Adversarial Training (AT) is one of the most effective methods to enhance the robustness of DNNs. However, existing AT methods suffer from an inherent trade-off between adversarial robustness and clean accuracy, which seriously hinders their real-world deployment. While this problem has been widely studied within the current AT paradigm, existing AT methods still typically experience a reduction in clean accuracy by over 10% to date, without significant improvements in robustness compared with simple baselines like PGD-AT. This inherent trade-off raises a question: whether the current AT paradigm, which assumes to learn the corresponding benign and adversarial samples as the same class, inappropriately combines clean and robust objectives that may be essentially inconsistent. In this work, we surprisingly reveal that up to 40% of CIFAR-10 adversarial samples always fail to satisfy such an assumption across various AT methods and robust models, explicitly indicating the improvement room for the current AT paradigm. Accordingly, to relax the tension between clean and robust learning derived from this overstrict assumption, we propose a new AT paradigm by introducing an additional dummy class for each original class, aiming to accommodate the hard adversarial samples with shifted distribution after perturbation. The robustness w.r.t. these adversarial samples can be achieved by runtime recovery from the predicted dummy classes to their corresponding original ones, eliminating the compromise with clean learning. Building on this new paradigm, we propose a novel plug-and-play AT technology named DUmmy Classes-based Adversarial Training (DUCAT). Extensive experiments on CIFAR-10, CIFAR-100, and Tiny-ImageNet demonstrate that the DUCAT concurrently improves clean accuracy and adversarial robustness compared with state-of-the-art benchmarks, effectively breaking the existing inherent trade-off.

This study presents a theory-inspired visual narrative generative system that integrates conceptual principles-comic authoring idioms-with generative and language models to enhance the comic creation process. Our system combines human creativity with AI models to support parts of the generative process, providing a collaborative platform for creating comic content. These comic-authoring idioms, derived from prior human-created image sequences, serve as guidelines for crafting and refining storytelling. The system translates these principles into system layers that facilitate comic creation through sequential decision-making, addressing narrative elements such as panel composition, story tension changes, and panel transitions. Key contributions include integrating machine learning models into the human-AI cooperative comic generation process, deploying abstract narrative theories into AI-driven comic creation, and a customizable tool for narrative-driven image sequences. This approach improves narrative elements in generated image sequences and engages human creativity in an AI-generative process of comics. We open-source the code at https://github.com/RimiChen/Collaborative_Comic_Generation.

Human intelligence, the most evident and accessible form of source of reasoning, hosted by biological hardware, has evolved and been refined over thousands of years, positioning itself today to create new artificial forms and preparing to self--design their evolutionary path forward. Beginning with the advent of foundation models, the rate at which human and artificial intelligence interact with each other has surpassed any anticipated quantitative figures. The close engagement led to both bits of intelligence to be impacted in various ways, which naturally resulted in complex confluences that warrant close scrutiny. In the sequel, we shall explore the interplay between human and machine intelligence, focusing on the crucial role humans play in developing ethical, responsible, and robust intelligent systems. We slightly delve into interesting aspects of implementation inspired by the mechanisms underlying neuroscience and human cognition. Additionally, we propose future perspectives, capitalizing on the advantages of symbiotic designs to suggest a human-centered direction for next-generation AI development. We finalize this evolving document with a few thoughts and open questions yet to be addressed by the broader community.

This paper explores the integration of visual communication and musical interaction by implementing a robotic camera within a "Guided Harmony" musical game. We aim to examine co-creative behaviors between human musicians and robotic systems. Our research explores existing methodologies like improvisational game pieces and extends these concepts to include robotic participation using a PTZ camera. The robotic system interprets and responds to nonverbal cues from musicians, creating a collaborative and adaptive musical experience. This initial case study underscores the importance of intuitive visual communication channels. We also propose future research directions, including parameters for refining the visual cue toolkit and data collection methods to understand human-machine co-creativity further. Our findings contribute to the broader understanding of machine intelligence in augmenting human creativity, particularly in musical settings.

Anyone who's ever stared in desperation at a paint colour chart will know that telling shades apart is not always the easiest task. Due to our biological differences, some people seem to have no trouble separating the subtlest of tones, while others find it tricky to find a matching pair of socks. If you've ever wondered where you fall on this colour spectrum, a new test will reveal how you stack up against your peers. So, what's your colour IQ? Take the test at this link to find out. The test, created by X-rite Pantone, is a simplified version of something called the Farnsworth Munsell 100 Hue Test which was developed in the 1940s by a scientist called Dean Farnsworth.

The world's shortest IQ test not only reveals your intelligence but also your level of patience. The test, called a Cognitive Reflection Test (CRT), consists of three math-based questions that target a person's ability to ignore their initial gut response in favor of a more rational thought process. Many quickly assume the answers are simple, but the Yale University professor who created the exam warned it isn't as straightforward as it may seem. Professor Shane Frederick created the CRT in 2005 and only 20 to 40 percent of students who have attempted it have passed. A Yale University professor designed a Cognitive Reflection Test ( CRT) that consists of three math-based questions that target a person's ability to ignore their initial gut response in favor of a more rational thought process Mathematical brain teasers are useful in helping people develop logical thinking by promoting brain stimulation and build visual and spatial reasoning skills.

The idea that superintelligent robots are alien invaders coming to "steal our jobs" reveals profound shortcomings in the way we think about work, value, and intelligence itself. Labor is not a zero-sum game, and robots aren't an "other" that competes with us. Like any technology, they're part of us, growing out of civilization the same way hair and nails grow out of a living body. When we "other" a fruit-picking robot – thinking of it as a competitor in a zero-sum game – we take our eyes off the real problem: the human who used to pick the fruit is considered disposable by the farm's owners and by society when no longer fit for that job. This implies that the human laborer was already being treated like a non-person – that is, like a machine.

The world's biggest record labels are suing two artificial intelligence startups, taking an aggressive stance to protect their intellectual property against technology that makes it easy for people to generate music based on existing songs. The Recording Industry Association of America said it filed twin lawsuits Monday against Suno AI and Uncharted Labs Inc., the developer of Udio AI, on behalf of Universal Music Group NV, Warner Music Group Corp. and Sony Music Entertainment. The RIAA, a trade group for record labels, is seeking damages of as much as 150,000 "per work infringed." That could amount to potentially billions of dollars. "The music community has embraced AI, and we are already partnering and collaborating with responsible developers to build sustainable AI tools centered on human creativity that put artists and songwriters in charge," Mitch Glazier, chief executive officer of the RIAA, said in a statement.

Over the last ten years, the realm of Artificial Intelligence (AI) has experienced an explosion of revolutionary breakthroughs, transforming what seemed like a far-off dream into a reality that is now deeply embedded in our everyday lives. AI's widespread impact is revolutionizing virtually all aspects of human life, and software engineering (SE) is no exception. As we explore this changing landscape, we are faced with questions about what the future holds for SE and how AI will reshape the roles, duties, and methodologies within the field. The introduction of these groundbreaking technologies highlights the inevitable shift towards a new paradigm, suggesting a future where AI's capabilities may redefine the boundaries of SE, potentially even more than human input. In this paper, we aim at outlining the key elements that, based on our expertise, are vital for the smooth integration of AI into SE, all while preserving the intrinsic human creativity that has been the driving force behind the field. First, we provide a brief description of SE and AI evolution. Afterward, we delve into the intricate interplay between AI-driven automation and human innovation, exploring how these two components can work together to advance SE practices to new methods and standards.