ לנוסח המלא ]

Classical shape descriptors such as Heat Kernel Signature (HKS), Wave Kernel Signature (WKS), and Signature of Histograms of Orientations (SHOT), while widely used in shape analysis, exhibit sensitivity to mesh connectivity, sampling patterns, and topological noise. While differential geometry offers a promising alternative through its theory of differential invariants, which are theoretically guaranteed to be robust shape descriptors, the computation of these invariants on discrete m...
[ לנוסח המלא ]

Generative models, such as ChatGPT and DALL-E, are used by millions of people daily for tasks ranging from programming and content creation to resume filtering. These models often create the impression of being “intelligent,” which can incentivize careless use in critical applications. While generative models are empowering, they appear to be black boxes, and their misuse can result in harmful or unlawful outcomes. In this talk, I will present algorithms and tools for diss...
[ לנוסח המלא ]

Artificial intelligence (AI) offers immense potential to accelerate scientific discoveries crucial for combating climate change. However, this powerful tool comes with a significant environmental cost due to its substantial energy consumption and carbon emissions. This talk explores the research challenge of harnessing AI's capabilities while minimizing its ecological footprint. Bio: Dr. Tamar Eilam is an IBM Fellow and Chief Scientist for Sustainable Computing i...
[ לנוסח המלא ]

We explore the framework of contract design through a computational perspective. Contract design is a fundamental pillar of microeconomics, addressing the essential question of how to incentivize people to work. The significance of contract design was acknowledged by the Nobel Prize awarded to Hart and Holmström, and it applies to various real-life scenarios, such as determining bonuses for employees, setting commission structures for sales representatives, and designing payment schemes ...
[ לנוסח המלא ]