Niklas Klinger, Jonas Sander, Peterson Yuhala
et al.
Homomorphic encryption (HE) is a promising technology for confidential cloud computing, as it allows computations on encrypted data. However, HE is computationally expensive and often memory-bound on conventional computer architectures. Processing-in-Memory (PIM) is an alternative hardware architecture that integrates processing units and memory on the same chip or memory module. PIM enables higher memory bandwidth than conventional architectures and could thus be suitable for accelerating HE. In this work, we present DRAMatic, which implements operations foundational to HE on UPMEM's programmable, general-purpose PIM system, and evaluate its performance. DRAMatic incorporates many arithmetic optimizations, including residue number system and number-theoretic transform techniques, and can support the large parameters required for secure homomorphic evaluations. To compare performance, we evaluate DRAMatic against Microsoft SEAL, a popular open-source HE library, regarding both runtime and energy efficiency. The results show that DRAMatic significantly closes the gap between UPMEM PIM and Microsoft SEAL. However, we also show that DRAMatic is currently constrained by UPMEM PIM's multiplication performance and data transfer overhead. Finally, we discuss potential hardware extensions to UPMEM PIM.
Esta pesquisa investiga a prática continuada do ensino de balé clássico para um grupo de pessoas com mais de 50 anos, adotando uma abordagem metodológica participativa. O estudo foi realizado em parceria com o Programa UniversIdade, da Universidade Estadual de Campinas, que promove atividades extensionistas para esse público. As aulas analisadas foram estruturadas com base no trabalho de Zélia Monteiro, artista que propõe a continuidade da tradição do balé clássico enquanto desafia o discurso dominante na dança, ao valorizar as singularidades dos alunos. Os relatos dos participantes revelam que a prática do balé contribuiu significativamente para o bem-estar, autoestima, autoconsciência e sociabilidade, tornando-se parte da construção de uma velhice que celebra a experiência acumulada e a vida.
This paper addresses the challenges of learning representations for recipes and food images in the cross-modal retrieval problem. As the relationship between a recipe and its cooked dish is cause-and-effect, treating a recipe as a text source describing the visual appearance of a dish for learning representation, as the existing approaches, will create bias misleading image-and-recipe similarity judgment. Specifically, a food image may not equally capture every detail in a recipe, due to factors such as the cooking process, dish presentation, and image-capturing conditions. The current representation learning tends to capture dominant visual-text alignment while overlooking subtle variations that determine retrieval relevance. In this paper, we model such bias in cross-modal representation learning using causal theory. The causal view of this problem suggests ingredients as one of the confounder sources and a simple backdoor adjustment can alleviate the bias. By causal intervention, we reformulate the conventional model for food-to-recipe retrieval with an additional term to remove the potential bias in similarity judgment. Based on this theory-informed formulation, we empirically prove the oracle performance of retrieval on the Recipe1M dataset to be MedR=1 across the testing data sizes of 1K, 10K, and even 50K. We also propose a plug-and-play neural module, which is essentially a multi-label ingredient classifier for debiasing. New state-of-the-art search performances are reported on the Recipe1M dataset.
Multi-modal representation learning has become a pivotal area in artificial intelligence, enabling the integration of diverse modalities such as vision, text, and audio to solve complex problems. However, existing approaches predominantly focus on bimodal interactions, such as image-text pairs, which limits their ability to fully exploit the richness of multi-modal data. Furthermore, the integration of modalities in equal-scale environments remains underexplored due to the challenges of constructing large-scale, balanced datasets. In this study, we propose Synergy-CLIP, a novel framework that extends the contrastive language-image pre-training (CLIP) architecture to enhance multi-modal representation learning by integrating visual, textual, and audio modalities. Unlike existing methods that focus on adapting individual modalities to vanilla-CLIP, Synergy-CLIP aligns and captures latent information across three modalities equally. To address the high cost of constructing large-scale multi-modal datasets, we introduce VGG-sound+, a triple-modal dataset designed to provide equal-scale representation of visual, textual, and audio data. Synergy-CLIP is validated on various downstream tasks, including zero-shot classification, where it outperforms existing baselines. Additionally, we introduce a missing modality reconstruction task, demonstrating Synergy-CLIP's ability to extract synergy among modalities in realistic application scenarios. These contributions provide a robust foundation for advancing multi-modal representation learning and exploring new research directions.
Michael Feffer, Anusha Sinha, Wesley Hanwen Deng
et al.
In response to rising concerns surrounding the safety, security, and trustworthiness of Generative AI (GenAI) models, practitioners and regulators alike have pointed to AI red-teaming as a key component of their strategies for identifying and mitigating these risks. However, despite AI red-teaming's central role in policy discussions and corporate messaging, significant questions remain about what precisely it means, what role it can play in regulation, and how it relates to conventional red-teaming practices as originally conceived in the field of cybersecurity. In this work, we identify recent cases of red-teaming activities in the AI industry and conduct an extensive survey of relevant research literature to characterize the scope, structure, and criteria for AI red-teaming practices. Our analysis reveals that prior methods and practices of AI red-teaming diverge along several axes, including the purpose of the activity (which is often vague), the artifact under evaluation, the setting in which the activity is conducted (e.g., actors, resources, and methods), and the resulting decisions it informs (e.g., reporting, disclosure, and mitigation). In light of our findings, we argue that while red-teaming may be a valuable big-tent idea for characterizing GenAI harm mitigations, and that industry may effectively apply red-teaming and other strategies behind closed doors to safeguard AI, gestures towards red-teaming (based on public definitions) as a panacea for every possible risk verge on security theater. To move toward a more robust toolbox of evaluations for generative AI, we synthesize our recommendations into a question bank meant to guide and scaffold future AI red-teaming practices.
Addressing the challenge of limited labeled data in clinical settings, particularly in the prediction of fatty liver disease, this study explores the potential of graph representation learning within a semi-supervised learning framework. Leveraging graph neural networks (GNNs), our approach constructs a subject similarity graph to identify risk patterns from health checkup data. The effectiveness of various GNN approaches in this context is demonstrated, even with minimal labeled samples. Central to our methodology is the inclusion of human-centric explanations through explainable GNNs, providing personalized feature importance scores for enhanced interpretability and clinical relevance, thereby underscoring the potential of our approach in advancing healthcare practices with a keen focus on graph representation learning and human-centric explanation.
Galeria w niniejszym tomie czasopisma jest nieco inna niż w numerach wcześniejszych. Nie zawiera fotografii – uznaliśmy bowiem, że bliższy tematom dystrybucji i widowni filmowej będzie plakat: jako ważny element promocji, a często przecież jako pierwszy obraz zawiązujący relację film – odbiorca. Chcieliśmy, by autorskie propozycje plakatów dotyczyły filmów, które z jakichś względów wyróżniają się pod względem dystrybucyjnym – zarówno z perspektywy historycznej, jak i współczesnej. Z tytułów starszych wybór padł na dwa polskie „półkowniki”: Przypadek Krzysztofa Kieślowskiego (1981/1987) i Kobietę samotną Agnieszki Holland (1981/1987). Z produkcji nowszych wskazaliśmy Romę Alfonso Cuaróna (2018) i Nie patrz w górę Adama McKaya (2021) – filmy w dużej mierze zawdzięczające swoją rozpoznawalność usłudze video-on-demand (w obu wypadkach reprezentowanej przez Netflix), która w ostatnim czasie tak silnie zmieniła pejzaż mediów audiowizualnych. Do współpracy zaprosiliśmy Uniwersytet Artystyczny im. Magdaleny Abakanowicz w Poznaniu. Studenckie projekty powstały w I Pracowni Plakatu, na Wydziale Grafiki i Komunikacji Wizualnej (prowadzący: prof. Grzegorz Marszałek, p.o. kierownik: dr Marcin Markowski). Prezentowane grafiki pokazują rozmaite sposoby potraktowania zadanego tematu, w mniejszym lub większym stopniu nawiązujące do fabuły lub dyskursu danego filmu.
This article presents the theater scholarship of Irena Sławińska (1913–2004), an eminent humanist affiliated with the Catholic University of Lublin for more than five decades, co-founder of Polish drama and theater studies. The author discusses Sławińska’s research on the language of drama, poetic and religious drama, as well as her methodological proposals for drama and theater analysis, anthropology, and philosophy. The article also describes the scholar’s role in developing relations between Polish and Western theatre studies, especially with regard to Anglo- and Francophone research, and highlights her original contribution to the analysis of anthropological foundations of the idea of theater that refers to classical philosophy and Christianity.
Dramatic representation. The theater, The performing arts. Show business
The article focuses on one of the most critical issues when it comes to cultural heritage, namely the authenticity of a specific cultural practice and its role in the definition of a community identity. A fundamental characteristic for many UNESCO programs, authenticity is formally excluded from the text of the 2003 Convention for the Safeguarding of Intangible Cultural Heritage and from the Operational Directives; yet, in the application of these tools, it is one of the most problematic issues both for the communities of practitioners and for the bodies responsible for the protection of the registered elements, with clear implications of anthropological, political, and economic nature. The contribution reflects on the myth of authenticity and its declinations in terms of “ownership” and “exclusivity” of different cultural practices, approaching the analysis from a dual perspective: the regulatory developments at an international level and the most recent determinations of UNESCO are placed in dialogue with the legal and doctrinal interpretations in the Italian context, restoring the complexity of a subject in which demo-ethno-anthropological skills prove essential for the understanding of the law and its application to the concrete cases of human communities.
Anthropology, Dramatic representation. The theater
This study used a critical disability studies analysis of historical and contemporary theatre work, informed by interviews with theatre practitioners and spectators to understand how disability, ethnic, racial, gender, and sexual identity is being representing in Sinhala theatre in Sri Lanka. The thesis explored how theatre practitioners and audiences want to see identity representations evolve in future, to create change in Sri Lankan society.
This article aims to critically engage with Odin Teatret’s most recent addition to the repertoire, The Tree (2016), in order to investigate the ways in which Barba’s dramaturgical decision-making processes create a performance field that metaphorically comments on the status of the group today whilst critiquing contemporary geo-politics. Importantly, we argue that notions of interculturalism – which have often been employed by scholars to critique the Odin’s work – do not address the full complexity of the embodied concatenation of the group’s practice, and we employ the term interstitial to more effectively articulate the complex space produced by the group’s training and performances.
Hostages of Me by Tue Biering and Hvad har vi egentlig haft gang i? Etiske, sociale og kunstneriske undersøgelser by Jeppe Kristensen: In two articles, the founders of FIX&FOXY are reflecting on how the production company can develop theater and performances, in order to make the audience reflect on societal dilemmas. InterviewsPretty Woman Walking Down the Street. Interview with Biering and Kristensen by Gade. The interview explores the artistic strategy around the performance Pretty Woman A/S (2008), performed by female prostitutes, which triggered a strong public debate. Møder, relationer, populærkultur og repræsentation. Interview with Bering by Gade. In this conversation, Gade draws a portrait of FIX&FOXY’s practices, and identifies some fundamental themes in contemporary theatre. Udflugt til ungdomsland. Interview with Kristensen by Christoffersen and Krøgholt. Kristensen reflects on the process of Youth (Ungdom) focusing and on how the company created ownership for the young participants, to give agency as co-developers of the performance’s various spaces. My Deer Hunter. Interview af de medvirkende og det kreative team. Interview with participants from My Deer Hunter by Christoffersen, Krøgholt og Winkelhorn. In dialouge with four participating veterans and the artistic team behind My Deer Hunter, the interview explores, how the performance and rehearsal process functioned for a group of PTSD affected veterans, and how their histories and participation in war was challenged. FIX&FOXY’s poetik, metode og organisering. Interview with Biering by Christoffersen, Krøgholt and Winkelhorn. Biering tells about the principles and the theatre view that have been guiding for FIX&FOXY’s creative and theatrical strategies throughout the theatre’s work. Articles Europæerne. En postdramatisk tilgang til klassikerne by Mads Thygesen. How did the staging of The Europeans exploit classics as a tool to intervene and mix in a current historical and political context? The common denominator for the work was European wars as a dramatic focal point. The article discusses how this performance illuminates the seed of FIX&FOXY’s poetics and conceptual thinking from 2005. Mod alle Odds. Tragedie og statistik by Erik Exe Christoffersen. Against All Odds (2019) are based on identity, representation, and statistics, which portrays how today’s young persons’ lives would statistically look in the future. The question raised by Christoffersen is, how the dramaturgy of the performance creates communication. Forvaltningen af publikums ubehag. FIX&FOXY som politisk konfrontationskunst by Laura Luise Schultz. She describes the approach to the audience in various of performances and highlights, that a central feature of FIX&FOXY’s political remediation is their sophisticated engagement with the audience and managing of the audience’s discomfort. Love Theater. Uhåndgribelige konflikter by Jeppe Kristensen. Kristensen went to Bangkok to cast a prostitute who should play the leading character in Love Theater. The performance was based on her own life-experiences as prostitute, and the article is reflecting on intangible conflicts, regarding the prejudices of an audience. Samtidskunst, repræsentation og remediering by Erik Exe Christoffersen. Christoffersen emphasizes FIX&FOXY’s way of doing remediation, perceived as a way of ‘overpainting’ a work like a palimpsest. Verdensteater og øjebliksteater by Jeppe Kristensen. Kristensen gives an overall artistic discussion of FIX&FOXY and draws a thread from the company’s beginning as a theatrical variant of contemporary art, to Peter Osborne’s analysis of what contemporary art is today. EssaysFIX&FOXYs distribuering af ledelse by Ida Krøgholt. Krøgholt is unfolding FIX&FOXY’s way of working as distributed facilitation, where the participants facilitate each other, and thus through the theatre process develop an awareness of communication and observation. FIX&FOXY’s representation strategies by Anne Liisberg. Liisberg raises the important questions: Who and how can we represent? And who will never be represented?
Este ensaio objetiva problematizar a paisagem como noção operacional em Artes da Cena. Reflete-se sobre a paisagem no teatro de Gertrude Stein como paradigma para uma cena arquitetada desde uma forma correlacional. Depreende-se, então, que a paisagem na sua condição exemplar pode operar como uma poiética teatral percebida na sua integralidade, nas suas materializações e nos seus possíveis sentidos imaginários.
Copertina del numero 3, comitato editoriale e comitato scientifico
L'immagine di copertina è una immagine della performance on-line di Bruma/Net di Kònic Thtr.
Elaborazione grafica di Vincenzo Sansone
Learning effective language representations from crowdsourced labels is crucial for many real-world machine learning tasks. A challenging aspect of this problem is that the quality of crowdsourced labels suffer high intra- and inter-observer variability. Since the high-capacity deep neural networks can easily memorize all disagreements among crowdsourced labels, directly applying existing supervised language representation learning algorithms may yield suboptimal solutions. In this paper, we propose \emph{TACMA}, a \underline{t}emporal-\underline{a}ware language representation learning heuristic for \underline{c}rowdsourced labels with \underline{m}ultiple \underline{a}nnotators. The proposed approach (1) explicitly models the intra-observer variability with attention mechanism; (2) computes and aggregates per-sample confidence scores from multiple workers to address the inter-observer disagreements. The proposed heuristic is extremely easy to implement in around 5 lines of code. The proposed heuristic is evaluated on four synthetic and four real-world data sets. The results show that our approach outperforms a wide range of state-of-the-art baselines in terms of prediction accuracy and AUC. To encourage the reproducible results, we make our code publicly available at \url{https://github.com/CrowdsourcingMining/TACMA}.
The BR, formulated by Zak in the 80s, is widely used in studies of topological phase of material. EBR are considered the building block of TQC. However, there were debate on whether they admit split bands, or if they contain band invariant subspaces. This manuscript presents a clear definition of the basis and illustrate that the band transformation properties are dependent on the band connectivity. Two different Fourier transform conventions in defining the BR induced from the same set of localised Wannier functions are discussed and identified as related by a simple gauge transformation. The TB BR are used to derive the form of TB Hamiltonian using group theoretical technique. The transformation properties of EBR allow explicit decomposition in terms of irreps of space group, and use of projection operators in determining symmetry permitted band connectivity. It is shown that EBRs arising from Wyckoff positions with multiplicity can have multiple atomic limits and identifies explicitly what occurs at HSPs on the surface of BZ as what determines the band connectivity and the irreducible nature of the connected band. Such multiple configurations arise from multiple ways to block-diagonalising representation matrix at these HSPs. The symmetry permitted connectivity allows the existence of dynamic band invariant subspaces known as irreducible band representations. Such IBR, induced from Wannier functions centred on linear combination of orbits of Wyckoff positions, can also arise from interaction among composite EBRs. They are rooted in the permutation symmetry of crystallographic orbits of Wyckoff positions with multiplicity and can occur even if the parental EBR is classified as indecomposable. When symmetry permitted split EBR occurs, which does not correspond to division between connected IBRs, the topologies of the bands are potentially non-trivial on both sides of the gap.
Sobhan Moosavi, Pravar D. Mahajan, Srinivasan Parthasarathy
et al.
Identifying driving styles is the task of analyzing the behavior of drivers in order to capture variations that will serve to discriminate different drivers from each other. This task has become a prerequisite for a variety of applications, including usage-based insurance, driver coaching, driver action prediction, and even in designing autonomous vehicles; because driving style encodes essential information needed by these applications. In this paper, we present a deep-neural-network architecture, we term D-CRNN, for building high-fidelity representations for driving style, that combine the power of convolutional neural networks (CNN) and recurrent neural networks (RNN). Using CNN, we capture semantic patterns of driver behavior from trajectories (such as a turn or a braking event). We then find temporal dependencies between these semantic patterns using RNN to encode driving style. We demonstrate the effectiveness of these techniques for driver identification by learning driving style through extensive experiments conducted on several large, real-world datasets, and comparing the results with the state-of-the-art deep-learning and non-deep-learning solutions. These experiments also demonstrate a useful example of bias removal, by presenting how we preprocess the input data by sampling dissimilar trajectories for each driver to prevent spatial memorization. Finally, this paper presents an analysis of the contribution of different attributes for driver identification; we find that engine RPM, Speed, and Acceleration are the best combination of features.
Ujjal Kr Dutta, Sandeep Repakula, Maulik Parmar
et al.
In this paper, we utilize deep visual Representation Learning to address an important problem in fashion e-commerce: color variants identification, i.e., identifying fashion products that match exactly in their design (or style), but only to differ in their color. At first we attempt to tackle the problem by obtaining manual annotations (depicting whether two products are color variants), and train a supervised triplet loss based neural network model to learn representations of fashion products. However, for large scale real-world industrial datasets such as addressed in our paper, it is infeasible to obtain annotations for the entire dataset, while capturing all the difficult corner cases. Interestingly, we observed that color variants are essentially manifestations of color jitter based augmentations. Thus, we instead explore Self-Supervised Learning (SSL) to solve this problem. We observed that existing state-of-the-art SSL methods perform poor, for our problem. To address this, we propose a novel SSL based color variants model that simultaneously focuses on different parts of an apparel. Quantitative and qualitative evaluation shows that our method outperforms existing SSL methods, and at times, the supervised model.
Our research deals with the role of theatrical decoration in creating visual thumbs and the effect achieved as a result in the theatrical presentation in terms of supporting the idea of centralization of the dramatic construction of the show, as the researcher emphasizes that this topic has begun with a new horizon removed many technical concepts and knowledge in the theater. Horizon knowledge and discoveries based on the structures of light and sight to achieve an existing transformation from steel to ethereal. According to these new concepts, systems other than those based on old methods of presentation have been formed.In light of this, the researcher divided his research into:First: the problem of research and the need for it. The researcher asked the problem a number of questions, the most important of which is: how does the illusion in the theater affect the phenomenon of receiving. He also set his goal of revealing the visual illusion in contemporary theatrical decor. He linked the importance of research in the fact that it benefits scholars and workers in the theatrical production industry.The researcher addressed in the second chapter (cognitive framework) the structure of illusion in theatrical decoration based on the image in the visual art is considered to be deceptive and shaded and the information is collected by the sense of sight and then treated by the brain . Where the illusion of reading the image occurs through the theoretical manipulation of the drawing of the work. In the last chapter, the researcher adopted the descriptive analytical method of reading the levels of the sample and the directing treatment and the role of visual deception in the illusion achieved in the research and his awareness of the play (Facebook) which was presented on the national stage in Baghdad in March 2011 by the preparation and directing (Imad Mohammed) and representation (Mohammed Hashem), and then reached the researcher at the end of his research to the most important results and the most prominent conclusions and sealed the list of sources and references on which he relied.