Search

A neural network-based framework is developed and experimentally demonstrated for the problem of estimating the shape of a soft continuum arm (SCA) from noisy measurements of the pose at a finite number of locations along the length of the arm. The neural network takes as input these measurements and produces as output a finite-dimensional approximation of the strain, which is further used to reconstruct the infinite-dimensional smooth posture. This problem is important for various soft robotic applications. It is challenging due to the flexible aspects that lead to the infinite-dimensional reconstruction problem for the continuous posture and strains. Because of this, past solutions to this problem are computationally intensive. The proposed fast smooth reconstruction method is shown to be five orders of magnitude faster while having comparable accuracy. The framework is evaluated on two testbeds: a simulated octopus muscular arm and a physical BR2 pneumatic soft manipulator., Comment: 6 pages + reference, 5 figures, submitted to ICRA 2025

Let $R\ $be an integral domain and $R^{\#}$ the set of all nonzero nonunits of $R.\ $For every elements $a,b\in R^{\#},$ we define $a\sim b$ if and only if $aR=bR,$ that is, $a$ and $b$ are associated elements. Suppose that $EC(R^{\#})$ is the set of all equivalence classes of $R^{\#}\ $according to $\sim$.$\ $Let $U_{a}=\{[b]\in EC(R^{\#}):b\ $divides $a\}$ for every $a\in R^{\#}.$ Then we prove that the family $\{U_{a}\}_{a\in R^{\#}}$ becomes a basis for a topology on $EC(R^{\#}).\ $This topology is called divisor topology of $R\ $and denoted by $D(R).\ $We investigate the connections between the algebraic properties of $R\ $and the topological properties of$\ D(R)$. In particular, we investigate the seperation axioms on $D(R)$, first and second countability axioms, connectivity and compactness on $D(R)$. We prove that for atomic domains $R,\ $the divisor topology $D(R)\ $is a Baire space. Also, we characterize valution domains $R$ in terms of nested property of $D(R).$ In the last section, we introduce a new topological proof of the infinitude of prime elements in a UFD and integers by using the topology $D(R)$., Comment: Comments welcome

Temporal fluctuations in the superconducting qubit lifetime, $T_1$, bring up additional challenges in building a fault-tolerant quantum computer. While the exact mechanisms remain unclear, $T_1$ fluctuations are generally attributed to the strong coupling between the qubit and a few near-resonant two-level systems (TLSs) that can exchange energy with an assemble of thermally fluctuating two-level fluctuators (TLFs) at low frequencies. Here, we report $T_1$ measurements on the qubits with different geometrical footprints and surface dielectrics as a function of the temperature. By analyzing the noise spectrum of the qubit depolarization rate, $\Gamma_1 = 1/T_1$, we can disentangle the impact of TLSs, non-equilibrium quasiparticles (QPs), and equilibrium (thermally excited) QPs on the variance in $\Gamma_1$. We find that $\Gamma_1$ variances in the qubit with a small footprint are more susceptible to the QP and TLS fluctuations than those in the large-footprint qubits. Furthermore, the QP-induced variances in all qubits are consistent with the theoretical framework of QP diffusion and fluctuation. We suggest these findings can offer valuable insights for future qubit design and engineering optimization., Comment: 6+4 pages, 3+3 figures

In this paper, we associate a new topology to a nonzero unital module $M$ over a commutative $R$, which is called Golomb topology of the $R$-module $M$. Let $M\ $be an\ $R$-module and $B_{M}$ be the family of coprime cosets $\{m+N\}$ where $m\in M$ and $N\ $is a nonzero submodule of $M\ $such that $N+Rm=M$. We prove that if $M\ $is a meet irreducible multiplication module or $M\ $is a meet irreducible finitely generated module in which every maximal submodule is strongly irreducible, then $B_{M}\ $is the basis for a topology on $M\ $which is denoted by $\widetilde{G(M)}.$ In particular, the subspace topology on $M-\{0\}$ is called the Golomb topology of the $R$-module $M\ $and denoted by $G(M)$. We investigate the relations between topological properties of $G(M)\ $and algebraic properties of $M.\ $In particular, we characterize some important classes of modules such as simple modules, Jacobson semisimple modules in terms of Golomb topology., Comment: Comments welcome!

Ion channels orchestrate the communication between cells and their environment. These are special proteins capable of changing their shape to allow ions to pass through membranes in response to stimuli like membrane tension. As the letters are written and exchanged in the form of ionic currents, the energetic cost of this communication is of interest to many. To this end, we introduce the nanoscale thermodynamics of mechanosensitive ion channels, which amounts to defining work and heat for traces obtained during patch-clamp experiments. We also discuss the interplay between ion channel physics and evolution by showing how information-processing capabilities are coupled with the energy landscapes of channels.

In visual Reinforcement Learning (RL), learning from pixel-based observations poses significant challenges on sample efficiency, primarily due to the complexity of extracting informative state representations from high-dimensional data. Previous methods such as contrastive-based approaches have made strides in improving sample efficiency but fall short in modeling the nuanced evolution of states. To address this, we introduce MOOSS, a novel framework that leverages a temporal contrastive objective with the help of graph-based spatial-temporal masking to explicitly model state evolution in visual RL. Specifically, we propose a self-supervised dual-component strategy that integrates (1) a graph construction of pixel-based observations for spatial-temporal masking, coupled with (2) a multi-level contrastive learning mechanism that enriches state representations by emphasizing temporal continuity and change of states. MOOSS advances the understanding of state dynamics by disrupting and learning from spatial-temporal correlations, which facilitates policy learning. Our comprehensive evaluation on multiple continuous and discrete control benchmarks shows that MOOSS outperforms previous state-of-the-art visual RL methods in terms of sample efficiency, demonstrating the effectiveness of our method. Our code is released at https://github.com/jsun57/MOOSS., Comment: WACV 2025

During Russia's invasion of Ukraine in February 2022, Telegram became an essential social media platform for Kremlin-sponsored propaganda dissemination. Over time, Anti-Kremlin Russian opposition channels have also emerged as a prominent voice of dissent against the state-sponsored propaganda. This study examines the dynamics of Anti-Kremlin content on Telegram over seven phases of the invasion, inspired by the concept of breach in narrative theory. A data-driven, computational analysis of emerging topics revealed the Russian economy, combat updates, international politics, and Russian domestic affairs, among others. Using a common set of statistical contrasts by phases of the invasion, a longitudinal analysis of topic prevalence allowed us to examine associations with documented offline events and viewer reactions, suggesting an adaptive breach-oriented communications strategy that maintained viewer interest. Viewer approval of those events that threaten Kremlin control suggests that Telegram levels the online playing field for the opposition, surprising given the Kremlin's suppression of free speech offline.

Central charge is a fundamental quantity in conformal field theories (CFT), and plays a crucial role in determining universality classes of critical points in two-dimensional systems. Despite its significance, the measurement of central charge has remained elusive thus far. In this work, we present the first experimental determination of the central charge using a universal quantum processor. Using a classically optimized variational quantum circuit and employing advanced error mitigation techniques, we successfully prepare ground states of various $1+1D$ quantum spin chain models at their critical point. Leveraging the heavy-hex structure of IBM quantum processors, we are able to implement periodic boundary conditions and mitigate boundary effects. We then extract the central charge from the scaling behavior of the sub-leading term of R{\'{e}}nyi generalizations of classical Shannon entropy, computed for local Pauli measurements in the conformal bases ($\sigma^{z}$ and $\sigma^x$). The experimental results are consistent with the known central charge values for the transverse field Ising (TFI) chain ($c=0.5$) and the XXZ chain ($c=1$), achieving relative errors as low as 5 percent., Comment: 7 + 13 pages, 4 + 11 figures

Neutral atom arrays driven into Rydberg states constitute a promising approach for realizing programmable quantum systems. Enabled by strong interactions associated with Rydberg blockade, they allow for simulation of complex spin models and quantum dynamics. We introduce a new Floquet engineering technique for systems in the blockade regime that provides control over novel forms of interactions and entanglement dynamics in such systems. Our approach is based on time-dependent control of Rydberg laser detuning and leverages perturbations around periodic many-body trajectories as resources for operator spreading. These time-evolved operators are utilized as a basis for engineering interactions in the effective Hamiltonian describing the stroboscopic evolution. As an example, we show how our method can be used to engineer strong spin exchange, consistent with the blockade, in a one-dimensional chain, enabling the exploration of gapless Luttinger liquid phases. In addition, we demonstrate that combining gapless excitations with Rydberg blockade can lead to dynamic generation of large-scale multi-partite entanglement. Experimental feasibility and possible generalizations are discussed., Comment: 5 + 7 pages, 4 + 4 figures

Simulating quantum dynamics of lattice gauge theories (LGTs) is an exciting frontier in quantum science. Programmable quantum simulators based on neutral atom arrays are a promising approach to achieve this goal, since strong Rydberg blockade interactions can be used to naturally create low energy subspaces that can encode local gauge constraints. However, realizing regimes of LGTs where both matter and gauge fields exhibit significant dynamics requires the presence of tunable multi-body interactions such as those associated with ring exchange, which are challenging to realize directly. Here, we develop a method for generating such interactions based on time-periodic driving. Our approach utilizes controlled deviations from time-reversed trajectories, which are accessible in constrained PXP-type models via the application of frequency modulated global pulses. We show that such driving gives rise to a family of effective Hamiltonians with multi-body interactions whose strength is non-perturbative in their respective operator weight. We apply this approach to a two-dimensional U(1) LGT on the Kagome lattice, where we engineer strong six-body magnetic plaquette terms that are tunable relative to the kinetic energy of matter excitations, demonstrating access to previously unexplored dynamical regimes. Potential generalizations and prospects for experimental implementations are discussed., Comment: 12 + 6 pages, 6 + 3 figures

Modern financial institutions rely on data for many operations, including a need to drive efficiency, enhance services and prevent financial crime. Data sharing across an organisation or between institutions can facilitate rapid, evidence-based decision making, including identifying money laundering and fraud. However, data privacy regulations impose restrictions on data sharing. Privacy-enhancing technologies are being increasingly employed to allow organisations to derive shared intelligence while ensuring regulatory compliance. This paper examines the case in which regulatory restrictions mean a party cannot share data on accounts of interest with another (internal or external) party to identify people that hold an account in each dataset. We observe that the names of account holders may be recorded differently in each data set. We introduce a novel privacy-preserving approach for fuzzy name matching across institutions, employing fully homomorphic encryption with locality-sensitive hashing. The efficiency of the approach is enhanced using a clustering mechanism. The practicality and effectiveness of the proposed approach are evaluated using different datasets. Experimental results demonstrate it takes around 100 and 1000 seconds to search 1000 names from 10k and 100k names, respectively. Moreover, the proposed approach exhibits significant improvement in reducing communication overhead by 30-300 times, using clustering., Comment: 13 pages

The thermal conductivity, $\kappa$, of a homogeneous chain of generically-ranged interacting planar rotors, more precisely the inertial $\alpha-XY$ model, is numerically studied with the coupling constant decaying as $r^{-\alpha}$. The conductance ($\sigma\equiv \kappa/L$) is calculated for typical values of $\alpha$, temperature $T$ and lattice size $L$. For large $L$, the results can be collapsed into an universal $q$-stretched exponential form, namely $L^{\delta_{\alpha}} \sigma \propto e_{q_{\alpha}}^{-B_{\alpha}(L^{\gamma_{\alpha}}T)^{\eta_{\alpha}}}$, where $e_q^z\equiv [1+ (1-q)z]^{1/(1-q)}$. The parameters $(\gamma_{\alpha},\delta_{\alpha},B_{\alpha}, \eta_{\alpha})$ are $\alpha$-dependent, and $q_{\alpha}$ is the index of the $q$-stretched exponential. This form is achievable due to the ratio $\eta_{\alpha}/(q-1)$ being almost constant with respect to the lattice size $L$. Two distinct regimes are identified: for $0 \le \alpha < 2$, the Fourier law is violated, whereas for $\alpha\ge 2$, it is satisfied. These findings provide significant insights into heat conduction mechanisms in systems with long-range interactions., Comment: 11 pages, 6 figures

Heavy-tailed distributions are infamously difficult to estimate because their moments tend to infinity as the shape of the tail decay increases. Nevertheless, this study shows the utilization of a modified group of moments for estimating a heavy-tailed distribution. These modified moments are determined from powers of the original distribution. The nth-power distribution is guaranteed to have finite moments up to n-1. Samples from the nth-power distribution are drawn from n-tuple Independent Approximates, which are the set of independent samples grouped into n-tuples and sub-selected to be approximately equal to each other. We show that Independent Approximates are a maximum likelihood estimator for the generalized Pareto and the Student's t distributions, which are members of the family of coupled exponential distributions. We use the first (original), second, and third power distributions to estimate their zeroth (geometric mean), first, and second power-moments respectively. In turn, these power-moments are used to estimate the scale and shape of the distributions. A least absolute deviation criteria is used to select the optimal set of Independent Approximates. Estimates using higher powers and moments are possible though the number of n-tuples that are approximately equal may be limited., Comment: 23 pages, 2 figures

Understanding the collective quantum dynamics of nonequilibrium many-body systems is an outstanding challenge in quantum science. In particular, dynamics driven by quantum fluctuations are important for the formation of exotic quantum phases of matter \cite{altman2023quantum}, fundamental high-energy processes \cite{bauer2023highenergy}, quantum metrology \cite{degen2017sensing, li2023scrambling}, and quantum algorithms \cite{ebadi2022quantum}. Here, we use a programmable quantum simulator based on Rydberg atom arrays to experimentally study collective dynamics across a (2+1)D Ising quantum phase transition. After crossing the quantum critical point, we observe a gradual growth of correlations through coarsening of antiferromagnetically ordered domains~\cite{Samajdar2024}. By deterministically preparing and following the evolution of ordered domains, we show that the coarsening is driven by the curvature of domain boundaries, and find that the dynamics accelerate with proximity to the quantum critical point. We quantitatively explore these phenomena and further observe long-lived oscillations of the order parameter, corresponding to an amplitude (Higgs) mode \cite{pekker2015amplitude}. These observations offer a unique viewpoint into emergent collective dynamics in strongly correlated quantum systems and nonequilibrium quantum processes., Comment: 25 pages, 14 figures

Foundation models (FMs) have revolutionized computer vision, enabling effective learning across different domains. However, their performance under domain shift is yet underexplored. This paper investigates the zero-shot domain adaptation potential of FMs by comparing different backbone architectures and introducing novel domain-aware components that leverage domain related textual embeddings. We propose domain adaptive normalization, termed as Domino, which explicitly leverages domain embeddings during fine-tuning, thus making the model domain aware. Ultimately, Domino enables more robust computer vision models that can adapt effectively to various unseen domains., Comment: Accepted at ICML 2024 Workshop on Foundation Models in the Wild

This work investigates how personality expression and embodiment affect personality perception and learning in educational conversational agents. We extend an existing personality-driven conversational agent framework by integrating LLM-based conversation support tailored to an educational application. We describe a user study built on this system to evaluate two distinct personality styles: high extroversion and agreeableness and low extroversion and agreeableness. For each personality style, we assess three models: (1) a dialogue-only model that conveys personality through dialogue, (2) an animated human model that expresses personality solely through dialogue, and (3) an animated human model that expresses personality through both dialogue and body and facial animations. The results indicate that all models are positively perceived regarding both personality and learning outcomes. Models with high personality traits are perceived as more engaging than those with low personality traits. We provide a comprehensive quantitative and qualitative analysis of perceived personality traits, learning parameters, and user experiences based on participant ratings of the model types and personality styles, as well as users' responses to open-ended questions., Comment: 15 pages, 4 figures, 3 tables

Exoskeleton devices impose kinematic constraints on a user's motion and affect their stability due to added mass but also due to the simplified mechanical design. This paper investigates how these constraints resulting from simplified mechanical designs impact the gait kinematics and stability of users by wearing an ankle exoskeleton with changeable degree of freedom (DoF). The exoskeleton used in this paper allows one, two, or three DoF at the ankle, simulating different levels of mechanical complexity. This effect was evaluated in a pilot study consisting of six participants walking on a straight path. The results show that increasing the exoskeleton DoF results in an improvement of several metrics, including kinematics and gait parameters. The transition from 1 DoF to 2 DoF is shown to have a larger effect than the transition from 2 DoF to 3 DoF for an ankle exoskeleton. However, an exoskeleton with 3 DoF at the ankle featured the best results. Increasing the number of DoF resulted in stability values closer the values when walking without the exoskeleton, despite the added weight of the exoskeleton., Comment: This document is the non-revised version of the paper submitted to IEEE RAS EMBS BioRob 2024. The revised version has been submitted to IEEE Transactions on Medical Robotics and Bionics (IEEE T-MRB)

Excitons in monolayer transition metal dichalcogenides (TMDCs) offer intriguing new possibilities for optoelectronics with no analogues in bulk semiconductors. Yet, intrinsic defects in TMDCs limit the radiative exciton recombination pathways. As a result, the photoluminescence (PL) quantum yield (QY) is limited. Methods like superacid treatment, electrical doping, and plasmonic engineering can inhibit nonradiative decay channels and enhance PL. Here, we show a more straightforward approach that allows PL enhancement. An engineered vertical van der Waals (vdW) metal-monolayer semiconductor junction (MSJ) results in PL enhancement of more than an order of magnitude at technologically relevant excitation powers. Such MSJ can be constructed by vertically stacking metals with suitable work function either above or below a monolayer semiconducting TMDC. Our experiments reveal that the underlying PL enhancement mechanism is to be the suppressed exciton quenching due to the absence of metal-induced gap states and weak Fermi level pinning, thanks to the vdW gapped interface between the metal and the TMDC. Our time-resolved PL measurements further indicate that reduced exciton-exciton annihilation, even at high generation rates, contributes to the observed PL enhancement. The PL intensity is further increased by the proximity of surface plasmons in the metal with the TMDC layer. Our findings shed light on the interaction at vdW metal-semiconductor interfaces and offer a path to improving the optoelectronic performance of semiconducting TMDCs.

The quality of social interaction is crucial for psychological and physiological health. Previous research shows that smartphones can negatively impact face-to-face social interactions. Many HCI studies have addressed this by limiting smartphone use during social interactions. While these studies show a decrease in smartphone use, restrictive approaches have their drawbacks. Users need high levels of self-regulation to follow them, and they may cause unintended effects like withdrawal symptoms. Given the impact of smartphones on social interactions, both positive and negative, new solutions are needed to reduce the negative effects of excessive smartphone use without resorting to restrictive methods. This thesis aims to explore smartphone use behavior in the context of social interactions and relationships using various data collection techniques to understand how this behavior hinders and supports social interactions. We began with in situ observations and focus group sessions. Based on insights from these steps, we developed two research prototypes to improve social interactions without restricting smartphone use. We gathered user feedback, reactions, and concerns about these prototypes through user studies. Finally, we evaluated how these prototypes affected conversation quality in social interactions through an experimental user study. This thesis contributes to the field of digital well-being by offering user insights, design implications, and approaches that can guide the creation of solutions to enhance social interactions in the presence of smartphones., Comment: 157 Pages, 20 figures, 5 Tables, PhD Thesis

We present a vision-based navigation system for under-canopy agricultural robots using semantic keypoints. Autonomous under-canopy navigation is challenging due to the tight spacing between the crop rows ($\sim 0.75$ m), degradation in RTK-GPS accuracy due to multipath error, and noise in LiDAR measurements from the excessive clutter. Our system, CropFollow++, introduces modular and interpretable perception architecture with a learned semantic keypoint representation. We deployed CropFollow++ in multiple under-canopy cover crop planting robots on a large scale (25 km in total) in various field conditions and we discuss the key lessons learned from this., Comment: Accepted to the IEEE ICRA Workshop on Field Robotics 2024

Affordances, a concept rooted in ecological psychology and pioneered by James J. Gibson, have emerged as a fundamental framework for understanding the dynamic relationship between individuals and their environments. Expanding beyond traditional perceptual and cognitive paradigms, affordances represent the inherent effect and action possibilities that objects offer to the agents within a given context. As a theoretical lens, affordances bridge the gap between effect and action, providing a nuanced understanding of the connections between agents' actions on entities and the effect of these actions. In this study, we propose a model that unifies object, action and effect into a single latent representation in a common latent space that is shared between all affordances that we call the affordance space. Using this affordance space, our system is able to generate effect trajectories when action and object are given and is able to generate action trajectories when effect trajectories and objects are given. In the experiments, we showed that our model does not learn the behavior of each object but it learns the affordance relations shared by the objects that we call equivalences. In addition to simulated experiments, we showed that our model can be used for direct imitation in real world cases. We also propose affordances as a base for Cross Embodiment transfer to link the actions of different robots. Finally, we introduce selective loss as a solution that allows valid outputs to be generated for indeterministic model inputs., Comment: Early preprint

Traditional path-planning techniques treat humans as obstacles. This has changed since robots started to enter human environments. On modern robots, social navigation has become an important aspect of navigation systems. To use learning-based techniques to achieve social navigation, a powerful framework that is capable of representing complex functions with as few data as possible is required. In this study, we benefited from recent advances in deep learning at both global and local planning levels to achieve human-aware navigation on a simulated robot. Two distinct deep models are trained with respective objectives: one for global planning and one for local planning. These models are then employed in the simulated robot. In the end, it has been shown that our model can successfully carry out both global and local planning tasks. We have shown that our system could generate paths that successfully reach targets while avoiding obstacles with better performance compared to feed-forward neural networks., Comment: Presented in RO-MAN 2021 Workshop on Robot Behavior Adaptation to Human Social Norms (TSAR)

Trustworthiness is a crucial concept in the context of human-robot interaction. Cooperative robots must be transparent regarding their decision-making process, especially when operating in a human-oriented environment. This paper presents a comprehensive end-to-end framework aimed at fostering trustworthy bidirectional human-robot interaction in collaborative environments for the social navigation of mobile robots. In this framework, the robot communicates verbally while the human guides with gestures. Our method enables a mobile robot to predict the trajectory of people and adjust its route in a socially-aware manner. In case of conflict between human and robot decisions, detected through visual examination, the route is dynamically modified based on human preference while verbal communication is maintained. We present our pipeline, framework design, and preliminary experiments that form the foundation of our proposition., Comment: Accepted by Robot Trust for Symbiotic Societies (RTSS) Workshop at ICRA 2024

Two curves are affinely equivalent if there exists an affine mapping transforming one of them onto the other. Thus, detecting affine equivalence comprises, as important particular cases, similarity, congruence and symmetry detection. In this paper we generalize previous results by the authors to provide an algorithm for computing the affine equivalences between two parametric curves of certain types, in any dimension. In more detail, the algorithm is valid for rational curves, and for parametric curves with non-rational but meromorphic components admitting a rational inverse. Unlike other algorithms already known for rational curves, the algorithm completely avoids polynomial system solving, and uses bivariate factoring, instead, as a fundamental tool. The algorithm has been implemented in the computer algebra system {\tt Maple}, and can be freely downloaded and used.

Socially compliant navigation is an integral part of safety features in Human-Robot Interaction. Traditional approaches to mobile navigation prioritize physical aspects, such as efficiency, but social behaviors gain traction as robots appear more in daily life. Recent techniques to improve the social compliance of navigation often rely on predefined features or reward functions, introducing assumptions about social human behavior. To address this limitation, we propose a novel Learning from Demonstration (LfD) framework for social navigation that exclusively utilizes raw sensory data. Additionally, the proposed system contains mechanisms to consider the future paths of the surrounding pedestrians, acknowledging the temporal aspect of the problem. The final product is expected to reduce the anxiety of people sharing their environment with a mobile robot, helping them trust that the robot is aware of their presence and will not harm them. As the framework is currently being developed, we outline its components, present experimental results, and discuss future work towards realizing this framework., Comment: Accepted for presentation in the workshop of Robot Trust for Symbiotic Societies (RTSS) at ICRA 2024

Today, machine learning tools, particularly artificial neural networks, have become crucial for diverse applications. However, current digital computing tools to train and deploy artificial neural networks often struggle with massive data sizes and high power consumptions. Optical computing provides inherent parallelism and perform fundamental operations with passive optical components. However, most of the optical computing platforms suffer from relatively low accuracies for machine learning tasks due to fixed connections while avoiding complex and sensitive techniques. Here, we demonstrate a genetically programmable yet simple optical neural network to achieve high performances with optical random projection. By genetically programming the orientation of the scattering medium which acts as a random projection kernel and only using 1% of the search space, our novel technique finds an optimum kernel and improves its initial test accuracies 7-22% for various machine learning tasks. Our optical computing method presents a promising approach to achieve high performance in optical neural networks with a simple and scalable design., Comment: Manuscript: 11 pages, 5 Figures. Supplementary material: 8 pages, 6 Figures, 2 Tables

We introduce a novel photonic neural network using photonic crystal fibers, leveraging femtosecond pulse supercontinuum generation for optical computing. Investigating its efficacy across machine learning tasks, we uncover the crucial impact of nonlinear pulse propagation dynamics on network performance. Our findings show that octave-spanning supercontinuum generation results in loss of dataset variety due to many-to-one mapping, and optimal performance requires balancing optical nonlinearity. This study offers guidance for designing energy-efficient and high-performance photonic neural network architectures by explaining the interplay between nonlinear dynamics and optical computing., Comment: 5 pages, 4 figures

Deployments of artificial intelligence in medical diagnostics mandate not just accuracy and efficacy but also trust, emphasizing the need for explainability in machine decisions. The recent trend in automated medical image diagnostics leans towards the deployment of Transformer-based architectures, credited to their impressive capabilities. Since the self-attention feature of transformers contributes towards identifying crucial regions during the classification process, they enhance the trustability of the methods. However, the complex intricacies of these attention mechanisms may fall short of effectively pinpointing the regions of interest directly influencing AI decisions. Our research endeavors to innovate a unique attention block that underscores the correlation between 'regions' rather than 'pixels'. To address this challenge, we introduce an innovative system grounded in prototype learning, featuring an advanced self-attention mechanism that goes beyond conventional ad-hoc visual explanation techniques by offering comprehensible visual insights. A combined quantitative and qualitative methodological approach was used to demonstrate the effectiveness of the proposed method on the large-scale NIH chest X-ray dataset. Experimental results showed that our proposed method offers a promising direction for explainability, which can lead to the development of more trustable systems, which can facilitate easier and rapid adoption of such technology into routine clinics. The code is available at www.github.com/NUBagcilab/r2r_proto.

Human brain and behavior provide a rich venue that can inspire novel control and learning methods for robotics. In an attempt to exemplify such a development by inspiring how humans acquire knowledge and transfer skills among tasks, we introduce a novel multi-task reinforcement learning framework named Episodic Return Progress with Bidirectional Progressive Neural Networks (ERP-BPNN). The proposed ERP-BPNN model (1) learns in a human-like interleaved manner by (2) autonomous task switching based on a novel intrinsic motivation signal and, in contrast to existing methods, (3) allows bidirectional skill transfer among tasks. ERP-BPNN is a general architecture applicable to several multi-task learning settings; in this paper, we present the details of its neural architecture and show its ability to enable effective learning and skill transfer among morphologically different robots in a reaching task. The developed Bidirectional Progressive Neural Network (BPNN) architecture enables bidirectional skill transfer without requiring incremental training and seamlessly integrates with online task arbitration. The task arbitration mechanism developed is based on soft Episodic Return progress (ERP), a novel intrinsic motivation (IM) signal. To evaluate our method, we use quantifiable robotics metrics such as 'expected distance to goal' and 'path straightness' in addition to the usual reward-based measure of episodic return common in reinforcement learning. With simulation experiments, we show that ERP-BPNN achieves faster cumulative convergence and improves performance in all metrics considered among morphologically different robots compared to the baselines., Comment: 9 pages, 5 figures

While the performance of recent learned intra and sequential video compression models exceed that of respective traditional codecs, the performance of learned B-frame compression models generally lag behind traditional B-frame coding. The performance gap is bigger for complex scenes with large motions. This is related to the fact that the distance between the past and future references vary in hierarchical B-frame compression depending on the level of hierarchy, which causes motion range to vary. The inability of a single B-frame compression model to adapt to various motion ranges causes loss of performance. As a remedy, we propose controlling the motion range for flow prediction during inference (to approximately match the range of motions in the training data) by downsampling video frames adaptively according to amount of motion and level of hierarchy in order to compress all B-frames using a single flexible-rate model. We present state-of-the-art BD rate results to demonstrate the superiority of our proposed single-model motion-adaptive inference approach to all existing learned B-frame compression models., Comment: 7 pages, submitted to IEEE ICIP 2024

Learning from Demonstration (LfD) is a widely used technique for skill acquisition in robotics. However, demonstrations of the same skill may exhibit significant variances, or learning systems may attempt to acquire different means of the same skill simultaneously, making it challenging to encode these motions into movement primitives. To address these challenges, we propose an LfD framework, namely the Conditional Neural Expert Processes (CNEP), that learns to assign demonstrations from different modes to distinct expert networks utilizing the inherent information within the latent space to match experts with the encoded representations. CNEP does not require supervision on which mode the trajectories belong to. We compare the performance of CNEP against widely used and powerful LfD methods such as Gaussian Mixture Models, Probabilistic Movement Primitives, and Stable Movement Primitives and show that our method outperforms these baselines on multimodal trajectory datasets. The results reveal enhanced modeling performance for movement primitives, leading to the synthesis of trajectories that more accurately reflect those demonstrated by experts, particularly when the skill demonstrations include intersection points from various trajectories. We evaluated the CNEP model on two real-robot tasks, namely obstacle avoidance and pick-and-place tasks, that require the robot to learn multi-modal motion trajectories and execute the correct primitives given target environment conditions. We also showed that our system is capable of on-the-fly adaptation to environmental changes via an online conditioning mechanism. Lastly, we believe that CNEP offers improved explainability and interpretability by autonomously finding discrete behavior primitives and providing probability values about its expert selection decisions., Comment: This work has been submitted to the IEEE RA-L for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible. Submitted to Robotics and Automation Letters on July 5, 2024

The prevalence of smart devices with the ability to capture moments in multiple modalities has enabled users to experience multimodal information online. However, large Language (LLMs) and Vision models (LVMs) are still limited in capturing holistic meaning with cross-modal semantic relationships. Without explicit, common sense knowledge (e.g., as a knowledge graph), Visual Language Models (VLMs) only learn implicit representations by capturing high-level patterns in vast corpora, missing essential contextual cross-modal cues. In this work, we design a framework to couple explicit commonsense knowledge in the form of knowledge graphs with large VLMs to improve the performance of a downstream task, predicting the effectiveness of multi-modal marketing campaigns. While the marketing application provides a compelling metric for assessing our methods, our approach enables the early detection of likely persuasive multi-modal campaigns and the assessment and augmentation of marketing theory.

Metabolic energy consumption of a powered lower-limb exoskeleton user mainly comes from the upper body effort since the lower body is considered to be passive. However, the upper body effort of the users is largely ignored in the literature when designing motion controllers. In this work, we use deep reinforcement learning to develop a locomotion controller that minimizes ground reaction forces (GRF) on crutches. The rationale for minimizing GRF is to reduce the upper body effort of the user. Accordingly, we design a model and a learning framework for a human-exoskeleton system with crutches. We formulate a reward function to encourage the forward displacement of a human-exoskeleton system while satisfying the predetermined constraints of a physical robot. We evaluate our new framework using Proximal Policy Optimization, a state-of-the-art deep reinforcement learning (RL) method, on the MuJoCo physics simulator with different hyperparameters and network architectures over multiple trials. We empirically show that our learning model can generate joint torques based on the joint angle, velocities, and the GRF on the feet and crutch tips. The resulting exoskeleton model can directly generate joint torques from states in line with the RL framework. Finally, we empirically show that policy trained using our method can generate a gait with a 35% reduction in GRF with respect to the baseline., Comment: 6 pages, 5 Figures

Deep learning models like Transformers and Convolutional Neural Networks (CNNs) have revolutionized various domains, but their parameter-intensive nature hampers deployment in resource-constrained settings. In this paper, we introduce a novel concept utilizes column space and row space of weight matrices, which allows for a substantial reduction in model parameters without compromising performance. Leveraging this paradigm, we achieve parameter-efficient deep learning models.. Our approach applies to both Bottleneck and Attention layers, effectively halving the parameters while incurring only minor performance degradation. Extensive experiments conducted on the ImageNet dataset with ViT and ResNet50 demonstrate the effectiveness of our method, showcasing competitive performance when compared to traditional models. This approach not only addresses the pressing demand for parameter efficient deep learning solutions but also holds great promise for practical deployment in real-world scenarios.

The successful portrayal of personality in digital characters improves communication and immersion. Current research focuses on expressing personality through modifying animations using heuristic rules or data-driven models. While studies suggest motion style highly influences the apparent personality, the role of appearance can be similarly essential. This work analyzes the influence of movement and appearance on the perceived personality of short videos altered by motion transfer networks. We label the personalities in conference video clips with a user study to determine the samples that best represent the Five-Factor model's high, neutral, and low traits. We alter these videos using the Thin-Plate Spline Motion Model, utilizing the selected samples as the source and driving inputs. We follow five different cases to study the influence of motion and appearance on personality perception. Our comparative study reveals that motion and appearance influence different factors: motion strongly affects perceived extraversion, and appearance helps convey agreeableness and neuroticism.

We investigate the Noether symmetries of the Klein--Gordon Lagrangian for Bianchi I spacetime. This is accomplished using a set of new Noether symmetry relations for the Klein--Gordon Lagrangian of Bianchi I spacetime, which reduces to the wave equation in a special case. A detailed Noether symmetry analysis of the Klein--Gordon and the wave equations for Bianchi I spacetime is presented, and the corresponding conservation laws are derived., Comment: 21 pages, no figures, two tables

The RADiCAL Collaboration is conducting R\&D on high performance electromagnetic (EM) calorimetry to address the challenges expected in future collider experiments under conditions of high luminosity and/or high irradiation (FCC-ee, FCC-hh and fixed target and forward physics environments). Under development is a sampling calorimeter approach, known as RADiCAL modules, based on scintillation and wavelength-shifting (WLS) technologies and photosensor, including SiPM and SiPM-like technology. The modules discussed herein consist of alternating layers of very dense (W) absorber and scintillating crystal (LYSO:Ce) plates, assembled to a depth of 25 $X_0$. The scintillation signals produced by the EM showers in the region of EM shower maximum (shower max) are transmitted to SiPM located at the upstream and downstream ends of the modules via quartz capillaries which penetrate the full length of the module. The capillaries contain DSB1 organic plastic WLS filaments positioned within the region of shower max, where the shower energy deposition is greatest, and fused with quartz rod elsewhere. The wavelength shifted light from this spatially-localized shower max region is then propagated to the photosensors. This paper presents the results of an initial measurement of the time resolution of a RADiCAL module over the energy range 25 GeV $\leq$ E $\leq$ 150 GeV using the H2 electron beam at CERN. The data indicate an energy dependence of the time resolution that follows the functional form: $\sigma_{t} = a/\sqrt{E} \oplus b$, where a = 256 $\sqrt{GeV}$~ps and b = 17.5 ps. The time resolution measured at the highest electron beam energy for which data was currently recorded (150 GeV) was found to be $\sigma_{t}$ = 27 ps.

Discovering the symbols and rules that can be used in long-horizon planning from a robot's unsupervised exploration of its environment and continuous sensorimotor experience is a challenging task. The previous studies proposed learning symbols from single or paired object interactions and planning with these symbols. In this work, we propose a system that learns rules with discovered object and relational symbols that encode an arbitrary number of objects and the relations between them, converts those rules to Planning Domain Description Language (PDDL), and generates plans that involve affordances of the arbitrary number of objects to achieve tasks. We validated our system with box-shaped objects in different sizes and showed that the system can develop a symbolic knowledge of pick-up, carry, and place operations, taking into account object compounds in different configurations, such as boxes would be carried together with a larger box that they are placed on. We also compared our method with the state-of-the-art methods and showed that planning with the operators defined over relational symbols gives better planning performance compared to the baselines.