Search

As Machine Learning (ML) makes its way into aviation, ML enabled systems including low criticality systems require a reliable certification process to ensure safety and performance. Traditional standards, like DO 178C, which are used for critical software in aviation, do not fully cover the unique aspects of ML. This paper proposes a semi automated certification approach, specifically for low criticality ML systems, focusing on data and model validation, resilience assessment, and usability assurance while integrating manual and automated processes. Key aspects include structured classification to guide certification rigor on system attributes, an Assurance Profile that consolidates evaluation outcomes into a confidence measure the ML component, and methodologies for integrating human oversight into certification activities. Through a case study with a YOLOv8 based object detection system designed to classify military and civilian vehicles in real time for reconnaissance and surveillance aircraft, we show how this approach supports the certification of ML systems in low criticality airborne applications., Comment: Accepted at CAIN (International Conference of AI Engineering) 2025

The widespread adoption of machine learning (ML) has brought forth diverse models with varying architectures, and data requirements, introducing new challenges in integrating these systems into real-world applications. Traditional solutions often struggle to manage the complexities of connecting heterogeneous models, especially when dealing with varied technical specifications. These limitations are amplified in large-scale, collaborative projects where stakeholders contribute models with different technical specifications. To address these challenges, we developed LoCoML, a low-code framework designed to simplify the integration of diverse ML models within the context of the \textit{Bhashini Project} - a large-scale initiative aimed at integrating AI-driven language technologies such as automatic speech recognition, machine translation, text-to-speech, and optical character recognition to support seamless communication across more than 20 languages. Initial evaluations show that LoCoML adds only a small amount of computational load, making it efficient and effective for large-scale ML integration. Our practical insights show that a low-code approach can be a practical solution for connecting multiple ML models in a collaborative environment., Comment: The paper has been accepted for presentation at the 4th International Conference on AI Engineering (CAIN) 2025 co-located with 47th IEEE/ACM International Conference on Software Engineering (ICSE) 2025

Restless Multi-Armed Bandits (RMABs) have been successfully applied to resource allocation problems in a variety of settings, including public health. With the rapid development of powerful large language models (LLMs), they are increasingly used to design reward functions to better match human preferences. Recent work has shown that LLMs can be used to tailor automated allocation decisions to community needs using language prompts. However, this has been studied primarily for English prompts and with a focus on task performance only. This can be an issue since grassroots workers, especially in developing countries like India, prefer to work in local languages, some of which are low-resource. Further, given the nature of the problem, biases along population groups unintended by the user are also undesirable. In this work, we study the effects on both task performance and fairness when the DLM algorithm, a recent work on using LLMs to design reward functions for RMABs, is prompted with non-English language commands. Specifically, we run the model on a synthetic environment for various prompts translated into multiple languages. The prompts themselves vary in complexity. Our results show that the LLM-proposed reward functions are significantly better when prompted in English compared to other languages. We also find that the exact phrasing of the prompt impacts task performance. Further, as prompt complexity increases, performance worsens for all languages; however, it is more robust with English prompts than with lower-resource languages. On the fairness side, we find that low-resource languages and more complex prompts are both highly likely to create unfairness along unintended dimensions., Comment: Accepted at the AAAI-2025 Deployable AI Workshop

Optical components and circuits that deal with multiple signal generation and processing are quintessential for artificial neural networks. Herein, we present a proof-of-concept four-layered organic optical artificial neural network (ANN)-like architecture, constructed from flexible organic crystals of (E)-1-(((5-methylpyridin-2-yl)imino)methyl)naphthalene-2-ol (MPyIN), employing an atomic force microscopy cantilever tip-based mechanical micromanipulation technique. Initially, the strategic selection of four MPyIN crystal active waveguides of varying lengths, mechanically bending them into serpentine-like forms, followed by their hierarchical integration, creates neuron-like, four-layered interconnected optical waveguides with six optical synapses. The synapses in the ANN-like architecture enable parallel transmissions of passive optical signals via evanescent coupling across multiple paths through various layers of the serpentine-shaped optical waveguides. Notably, the feedforward mechanism allows the synapses to multiply and split the optical signal generated at any input into four diverging signals with varying magnitudes. Here, certain outputs deliver a mixed signal (passive and active) due to diverging and converging optical transmission paths. This hierarchical, ANN-like tiny architecture paves the way for the development of smart optical neural networks utilizing multiple emissive and phase-changing organic crystals.

Swarmalators are phase oscillators capable of simultaneous swarming and synchronization, making them potential candidates for replicating complex dynamical states. In this work, we explore the effects of a frustration parameter in the phase interaction functions of a two-dimensional swarmalator model inspired by the solvable Sakaguchi-swarmalators that move in a one-dimensional ring. The impact of the frustration parameter in these models has been a topic of great interest. Real-world coupled systems with frustration exhibit remarkable collective dynamical states, underscoring the relevance of this study. The frustration parameter induces various states exhibiting non-stationarity, chimeric clustering, and global translational motion, where swarmalators move spontaneously in two-dimensional space. We investigate the characteristics of these states and their responses to changes in the frustration parameter. Notably, the emergence of chimeric states suggests the crucial role of non-stationarity in phase interactions for spontaneous population clustering. Additionally, we examine how phase non-stationarity influences the spatial positions of swarmalators and provide a classification of these states based on different order parameters., Comment: 10 pages, 14 figures

How effective is peer-reviewing in identifying important papers? We treat this question as a forecasting task. Can we predict which papers will be highly cited in the future based on venue and "early returns" (citations soon after publication)? We show early returns are more predictive than venue. Finally, we end with constructive suggestions to address scaling challenges: (a) too many submissions and (b) too few qualified reviewers., Comment: The 31st International Conference on Computational Linguistics (COLING 2025)

With the rise of marine exploration, underwater imaging has gained significant attention as a research topic. Underwater video enhancement has become crucial for real-time computer vision tasks in marine exploration. However, most existing methods focus on enhancing individual frames and neglect video temporal dynamics, leading to visually poor enhancements. Furthermore, the lack of ground-truth references limits the use of abundant available underwater video data in many applications. To address these issues, we propose a two-stage framework for enhancing underwater videos. The first stage uses a denoising diffusion probabilistic model to learn a generative prior from unlabeled data, capturing robust and descriptive feature representations. In the second stage, this prior is incorporated into a physics-based image formulation for spatial enhancement, while also enforcing temporal consistency between video frames. Our method enables real-time and computationally-efficient processing of high-resolution underwater videos at lower resolutions, and offers efficient enhancement in the presence of diverse water-types. Extensive experiments on four datasets show that our approach generalizes well and outperforms existing enhancement methods. Our code is available at github.com/suhas-srinath/undive., Comment: Accepted to IEEE/CVF WACV 2025

This research investigates the dynamics of a forced Lienard oscillator featuring asymmetric potential wells. We provide compelling evidence of extreme events (EE) in the system by manipulating the height of the potential well. In the case of a symmetric well, the system exhibits chaotic behavior, with the trajectory irregularly traversing between the two wells, resulting in frequent large oscillations under specific parameter values. However, the introduction of asymmetry in the potential wells induces a noteworthy transformation. The frequency of jumping between wells is significantly diminished. In essence, the system trajectory displays rare yet recurrent hops to the adjacent well, which we identify as EE. The intricate dynamical behavior observed in the system is elucidated through bifurcation diagrams and Lyapunov exponents. The emergence of EE in the system, governed by various parameters, is characterized using the threshold height, probability distribution function, and inter-event intervals. We illustrate the regions of EE using phase diagram plots and demonstrate the control of EE by incorporating a damping term into the system., Comment: 13 Pages

Message aggregation is often used with a goal to reduce communication cost in HPC applications. The difference in the order of overhead of sending a message and cost of per byte transferred motivates the need for message aggregation, for several irregular fine-grained messaging applications like graph algorithms and parallel discrete event simulation (PDES). While message aggregation is frequently utilized in "MPI-everywhere" model, to coalesce messages between processes mapped to cores, such aggregation across threads in a process, say in MPI+X models or Charm++ SMP (Shared Memory Parallelism) mode, is often avoided. Within-process coalescing is likely to require synchronization across threads and lead to performance issues from contention. However, as a result, SMP-unaware aggregation mechanisms may not fully utilize aggregation opportunities available to applications in SMP mode. Additionally, while the benefit of message aggregation is often analyzed in terms of reducing the overhead, specifically the per message cost, we also analyze different schemes that can aid in reducing the message latency, ie. the time from when a message is sent to the time when it is received. Message latency can affect several applications like PDES with speculative execution where reducing message latency could result in fewer rollbacks. To address these challenges, in our work, we demonstrate the effectiveness of shared memory-aware message aggregation schemes for a range of proxy applications with respect to messaging overhead and latency., Comment: A shorter version of this paper has been accepted at IA^3 workshop at SC24

Anxiety is a common mental health condition characterised by excessive worry, fear and apprehension about everyday situations. Even with significant progress over the past few years, predicting anxiety from electroencephalographic (EEG) signals, specifically using error-related negativity (ERN), still remains challenging. Following the PRISMA protocol, this paper systematically reviews 54 research papers on using EEG and ERN markers for anxiety detection published in the last 10 years (2013 -- 2023). Our analysis highlights the wide usage of traditional machine learning, such as support vector machines and random forests, as well as deep learning models, such as convolutional neural networks and recurrent neural networks across different data types. Our analysis reveals that the development of a robust and generic anxiety prediction method still needs to address real-world challenges, such as task-specific setup, feature selection and computational modelling. We conclude this review by offering potential future direction for non-invasive, objective anxiety diagnostics, deployed across diverse populations and anxiety sub-types.

We introduce $\texttt{ReMOVE}$, a novel reference-free metric for assessing object erasure efficacy in diffusion-based image editing models post-generation. Unlike existing measures such as LPIPS and CLIPScore, $\texttt{ReMOVE}$ addresses the challenge of evaluating inpainting without a reference image, common in practical scenarios. It effectively distinguishes between object removal and replacement. This is a key issue in diffusion models due to stochastic nature of image generation. Traditional metrics fail to align with the intuitive definition of inpainting, which aims for (1) seamless object removal within masked regions (2) while preserving the background continuity. $\texttt{ReMOVE}$ not only correlates with state-of-the-art metrics and aligns with human perception but also captures the nuanced aspects of the inpainting process, providing a finer-grained evaluation of the generated outputs., Comment: Accepted at The First Workshop on the Evaluation of Generative Foundation Models (EvGENFM) at CVPR 2024

We argue that Content-based filtering (CBF) and Graph-based methods (GB) complement one another in Academic Search recommendations. The scientific literature can be viewed as a conversation between authors and the audience. CBF uses abstracts to infer authors' positions, and GB uses citations to infer responses from the audience. In this paper, we describe nine differences between CBF and GB, as well as synergistic opportunities for hybrid combinations. Two embeddings will be used to illustrate these opportunities: (1) Specter, a CBF method based on BERT-like deepnet encodings of abstracts, and (2) ProNE, a GB method based on spectral clustering of more than 200M papers and 2B citations from Semantic Scholar.

Cascading failures represent a fundamental threat to the integrity of complex systems, often precipitating a comprehensive collapse across diverse infrastructures and financial networks. This research articulates a robust and pragmatic approach designed to attenuate the risk of such failures within complex networks, emphasizing the pivotal role of local network topology. The core of our strategy is an innovative algorithm that systematically identifies a subset of critical nodes within the network, a subset whose relative size is substantial in the context of the network's entirety. Enhancing this algorithm, we employ a graph coloring heuristic to precisely isolate nodes of paramount importance, thereby minimizing the subset size while maximizing strategic value. Securing these nodes significantly bolsters network resilience against cascading failures. The method proposed to identify critical nodes and experimental results show that the proposed technique outperforms other typical techniques in identifying critical nodes. We substantiate the superiority of our approach through comparative analyses with existing mitigation strategies and evaluate its performance across various network configurations and failure scenarios. Empirical validation is provided via the application of our method to real-world networks, confirming its potential as a strategic tool in enhancing network robustness.

Field robotics applications, such as search and rescue, involve robots operating in large, unknown areas. These environments present unique challenges that compound the difficulties faced by a robot operator. The use of multi-robot teams, assisted by carefully designed autonomy, help reduce operator workload and allow the operator to effectively coordinate robot capabilities. In this work, we present a system architecture designed to optimize both robot autonomy and the operator experience in multi-robot scenarios. Drawing on lessons learned from our team's participation in the DARPA SubT Challenge, our architecture emphasizes modularity and interoperability. We empower the operator by allowing for adjustable levels of autonomy ("sliding mode autonomy"). We enhance the operator experience by using intuitive, adaptive interfaces that suggest context-aware actions to simplify control. Finally, we describe how the proposed architecture enables streamlined development of new capabilities for effective deployment of robot autonomy in the field., Comment: Accepted to the IEEE ICRA Workshop on Field Robotics 2024

In this position paper, we explore the power of storytelling and its connection to place through the use of Augmented Reality (AR) technology, particularly within the context of Th\'amien Ohlone history on the Santa Clara University campus. To do this, we utilized SLAM and 8th Wall to create virtual, location-based experiences that geolocate tribal stories at present-day sites, showcase the living culture of the Th\'amien Ohlone tribe, and advocate for physical markers that could exist to recognize their story. When doing so, we made sure to select locations that added to the story each stop tells to serve as our anchors. Our research then investigates both the social and technical considerations involved in selecting anchors for AR experiences, using the Th\'amien Ohlone AR Tour as a case study., Comment: Presented at CHI 2024 (arXiv:2404.05889)

We consider a modified damped version of H\'enon-Heiles system and investigate its integrability. By extending the Painlev\'e analysis of ordinary differential equations we find that the modified H\'enon-Heiles system possesses the Painlev\'e property for three distinct parametric restrictions. For each of the identified cases, we construct two independent integrals of motion using the well known Prelle-Singer method. We then derive a set of nontrivial non-point symmetries for each of the identified integrable cases of the modified H\'enon-Heiles system. We infer that the modified H\'enon-Heiles system is integrable for three distinct parametric restrictions. Exact solutions are given explicitly for two integrable cases., Comment: Accepted for publication in Journal of Mathematical Physics

In this study, we leverage SCADA data from diverse wind turbines to predict power output, employing advanced time series methods, specifically Functional Neural Networks (FNN) and Long Short-Term Memory (LSTM) networks. A key innovation lies in the ensemble of FNN and LSTM models, capitalizing on their collective learning. This ensemble approach outperforms individual models, ensuring stable and accurate power output predictions. Additionally, machine learning techniques are applied to detect wind turbine performance deterioration, enabling proactive maintenance strategies and health assessment. Crucially, our analysis reveals the uniqueness of each wind turbine, necessitating tailored models for optimal predictions. These insight underscores the importance of providing automatized customization for different turbines to keep human modeling effort low. Importantly, the methodologies developed in this analysis are not limited to wind turbines; they can be extended to predict and optimize performance in various machinery, highlighting the versatility and applicability of our research across diverse industrial contexts., Comment: 19 Pages, 17 Figures, 3 Tables, Submitted at Applied Sciences (MDPI)

Recent developments in the field of diffusion models have demonstrated an exceptional capacity to generate high-quality prompt-conditioned image edits. Nevertheless, previous approaches have primarily relied on textual prompts for image editing, which tend to be less effective when making precise edits to specific objects or fine-grained regions within a scene containing single/multiple objects. We introduce a novel framework for zero-shot localized multi-object editing through a multi-diffusion process to overcome this challenge. This framework empowers users to perform various operations on objects within an image, such as adding, replacing, or editing $\textbf{many}$ objects in a complex scene $\textbf{in one pass}$. Our approach leverages foreground masks and corresponding simple text prompts that exert localized influences on the target regions resulting in high-fidelity image editing. A combination of cross-attention and background preservation losses within the latent space ensures that the characteristics of the object being edited are preserved while simultaneously achieving a high-quality, seamless reconstruction of the background with fewer artifacts compared to the current methods. We also curate and release a dataset dedicated to multi-object editing, named $\texttt{LoMOE}$-Bench. Our experiments against existing state-of-the-art methods demonstrate the improved effectiveness of our approach in terms of both image editing quality and inference speed., Comment: 18 pages