Controlling the generation of large language models (LLMs) remains a central challenge to ensure their safe and reliable deployment. While prompt engineering and finetuning are common approaches, recent work has explored latent steering, a lightweight technique that alters LLM internal activations to guide generation. However, subsequent studies revealed latent steering's effectiveness to be limited, often underperforming simple instruction prompting. To address this limitation, we first establish a benchmark across diverse behaviors for standardized evaluation of steering techniques. Building on insights from this benchmark, we introduce Instruction Attention Boosting (InstABoost), a latent steering method that boosts the strength of instruction prompting by altering the model's attention during generation. InstABoost combines the strengths of existing approaches and is theoretically supported by prior work that suggests that in-context rule following in transformer-based models can be controlled by manipulating attention on instructions. Empirically, InstABoost demonstrates superior control success compared to both traditional prompting and latent steering.

There are many filmmakers in Hollywood who view AI as antithetical to their creative process. This tension played a major role during the Hollywood strikes in 2023, with many on the picket lines expressing fears about job loss via automation. Talukdar, conversely, argues that AI tools will actually create new types of jobs, and enable studios to push their budgets further rather than slashing them. "There's this idea that instead of spending 50 million on a movie, you can now do it for 5 million, and there's some truth in that," he says. "But the other way to think about it--which is how every studio that we talked to is thinking about it--is now for that 50 million and for the same 100 people on that project, they're just going to be able to do what would have cost them 100 million before," he says.

Counter-terrorism authorities have, for years, characterized keeping up with terrorist organizations and their use of digital tools and social media apps as a game of Whac-a-Mole. Jihadist terrorist groups such as Islamic State and its predecessor al-Qaida, or even the neo-Nazi group the Base, have leveraged digital tools to recruit, covertly finance via crypto, download weapons for 3D printing and spread tradecraft to its followers, all while leaving law enforcement and intelligence agencies playing catch up. Over time, thwarting attacks and maintaining the technological advantage over these types of terror groups has evolved, as more and more open source resources become available. Now, with artificial intelligence – both on the horizon as a rapidly developing technology and in the here and now as free, accessible apps – agencies are scrambling. Sources familiar with the US government's counterterrorism efforts told the Guardian that multiple security agencies are very concerned about how AI is making hostile groups more efficient in their planning and operations.

--Removing floating litter from water bodies is crucial to preserving aquatic ecosystems and preventing environmental pollution. In this work, we present a multi-robot aerial soft manipulator for floating litter collection, leveraging the capabilities of aerial robots. The proposed system consists of two aerial robots connected by a flexible rope manipulator, which collects floating litter using a hook-based tool. Compared to single-aerial-robot solutions, the use of two aerial robots increases payload capacity and flight endurance while reducing the downwash effect at the manipulation point, located at the midpoint of the rope. Additionally, we employ an optimization-based rope-shape planner to compute the desired rope shape. The planner incorporates an adaptive behavior that maximizes grasping capabilities near the litter while minimizing rope tension when farther away. The computed rope shape trajectory is controlled by a shape visual servoing controller, which approximates the rope as a parabola. The complete system is validated in outdoor experiments, demonstrating successful grasping operations. An ablation study highlights how the planner's adaptive mechanism improves the success rate of the operation. Furthermore, real-world tests in a water channel confirm the effectiveness of our system in floating litter collection. These results demonstrate the potential of aerial robots for autonomous litter removal in aquatic environments. In 2019, 353 million tonnes of plastic waste was generated, only 9% of which was recycled, while 22% was mismanaged, with a considerable portion of it ending up in water. The best solutions to plastic pollution include preventing it from entering the environment, e.g., by limiting single-use plastic, and improving plastic management [1].

The Theory of Mind (ToM) refers to an agent's capacity to infer the mental states of other agents. ToM is essential for effective collaboration. To assess ToM in a dynamic, goal-oriented, and collaborative environment, we introduce a novel task, Instruction Inference, in which an agent assists a principal in reaching a goal by interpreting indirect or ambiguous instructions. We present Tomcat, an LLM-based agent, designed to exhibit ToM reasoning in interpreting and responding to the principal's instructions. We implement two variants of Tomcat. One, dubbed Fs-CoT, is based on a small number of examples (i.e., few-shot or Fs) demonstrating the requisite structured reasoning (i.e., chain-of-thought or CoT). One, dubbed CP, relies on commonsense knowledge and information about the problem (i.e., commonsense prompt or CP). We realized both variants of Tomcat on three leading large language models (LLMs), namely, GPT-4o, DeepSeek-R1, and Gemma-3-27B. To evaluate the effectiveness of Tomcat, we conducted a study with 52 human participants in which we provided participants with the same information as the CP variant of Tomcat. We computed intent accuracy, action optimality, and planning optimality to measure the ToM capabilities of Tomcat and our study participants. We found that Tomcat with Fs-CoT, particularly with GPT-4o and DeepSeek-R1, achieves performance comparable to the human participants, underscoring its ToM potential for human-AI collaboration.

Urban streets are essential public spaces that facilitate everyday physical activity and promote health equity. Drawing on Henri Lefebvre's spatial triad, this study proposes a conceptual and methodological framework to quantify street-level exercise deprivation through the dimensions of conceived (planning and structure), perceived (visual and sensory), and lived (practice and experiential) urban spaces. We integrate multi-source spatial data-including street networks, street-view imagery, and social media-using explainable machine learning (SHAP analysis) to classify streets by their dominant deprivation modes, forming a novel typology of spatial inequity. Results highlight significant differences across urban contexts: older city cores predominantly experience infrastructural constraints (conceived space), whereas new development areas suffer from experiential disengagement (lived space). Furthermore, by identifying spatial mismatches between population distribution and exercise intensity, our study reveals localized clusters of latent deprivation. Simulation experiments demonstrate that targeted improvements across spatial dimensions can yield up to 14% increases in exercise supportiveness. This research not only operationalizes Lefebvre's spatial theory at the street scale but also provides actionable insights and intervention guidelines, contributing to the broader goals of spatial justice and urban health equity.

Writing longer prompts for an AI assistant to generate a short story increases psychological ownership, a user's feeling that the writing belongs to them. To encourage users to write longer prompts, we evaluated two interaction techniques that modify the prompt entry interface of chat-based generative AI assistants: pressing and holding the prompt submission button, and continuously moving a slider up and down when submitting a short prompt. A within-subjects experiment investigated the effects of such techniques on prompt length and psychological ownership, and results showed that these techniques increased prompt length and led to higher psychological ownership than baseline techniques. A second experiment further augmented these techniques by showing AI-generated suggestions for how the prompts could be expanded. This further increased prompt length, but did not lead to improvements in psychological ownership. Our results show that simple interface modifications like these can elicit more writing from users and improve psychological ownership.

F ood insecurity is a significant social and public health issue that plagues many urban metropolitan areas around the world. Existing approaches to identifying food insecurity rely primarily on qualitative and quantitative survey data, which is difficult to scale. This project seeks to explore the effectiveness of using street-level images in modeling food insecurity at the census tract level. T o do so, we propose a two-step process of feature extraction and gated attention for image aggregation. W e evaluate the effectiveness of our model by comparing against other model architectures, interpreting our learned weights, and performing a case study. While our model falls slightly short in terms of its predictive power, we believe our approach still has the potential to supplement existing methods of identifying food insecurity for urban planners and policymakers.

Modern social robots can be considered the descendants of steam engines from the First Industrial Revolution (IR 1.0) and industrial robotic arms from the Third Industrial Revolution (IR 3.0). As some time has passed since the introduction of these robots during the Fourth Industrial Revolution (IR 4.0), challenges and issues in their interaction with humans have emerged, leading researchers to conclude that, like any other AI-based technology, these robots must also be human-centered to meet the needs of their users. This chapter aims to introduce humans and their needs in interactions with robots, ranging from short-term, one-on-one interactions (micro-level) to long-term, macro-level needs at the societal scale. Building upon the principles of human-centered AI, this chapter presents, for the first time, a new framework of human needs called the Dual Pyramid. This framework encompasses a comprehensive list of human needs in robot interactions, from the most fundamental, robot effectiveness to macro level requirements, such as the collaboration with robots in achieving the United Nations 17 Sustainable Development Goals.

Major depressive disorder represents one of the most significant global health challenges of the 21st century, affecting millions of people worldwide and creating substantial economic and social burdens. While conventional antidepressant therapies have provided relief for many individuals, their limitations including delayed onset of action, significant side effects, and treatment resistance in a substantial portion of patients have prompted researchers and healthcare providers to explore alternative therapeutic approaches (Kasneci et al.). African traditional medicine, with its rich heritage of plant-based remedies developed over millennia, offers a valuable resource for developing novel antidepressant treatments that may address some of these limitations. This paper examines the integration of large language models with African natural products for depression support, combining traditional knowledge with modern artificial intelligence technology to create accessible, evidence-based mental health support systems. The research presented here encompasses a comprehensive analysis of African medicinal plants with documented antidepressant properties, their pharmacological mechanisms, and the development of an AI-powered support system that leverages DeepSeek's advanced language model capabilities. The system provides evidence-based information about African herbal medicines, their clinical applications, safety considerations, and therapeutic protocols while maintaining scientific rigor and appropriate safety standards. Our findings demonstrate the potential for large language models to serve as bridges between traditional knowledge and modern healthcare, offering personalized, culturally appropriate depression support that honors both traditional wisdom and contemporary medical understanding.