Search

Large Language Model (LLM) image recognition is a powerful tool for extracting data from images, but accuracy depends on providing sufficient cues in the prompt - requiring a domain expert for specialized tasks. We introduce Cue Learning using Evolution for Accurate Recognition (CLEAR), which uses a combination of LLMs and evolutionary computation to generate and optimize cues such that recognition of specialized features in images is improved. It achieves this by auto-generating a novel domain-specific representation and then using it to optimize suitable textual cues with a genetic algorithm. We apply CLEAR to the real-world task of identifying sustainability data from interior and exterior images of buildings. We investigate the effects of using a variable-length representation compared to fixed-length and show how LLM consistency can be improved by refactoring from categorical to real-valued estimates. We show that CLEAR enables higher accuracy compared to expert human recognition and human-authored prompts in every task with error rates improved by up to two orders of magnitude and an ablation study evincing solution concision., Comment: 9 pages plus 2 pages of supplemental material

The eBPF framework enables execution of user-provided code in the Linux kernel. In the last few years, a large ecosystem of cloud services has leveraged eBPF to enhance container security, system observability, and network management. Meanwhile, incessant discoveries of memory safety vulnerabilities have left the systems community with no choice but to disallow unprivileged eBPF programs, which unfortunately limits eBPF use to only privileged users. To improve run-time safety of the framework, we introduce SafeBPF, a general design that isolates eBPF programs from the rest of the kernel to prevent memory safety vulnerabilities from being exploited. We present a pure software implementation using a Software-based Fault Isolation (SFI) approach and a hardware-assisted implementation that leverages ARM's Memory Tagging Extension (MTE). We show that SafeBPF incurs up to 4% overhead on macrobenchmarks while achieving desired security properties., Comment: 15 pages, 9 figures

When data on building features is unavailable, the task of determining how to improve that building in terms of carbon emissions becomes infeasible. We show that from only a set of images, a Large Language Model with appropriate prompt engineering and domain knowledge can successfully estimate a range of building features relevant for sustainability calculations. We compare our novel image-to-data method with a ground truth comprising real building data for 47 apartments and achieve accuracy better than a human performing the same task. We also demonstrate that the method can generate tailored recommendations to the owner on how best to improve their properties and discuss methods to scale the approach., Comment: 6 pages

Consumers wish to choose sustainable accommodation for their travels, and in the case of corporations, may be required to do so. Yet accommodation marketplaces provide no meaningful capability for sustainable choice: typically CO2 estimates are provided that are identical for all accommodation of the same type across an entire country. We propose a decision support system that enables real choice of sustainable accommodation. We develop a data-driven address-specific metric called EcoGrade, which integrates government approved datasets and uses interpolation where data is sparse. We validate the metric on 10,000 UK addresses in 10 cities, showing the match of our interpolations to reality is statistically significant. We show how the metric has been embedded into a decision support system for a global accommodation marketplace and tested by real users over several months with positive user feedback. In the EU, forty percent of final energy consumption is from buildings. We need to encourage all building owners to make their accommodation more efficient. The rental sector is one area where change can occur rapidly, as rented accommodation is renovated frequently. We anticipate our decision support system using EcoGrade will encourage this positive change., Comment: 8 pages

Monolithic operating systems, where all kernel functionality resides in a single, shared address space, are the foundation of most mainstream computer systems. However, a single flaw, even in a non-essential part of the kernel (e.g., device drivers), can cause the entire operating system to fall under an attacker's control. Kernel hardening techniques might prevent certain types of vulnerabilities, but they fail to address a fundamental weakness: the lack of intra-kernel security that safely isolates different parts of the kernel. We survey kernel compartmentalization techniques that define and enforce intra-kernel boundaries and propose a taxonomy that allows the community to compare and discuss future work. We also identify factors that complicate comparisons among compartmentalized systems, suggest new ways to compare future approaches with existing work meaningfully, and discuss emerging research directions., Comment: 24 pages, 7 figures

Conceptual architecture involves a highly creative exploration of novel ideas, often taken from other disciplines as architects consider radical new forms, materials, textures and colors for buildings. While today's generative AI systems can produce remarkable results, they lack the creativity demonstrated for decades by evolutionary algorithms. SCAPE, our proposed tool, combines evolutionary search with generative AI, enabling users to explore creative and good quality designs inspired by their initial input through a simple point and click interface. SCAPE injects randomness into generative AI, and enables memory, making use of the built-in language skills of GPT-4 to vary prompts via text-based mutation and crossover. We demonstrate that compared to DALL-E 3, SCAPE enables a 67% improvement in image novelty, plus improvements in quality and effectiveness of use; we show that in just three iterations SCAPE has a 24% image novelty increase enabling effective exploration, plus optimization of images by users. We use more than 20 independent architects to assess SCAPE, who provide markedly positive feedback., Comment: 8 pages

The sense of touch is an essential ability for skillfully performing a variety of tasks, providing the capacity to search and manipulate objects without relying on visual information. In this paper, we introduce a multi-finger robot system designed to manipulate objects using the sense of touch, without relying on vision. For tasks that mimic daily life, the robot uses its sense of touch to manipulate randomly placed objects in dark. The objective of this study is to enable robots to perform blind manipulation by using tactile sensation to compensate for the information gap caused by the absence of vision, given the presence of prior information. Training the policy through reinforcement learning in simulation and transferring the trained policy to the real environment, we demonstrate that blind manipulation can be applied to robots without vision. In addition, the experiments showcase the importance of tactile sensing in the blind manipulation tasks. Our project page is available at https://lee-kangwon.github.io/dextouch/, Comment: Project page: https://lee-kangwon.github.io/dextouch/; published in IEEE Robotics and Automation Letters (RA-L)

Executing contact-rich manipulation tasks necessitates the fusion of tactile and visual feedback. However, the distinct nature of these modalities poses significant challenges. In this paper, we introduce a system that leverages visual and tactile sensory inputs to enable dexterous in-hand manipulation. Specifically, we propose Robot Synesthesia, a novel point cloud-based tactile representation inspired by human tactile-visual synesthesia. This approach allows for the simultaneous and seamless integration of both sensory inputs, offering richer spatial information and facilitating better reasoning about robot actions. The method, trained in a simulated environment and then deployed to a real robot, is applicable to various in-hand object rotation tasks. Comprehensive ablations are performed on how the integration of vision and touch can improve reinforcement learning and Sim2Real performance. Our project page is available at https://yingyuan0414.github.io/visuotactile/ ., Comment: Project page: https://yingyuan0414.github.io/visuotactile/

For safety reasons, unprivileged users today have only limited ways to customize the kernel through the extended Berkeley Packet Filter (eBPF). This is unfortunate, especially since the eBPF framework itself has seen an increase in scope over the years. We propose SandBPF, a software-based kernel isolation technique that dynamically sandboxes eBPF programs to allow unprivileged users to safely extend the kernel, unleashing eBPF's full potential. Our early proof-of-concept shows that SandBPF can effectively prevent exploits missed by eBPF's native safety mechanism (i.e., static verification) while incurring 0%-10% overhead on web server benchmarks., Comment: 8 pages, 5 figures, to appear in the 1st SIGCOMM Workshop on eBPF and Kernel Extensions

The use of autonomous robots for delivery of goods to customers is an exciting new way to provide a reliable and sustainable service. However, in the real world, autonomous robots still require human supervision for safety reasons. We tackle the realworld problem of optimizing autonomous robot timings to maximize deliveries, while ensuring that there are never too many robots running simultaneously so that they can be monitored safely. We assess the use of a recent hybrid machine-learningoptimization approach COIL (constrained optimization in learned latent space) and compare it with a baseline genetic algorithm for the purposes of exploring variations of this problem. We also investigate new methods for improving the speed and efficiency of COIL. We show that only COIL can find valid solutions where appropriate numbers of robots run simultaneously for all problem variations tested. We also show that when COIL has learned its latent representation, it can optimize 10% faster than the GA, making it a good choice for daily re-optimization of robots where delivery requests for each day are allocated to robots while maintaining safe numbers of robots running at once., Comment: 10 pages including 1 page supplemental

If human societies are so complex, then how can we hope to understand them? Artificial Life gives us one answer. The field of Artificial Life comprises a diverse set of introspective studies that largely ask the same questions, albeit from many different perspectives: Why are we here? Who are we? Why do we behave as we do? Starting with the origins of life provides us with fascinating answers to some of these questions. However, some researchers choose to bring their studies closer to the present day. We are after all, human. It has been a few billion years since our ancestors were self-replicating molecules. Thus, more direct studies of ourselves and our human societies can reveal truths that may lead to practical knowledge. The papers in this special issue bring together scientists who choose to perform this kind of research., Comment: extended version with references

Teams are central to human accomplishment. Over the past half-century, psychologists have identified the Big-Five cross-culturally valid personality variables: Neuroticism, Extraversion, Openness, Conscientiousness, and Agreeableness. The first four have shown consistent relationships with team performance. Agreeableness (being harmonious, altruistic, humble, and cooperative), however, has demonstrated a non-significant and highly variable relationship with team performance. We resolve this inconsistency through computational modelling. An agent-based model (ABM) is used to predict the effects of personality traits on teamwork and a genetic algorithm is then used to explore the limits of the ABM in order to discover which traits correlate with best and worst performing teams for a problem with different levels of uncertainty (noise). New dependencies revealed by the exploration are corroborated by analyzing previously-unseen data from one the largest datasets on team performance to date comprising 3,698 individuals in 593 teams working on more than 5,000 group tasks with and without uncertainty, collected over a 10-year period. Our finding is that the dependency between team performance and Agreeableness is moderated by task uncertainty. Combining evolutionary computation with ABMs in this way provides a new methodology for the scientific investigation of teamwork, making new predictions, and improving our understanding of human behaviors. Our results confirm the potential usefulness of computer modelling for developing theory, as well as shedding light on the future of teams as work environments are becoming increasingly fluid and uncertain., Comment: Final version (open access) as published in journal

Constrained optimization problems can be difficult because their search spaces have properties not conducive to search, e.g., multimodality, discontinuities, or deception. To address such difficulties, considerable research has been performed on creating novel evolutionary algorithms or specialized genetic operators. However, if the representation that defined the search space could be altered such that it only permitted valid solutions that satisfied the constraints, the task of finding the optimal would be made more feasible without any need for specialized optimization algorithms. We propose Constrained Optimization in Latent Space (COIL), which uses a VAE to generate a learned latent representation from a dataset comprising samples from the valid region of the search space according to a constraint, thus enabling the optimizer to find the objective in the new space defined by the learned representation. Preliminary experiments show promise: compared to an identical GA using a standard representation that cannot meet the constraints or find fit solutions, COIL with its learned latent representation can perfectly satisfy different types of constraints while finding high-fitness solutions., Comment: Genetic and Evolutionary Computation Conference Companion (GECCO '22 Companion). ACM, Boston, USA, 8 pages

Despite the wide usage of container-based cloud computing, container auditing for security analysis relies mostly on built-in host audit systems, which often lack the ability to capture high-fidelity container logs. State-of-the-art reference-monitor-based audit techniques greatly improve the quality of audit logs, but their system-wide architecture is too costly to be adapted for individual containers. Moreover, these techniques typically require extensive kernel modifications, making them difficult to deploy in practical settings. In this paper, we present saBPF (secure audit BPF), an extension of the eBPF framework capable of deploying secure system-level audit mechanisms at the container granularity. We demonstrate the practicality of saBPF in Kubernetes by designing an audit framework, an intrusion detection system, and a lightweight access control mechanism. We evaluate saBPF and show that it is comparable in performance and security guarantees to audit systems from the literature that are implemented directly in the kernel., Comment: 15 pages, 7 figures

As a 3D topological insulator, bismuth selenide (Bi2Se3) has potential applications for electrically and optically controllable magnetic and optoelectronic devices. How the carriers interact with lattice is important to understand the coupling with its topological phase. It is essential to measure with a time scale smaller than picoseconds for initial interaction. Here we use an X-ray free-electron laser to perform time-resolved diffraction to study ultrafast carrier-induced lattice contractions and interlayer modulations in Bi2Se3 thin films. The lattice contraction depends on the carrier concentration and is followed by an interlayer expansion accompanied by oscillations. Using density functional theory (DFT) and the Lifshitz model, the initial contraction can be explained by van der Waals force modulation of the confined free carrier layers. Band inversion, related to a topological phase transition, is modulated by the expansion of the interlayer distance. These results provide insight into instantaneous topological phases on ultrafast timescales.

We performed polarized Raman spectroscopy on mechanically exfoliated few-layer MoTe2 samples and observed both 1T' and Td phases at room temperature. Few-layer 1T' and Td MoTe2 exhibited a significant difference especially in interlayer vibration modes, from which the interlayer coupling strengths were extracted using the linear chain model: strong in-plane anisotropy was observed in both phases. Furthermore, temperature-dependent Raman measurements revealed a peculiar phase transition behavior in few-layer 1T' MoTe2. In contrast to bulk 1T' MoTe2 crystals where the phase transition to the Td phase occurs at ~250 K, the temperature-driven phase transition to the Td phase is increasingly suppressed as the thickness is reduced, and the transition and the critical temperature varied dramatically from sample to sample even for the same thickness. Raman spectra of intermediate phases that correspond to neither 1T' nor Td phase with different interlayer vibration modes were observed, which suggests that several metastable phases exist with similar total energies., Comment: 58 pages (32 pages of main text, 26 pages of Supporting Information), to be published in ACS Nano

The behavior of 2-dimensional (2D) van der Waals (vdW) layered magnetic materials in the 2D limit of the few-layer thickness is an important fundamental issue for the understanding of the magnetic ordering in lower dimensions. The antiferromagnetic transition temperature TN of the Heisenberg-type 2D magnetic vdW material MnPS3 was estimated as a function of the number of layers. The antiferromagnetic transition was identified by temperature-dependent Raman spectroscopy, from the broadening of a phonon peak at 155 cm-1, accompanied by an abrupt redshift and an increase of its spectral weight. TN is found to decrease only slightly from ~78 K for bulk to ~ 66 K for 3L. The small reduction of TN in thin MnPS3 approaching the 2D limit implies that the interlayer vdW interaction is playing an important role in stabilizing magnetic ordering in layered magnetic materials.

Gallium selenide (GaSe) is one of layered group-III metal monochalcogenides, which has an indirect bandgap in monolayer and direct bandgap in bulk unlike other conventional transition metal dichalcogenides (TMDs) such as MoX2 and WX2 (X=S and Se). Four polytypes of bulk GaSe, designated as beta-, epsilon-, gamma-, and delta-GaSe, have been reported. Since different polytypes result in different optical and electrical properties even for the same thickness, identifying the polytype is essential in utilizing this material for various optoelectronic applications. We performed polarized Raman measurement on GaSe and found different ultra-low-frequency Raman spectra of inter-layer vibrational modes even for the same thickness due to different stacking sequences of the polytypes. By comparing the ultra-low-frequency Raman spectra with theoretical calculations and high-resolution electron microscopy measurements, we established the correlation between the ultra-low-frequency Raman spectra and the stacking sequences for trilayer GaSe. We further found that the AB-type stacking is more stable than the AA'-type stacking in GaSe.

The evolution of the optical phonons in layered semiconductor alloys SnSe1-xSx is studied as a function of the composition by using polarized Raman spectroscopy with six different excitation wavelengths (784.8, 632.8, 532, 514.5, 488, and 441.6 nm). The polarization dependences of the phonon modes are compared with transmission electron diffraction measurements to determine the crystallographic orientation of the samples. Some of the Raman modes show significant variation in their polarization behavior depending on the excitation wavelengths. It is established that the maximum intensity direction of the Ag2 mode of SnSe1-xSx (0<=x<=1) does not depend on the excitation wavelength and corresponds to the armchair direction. It is additionally found that the lower-frequency Raman modes of Ag1, Ag2 and B3g1 in the alloys show the typical one-mode behavior of optical phonons, whereas the higher-frequency modes of B3g2, Ag3 and Ag4 show two-mode behavior., Comment: X

Polarized Raman spectroscopy on few-layer ReS2 and ReSe2 was carried out to determine the crystallographic orientations. Since monolayer ReX2 (X=S or Se) has a distorted trigonal structure with only an inversion center, there is in-plane anisotropy and the two faces of a monolayer crystal are not equivalent. Since many physical properties vary sensitively depending on the crystallographic orientation, it is important to develop a reliable method to determine the crystal axes of ReX2. By comparing the relative polarization dependences of some representative Raman modes measured with three different excitation laser energies with high-resolution scanning transmission electron microscopy, we established a reliable procedure to determine the all three principal directions of few-layer ReX2 including a way to distinguish the two types of faces: a 2.41-eV laser for ReS2 or a 1.96-eV laser for ReSe2 should be chosen as the excitation source of polarized Raman measurements; then the relative directions of the maximum intensity polarization of the Raman modes at 151 and 212 cm-1 (124 and 161 cm-1) of ReS2 (ReSe2) can be used to determine the face types and the Re-chain direction unambiguously., Comment: 22 pages, 4 figures, supplementary information 9 pages