Search

Vision-language models have emerged as a powerful tool for previously challenging multi-modal classification problem in the medical domain. This development has led to the exploration of automated image description generation for multi-modal clinical scans, particularly for radiology report generation. Existing research has focused on clinical descriptions for specific modalities or body regions, leaving a gap for a model providing entire-body multi-modal descriptions. In this paper, we address this gap by automating the generation of standardized body station(s) and list of organ(s) across the whole body in multi-modal MR and CT radiological images. Leveraging the versatility of the Contrastive Language-Image Pre-training (CLIP), we refine and augment the existing approach through multiple experiments, including baseline model fine-tuning, adding station(s) as a superset for better correlation between organs, along with image and language augmentations. Our proposed approach demonstrates 47.6% performance improvement over baseline PubMedCLIP., Comment: $\copyright$ 2024 IEEE. Accepted in 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) 2024

In this paper, a new under-actuated Bi-Quadcopter Unmanned Aerial Vehicle is introduced. The proposed drone configuration can be controlled similar to a Bicopter. The dynamics of the proposed Bi-Quadcopter is developed using the Newton-Euler approach. Using the force decomposition technique, a mapping between the control wrench and actuator inputs is developed. A nonlinear position control is applied for the Bi-Quadcopter using the quaternion-based cascaded attitude controller. The performance of the proposed UAV with the control algorithm is verified through simulations. Finally, the actuator failure scenarios were analyzed., Comment: This paper is accepted for publication in the 2024 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS 2024), Shah Alam, Malaysia

In reinforcement learning, it is often difficult to automate high-dimensional, rapid decision-making in dynamic environments, especially when domains require real-time online interaction and adaptive strategies such as web-based games. This work proposes a state-of-the-art Flexible Deep Q-Network (FDQN) framework that can address this challenge with a selfadaptive approach that is processing high-dimensional sensory data in realtime using a CNN and dynamically adapting the model architecture to varying action spaces of different gaming environments and outperforming previous baseline models in various Atari games and the Chrome Dino game as baselines. Using the epsilon-greedy policy, it effectively balances the new learning and exploitation for improved performance, and it has been designed with a modular structure that it can be easily adapted to other HTML-based games without touching the core part of the framework. It is demonstrated that the FDQN framework can successfully solve a well-defined task in a laboratory condition, but more importantly it also discusses potential applications to more challenging real-world cases and serve as the starting point for future further exploration into automated game play and beyond.

Large language models (LLMs) have recently emerged as powerful tools for tackling many language-processing tasks. Despite their success, training and fine-tuning these models is still far too computationally and memory intensive. In this paper, we identify and characterise the important components needed for effective model convergence using gradient descent. In doing so we find that the intermediate activations used to implement backpropagation can be excessively compressed without incurring any degradation in performance. This result leads us to a cheap and memory-efficient algorithm for both fine-tuning and pre-training LLMs. The proposed algorithm simply divides the tokens up into smaller sub-tokens before projecting them onto a fixed 1-dimensional subspace during the forward pass. These features are then coarsely reconstructed during the backward pass to implement the update rules. We confirm the effectiveness of our algorithm as being complimentary to many state-of-the-art PEFT methods on the VTAB-1k fine-tuning benchmark. Furthermore, we outperform QLoRA for fine-tuning LLaMA and show competitive performance against other memory-efficient pre-training methods on the large-scale C4 dataset., Comment: NeurIPS 2024. Code available at https://github.com/roymiles/VeLoRA

CAPTCHAs are commonly used to distinguish between human and bot users on the web. However, despite having various types of CAPTCHAs, there are still concerns about their security and usability. To address these concerns, we surveyed over 250 participants from a university campus and Amazon Mechanical Turk. Our goal was to gather user perceptions regarding the security and usability of current CAPTCHA implementations. After analyzing the data using statistical and thematic methods, we found that users struggle to navigate current CAPTCHA challenges due to increasing difficulty levels. As a result, they experience frustration, which negatively impacts their user experience. Additionally, participants expressed concerns about the reliability and security of these systems. Our findings can offer valuable insights for creating more secure and user-friendly CAPTCHA technologies.

The study of Maya hieroglyphic writing unlocks the rich history of cultural and societal knowledge embedded within this ancient civilization's visual narrative. Artificial Intelligence (AI) offers a novel lens through which we can translate these inscriptions, with the potential to allow non-specialists access to reading these texts and to aid in the decipherment of those hieroglyphs which continue to elude comprehensive interpretation. Toward this, we leverage a foundational model to segment Maya hieroglyphs from an open-source digital library dedicated to Maya artifacts. Despite the initial promise of publicly available foundational segmentation models, their effectiveness in accurately segmenting Maya hieroglyphs was initially limited. Addressing this challenge, our study involved the meticulous curation of image and label pairs with the assistance of experts in Maya art and history, enabling the fine-tuning of these foundational models. This process significantly enhanced model performance, illustrating the potential of fine-tuning approaches and the value of our expanding dataset. We plan to open-source this dataset for encouraging future research, and eventually to help make the hieroglyphic texts legible to a broader community, particularly for Maya heritage community members.

Feature transformation aims to reconstruct the feature space of raw features to enhance the performance of downstream models. However, the exponential growth in the combinations of features and operations poses a challenge, making it difficult for existing methods to efficiently explore a wide space. Additionally, their optimization is solely driven by the accuracy of downstream models in specific domains, neglecting the acquisition of general feature knowledge. To fill this research gap, we propose an evolutionary LLM framework for automated feature transformation. This framework consists of two parts: 1) constructing a multi-population database through an RL data collector while utilizing evolutionary algorithm strategies for database maintenance, and 2) utilizing the ability of Large Language Model (LLM) in sequence understanding, we employ few-shot prompts to guide LLM in generating superior samples based on feature transformation sequence distinction. Leveraging the multi-population database initially provides a wide search scope to discover excellent populations. Through culling and evolution, the high-quality populations are afforded greater opportunities, thereby furthering the pursuit of optimal individuals. Through the integration of LLMs with evolutionary algorithms, we achieve efficient exploration within a vast space, while harnessing feature knowledge to propel optimization, thus realizing a more adaptable search paradigm. Finally, we empirically demonstrate the effectiveness and generality of our proposed method.

Large Vision-Language Models (LVLMs) often produce responses that misalign with factual information, a phenomenon known as hallucinations. While hallucinations are well-studied, the exact causes behind them remain underexplored. In this paper, we first investigate the root causes of hallucinations in LVLMs. Our findings reveal that existing mitigation techniques primarily reduce hallucinations for visual recognition prompts-those that require simple descriptions of visual elements-but fail for cognitive prompts that demand deliberate reasoning. We identify the core issue as a lack of true visual perception in LVLMs: although they can accurately recognize visual elements, they struggle to fully interpret these elements in the context of the input prompt and effectively link this recognition to their internal knowledge, which is critical for reasoning. To address this gap, we introduce Visual Description Grounded Decoding (VDGD), a simple, robust, and training-free method designed to enhance visual perception and improve reasoning capabilities in LVLMs. VDGD works by first generating a detailed description of the image and appending it as a prefix to the instruction. During response generation, tokens are sampled based on their KL divergence to the description, favoring candidates with lower divergence. Experimental results on multiple visual reasoning benchmarks and LVLMs demonstrate that VDGD consistently outperforms existing baselines 2% - 33%. Finally, we introduce VaLLu, a benchmark designed for comprehensive evaluation of the cognitive capabilities of LVLMs., Comment: Preprint. Under review

Ranking is a fundamental and popular problem in search. However, existing ranking algorithms usually restrict the granularity of ranking to full passages or require a specific dense index for each desired level of granularity. Such lack of flexibility in granularity negatively affects many applications that can benefit from more granular ranking, such as sentence-level ranking for open-domain question-answering, or proposition-level ranking for attribution. In this work, we introduce the idea of any-granularity ranking, which leverages multi-vector embeddings to rank at varying levels of granularity while maintaining encoding at a single (coarser) level of granularity. We propose a multi-granular contrastive loss for training multi-vector approaches, and validate its utility with both sentences and propositions as ranking units. Finally, we demonstrate the application of proposition-level ranking to post-hoc citation addition in retrieval-augmented generation, surpassing the performance of prompt-driven citation generation.

Many interventions in causal inference can be represented as transformations. We identify a local symmetry property satisfied by a large class of causal models under such interventions. Where present, this symmetry can be characterized by a type of map called a cocycle, an object that is central to dynamical systems theory. We show that such cocycles exist under general conditions and are sufficient to identify interventional and counterfactual distributions. We use these results to derive cocycle-based estimators for causal estimands and show they achieve semiparametric efficiency under typical conditions. Since (infinitely) many distributions can share the same cocycle, these estimators make causal inference robust to mis-specification by sidestepping superfluous modelling assumptions. We demonstrate both robustness and state-of-the-art performance in several simulations, and apply our method to estimate the effects of 401(k) pension plan eligibility on asset accumulation using a real dataset., Comment: Amended a typo on p.2

We present Keck Cosmic Web Imager IFU observations around extended Ly$\alpha$ halos of 27 typical star-forming galaxies with redshifts $2.0 < z < 3.2$ drawn from the MOSFIRE Deep Evolution Field survey. We examine the average Ly$\alpha$ surface-brightness profiles in bins of star-formation rate (SFR), stellar mass ($M_*$), age, stellar continuum reddening, SFR surface density ($\rm \Sigma_{SFR}$), and $\rm \Sigma_{SFR}$ normalized by stellar mass ($\rm \Sigma_{sSFR}$). The scale lengths of the halos correlate with stellar mass, age, and stellar continuum reddening; and anti-correlate with star-formation rate, $\rm \Sigma_{SFR}$, and $\rm \Sigma_{sSFR}$. These results are consistent with a scenario in which the down-the-barrel fraction of Ly$\alpha$ emission is modulated by the low-column-density channels in the ISM, and that the neutral gas covering fraction is related to the physical properties of the galaxies. Specifically, we find that this covering fraction increases with stellar mass, age, and $E(B-V)$; and decreases with SFR, $\rm \Sigma_{SFR}$ and $\rm \Sigma_{sSFR}$. We also find that the resonantly scattered Ly$\alpha$ emission suffers greater attenuation than the (non-resonant) stellar continuum emission, and that the difference in attenuation increases with stellar mass, age, and stellar continuum reddening, and decreases with $\rm \Sigma_{sSFR}$. These results imply that more reddened galaxies have more dust in their CGM., Comment: 12 pages, 7 figures, 2 tables, submitted to ApJ

Characters are an important aspect of any storyline and identifying and including them in descriptions is necessary for story understanding. While previous work has largely ignored identity and generated captions with someone (anonymized names), recent work formulates id-aware captioning as a fill-in-the-blanks (FITB) task, where, given a caption with blanks, the goal is to predict person id labels. However, to predict captions with ids, a two-stage approach is required: first predict captions with someone, then fill in identities. In this work, we present a new single stage approach that can seamlessly switch between id-aware caption generation or FITB when given a caption with blanks. Our model, Movie-Identity Captioner (MICap), uses a shared auto-regressive decoder that benefits from training with FITB and full-caption generation objectives, while the encoder can benefit from or disregard captions with blanks as input. Another challenge with id-aware captioning is the lack of a metric to capture subtle differences between person ids. To this end, we introduce iSPICE, a caption evaluation metric that focuses on identity tuples created through intermediate scene graphs. We evaluate MICap on Large-Scale Movie Description Challenge (LSMDC), where we show a 4.2% improvement in FITB accuracy, and a 1-2% bump in classic captioning metrics., Comment: CVPR 2024, Project Page: https://katha-ai.github.io/projects/micap/

This work presents an efficient approach for accelerating multilevel Markov Chain Monte Carlo (MCMC) sampling for large-scale problems using low-fidelity machine learning models. While conventional techniques for large-scale Bayesian inference often substitute computationally expensive high-fidelity models with machine learning models, thereby introducing approximation errors, our approach offers a computationally efficient alternative by augmenting high-fidelity models with low-fidelity ones within a hierarchical framework. The multilevel approach utilizes the low-fidelity machine learning model (MLM) for inexpensive evaluation of proposed samples thereby improving the acceptance of samples by the high-fidelity model. The hierarchy in our multilevel algorithm is derived from geometric multigrid hierarchy. We utilize an MLM to acclerate the coarse level sampling. Training machine learning model for the coarsest level significantly reduces the computational cost associated with generating training data and training the model. We present an MCMC algorithm to accelerate the coarsest level sampling using MLM and account for the approximation error introduced. We provide theoretical proofs of detailed balance and demonstrate that our multilevel approach constitutes a consistent MCMC algorithm. Additionally, we derive conditions on the accuracy of the machine learning model to facilitate more efficient hierarchical sampling. Our technique is demonstrated on a standard benchmark inference problem in groundwater flow, where we estimate the probability density of a quantity of interest using a four-level MCMC algorithm. Our proposed algorithm accelerates multilevel sampling by a factor of two while achieving similar accuracy compared to sampling using the standard multilevel algorithm.

Repulsive short-range interactions can induce p-wave attraction between fermions in dense matter and lead to Cooper pairing at the Fermi surface. We investigate this phenomenon, well-known as the Kohn-Luttinger effect in condensed matter physics, in dense matter with strong short-range repulsive interactions. We find that repulsive interactions required to stabilize massive neutron stars can induce p-wave pairing in neutron and quark matter. When massive vector bosons mediate the interaction between fermions, the induced interaction favors Cooper pairing in the 3P2 channel. For the typical strength of the interaction favored by massive neutron stars, the associated pairing gaps in neutrons can be in the range of 10 keV to 10 MeV. Strong and attractive spin-orbit and tensor forces between neutrons can result in repulsive induced interactions that greatly suppress the 3P2 pairing gap in neutron matter. In quark matter, the induced interaction is too small to result in pairing gaps of phenomenological relevance., Comment: 34 pages, 11 figures

Sensing the motion of physical objects in an environment enables numerous applications, from tracking occupancy in buildings and monitoring vital signs to diagnosing faults in machines. Typically, these application scenarios involve attaching a sensor, such as an accelerometer, to the object of interest, like a wearable device that tracks our steps. However, many of these scenarios require tracking motion in a noncontact manner where the sensor is not in touch with the object. A sensor in such a scenario observes variations in radio, light, acoustic, and infrared fields disturbed by the object's motion. Current noncontact sensing mechanisms often require substantial energy and involve complex processing on sophisticated hardware. We present TunnelSense, a novel mechanism that rethinks noncontact sensing using tunnel diode oscillators. They are highly sensitive to changes in their electromagnetic environments. The motion of an object near a tunnel diode oscillator induces corresponding changes in its resonant frequency and thus in the generated radio waves. Additionally, the low-power characteristics of the tunnel diode allow tags designed using them to operate on less than 100microwatt of power consumption and with a biasing voltage starting at 70 millivolt. This enables prolonged tag operation on a small battery or energy harvested from the environment. Among numerous applications enabled by the TunnelSense system, this work demonstrates its ability to detect breathing at distances up to 30 centimeter between the subject and the TunnelSense tag., Comment: This work is accepted at IEEE RFID 2024

This paper introduces Fusion Intelligence (FI), a bio-inspired intelligent system, where the innate sensing, intelligence and unique actuation abilities of biological organisms such as bees and ants are integrated with the computational power of Artificial Intelligence (AI). This interdisciplinary field seeks to create systems that are not only smart but also adaptive and responsive in ways that mimic the nature. As FI evolves, it holds the promise of revolutionizing the way we approach complex problems, leveraging the best of both biological and digital worlds to create solutions that are more effective, sustainable, and harmonious with the environment. We demonstrate FI's potential to enhance agricultural IoT system performance through a simulated case study on improving insect pollination efficacy (entomophily)., Comment: 7 pages, 4 figures, 1 Table

Going beyond mere fine-tuning of vision-language models (VLMs), learnable prompt tuning has emerged as a promising, resource-efficient alternative. Despite their potential, effectively learning prompts faces the following challenges: (i) training in a low-shot scenario results in overfitting, limiting adaptability, and yielding weaker performance on newer classes or datasets; (ii) prompt-tuning's efficacy heavily relies on the label space, with decreased performance in large class spaces, signaling potential gaps in bridging image and class concepts. In this work, we investigate whether better text semantics can help address these concerns. In particular, we introduce a prompt-tuning method that leverages class descriptions obtained from Large Language Models (LLMs). These class descriptions are used to bridge image and text modalities. Our approach constructs part-level description-guided image and text features, which are subsequently aligned to learn more generalizable prompts. Our comprehensive experiments conducted across 11 benchmark datasets show that our method outperforms established methods, demonstrating substantial improvements.

Large Language Models (LLMs) are becoming vital tools that help us solve and understand complex problems by acting as digital assistants. LLMs can generate convincing explanations, even when only given the inputs and outputs of these problems, i.e., in a ``black-box'' approach. However, our research uncovers a hidden risk tied to this approach, which we call *adversarial helpfulness*. This happens when an LLM's explanations make a wrong answer look right, potentially leading people to trust incorrect solutions. In this paper, we show that this issue affects not just humans, but also LLM evaluators. Digging deeper, we identify and examine key persuasive strategies employed by LLMs. Our findings reveal that these models employ strategies such as reframing the questions, expressing an elevated level of confidence, and cherry-picking evidence to paint misleading answers in a credible light. To examine if LLMs are able to navigate complex-structured knowledge when generating adversarially helpful explanations, we create a special task based on navigating through graphs. Most LLMs are not able to find alternative paths along simple graphs, indicating that their misleading explanations aren't produced by only logical deductions using complex knowledge. These findings shed light on the limitations of the black-box explanation setting and allow us to provide advice on the safe usage of LLMs., Comment: NeurIPS Regulatable ML Workshop

Image segmentation, the process of partitioning an image into meaningful regions, plays a pivotal role in computer vision and medical imaging applications. Unsupervised segmentation, particularly in the absence of labeled data, remains a challenging task due to the inter-class similarity and variations in intensity and resolution. In this study, we extract high-level features of the input image using pretrained vision transformer. Subsequently, the proposed method leverages the underlying graph structures of the images, seeking to discover and delineate meaningful boundaries using graph neural networks and modularity based optimization criteria without relying on pre-labeled training data. Experimental results on benchmark datasets demonstrate the effectiveness and versatility of the proposed approach, showcasing competitive performance compared to the state-of-the-art unsupervised segmentation methods. This research contributes to the broader field of unsupervised medical imaging and computer vision by presenting an innovative methodology for image segmentation that aligns with real-world challenges. The proposed method holds promise for diverse applications, including medical imaging, remote sensing, and object recognition, where labeled data may be scarce or unavailable. The github repository of the code is available on [https://github.com/ksgr5566/unseggnet]

Interpretability is the study of explaining models in understandable terms to humans. At present, interpretability is divided into two paradigms: the intrinsic paradigm, which believes that only models designed to be explained can be explained, and the post-hoc paradigm, which believes that black-box models can be explained. At the core of this debate is how each paradigm ensures its explanations are faithful, i.e., true to the model's behavior. This is important, as false but convincing explanations lead to unsupported confidence in artificial intelligence (AI), which can be dangerous. This paper's position is that we should think about new paradigms while staying vigilant regarding faithfulness. First, by examining the history of paradigms in science, we see that paradigms are constantly evolving. Then, by examining the current paradigms, we can understand their underlying beliefs, the value they bring, and their limitations. Finally, this paper presents 3 emerging paradigms for interpretability. The first paradigm designs models such that faithfulness can be easily measured. Another optimizes models such that explanations become faithful. The last paradigm proposes to develop models that produce both a prediction and an explanation.

We present the census of H$\beta$+[OIII] 4960,5008 \AA emitters at 6.87$ galaxies. We report a rapid decline of the [OIII] luminosity density at $z\gtrsim 6-7$ which cannot be explained by the evolution of the cosmic star-formation rate density. Finally we find that FRESCO detects in only 2h galaxies likely accounting for $\sim 10-20\%$ of the ionising budget at $z=7-8$ (assuming an escape fraction of 10%), raising the prospect of directly detecting a significant fraction of the sources of reionisation with JWST., Comment: 20 pages + appendices. Accepted in MNRAS. Public catalogue release at https://github.com/rameyer/fresco. V3: matching accepted version

Anomaly detection, a critical facet in data analysis, involves identifying patterns that deviate from expected behavior. This research addresses the complexities inherent in anomaly detection, exploring challenges and adapting to sophisticated malicious activities. With applications spanning cybersecurity, healthcare, finance, and surveillance, anomalies often signify critical information or potential threats. Inspired by the success of Anomaly Generative Adversarial Network (AnoGAN) in image domains, our research extends its principles to tabular data. Our contributions include adapting AnoGAN's principles to a new domain and promising advancements in detecting previously undetectable anomalies. This paper delves into the multifaceted nature of anomaly detection, considering the dynamic evolution of normal behavior, context-dependent anomaly definitions, and data-related challenges like noise and imbalances., Comment: 12 pages, 6 figures, accepted as Short paper at HCII 2024 (https://2024.hci.international)

Recent developments in adversarial machine learning have highlighted the importance of building robust AI systems to protect against increasingly sophisticated attacks. While frameworks like AI Guardian are designed to defend against these threats, they often rely on assumptions that can limit their effectiveness. For example, they may assume attacks only come from one direction or include adversarial images in their training data. Our proposal suggests a different approach to the AI Guardian framework. Instead of including adversarial examples in the training process, we propose training the AI system without them. This aims to create a system that is inherently resilient to a wider range of attacks. Our method focuses on a dynamic defense strategy using stable diffusion that learns continuously and models threats comprehensively. We believe this approach can lead to a more generalized and robust defense against adversarial attacks. In this paper, we outline our proposed approach, including the theoretical basis, experimental design, and expected impact on improving AI security against adversarial threats.

In the present work, interfacial magnetism at metal organic interface is probed using an isotope sensitive interface resolved nuclear resonance scattering technique which is made depth selective under x-rays standing wave conditions. Using GIWAXS and GINRS measurements, this study evidences the presence of symmetry-based PMA which appears at a lower thickness of Fe having distortion in cubic symmetry and disappears at a higher thickness of Fe as its cubic symmetry retains. The non-zero value of quadrupole splitting evidences the strain at the interfacial region which on increasing thickness of Fe relaxes. The diffusion of Fe is traced using XRF and NRR, deep penetration of Fe in Alq3 layer due to soft nature of the organic film is obtained. This thickness-dependent study enables us to understand the magnetic behavior of buried ferromagnetic metal in the vicinity of organic molecules.

Despite the remarkable success of Large Language Models (LLMs) in text understanding and generation, their potential for text clustering tasks remains underexplored. We observed that powerful closed-source LLMs provide good quality clusterings of entity sets but are not scalable due to the massive compute power required and the associated costs. Thus, we propose CACTUS (Context-Aware ClusTering with aUgmented triplet losS), a systematic approach that leverages open-source LLMs for efficient and effective supervised clustering of entity subsets, particularly focusing on text-based entities. Existing text clustering methods fail to effectively capture the context provided by the entity subset. Moreover, though there are several language modeling based approaches for clustering, very few are designed for the task of supervised clustering. This paper introduces a novel approach towards clustering entity subsets using LLMs by capturing context via a scalable inter-entity attention mechanism. We propose a novel augmented triplet loss function tailored for supervised clustering, which addresses the inherent challenges of directly applying the triplet loss to this problem. Furthermore, we introduce a self-supervised clustering task based on text augmentation techniques to improve the generalization of our model. For evaluation, we collect ground truth clusterings from a closed-source LLM and transfer this knowledge to an open-source LLM under the supervised clustering framework, allowing a faster and cheaper open-source model to perform the same task. Experiments on various e-commerce query and product clustering datasets demonstrate that our proposed approach significantly outperforms existing unsupervised and supervised baselines under various external clustering evaluation metrics., Comment: 16 pages

In the burgeoning market of short-term rentals, understanding pricing dynamics is crucial for a range of stake-holders. This study delves into the factors influencing Airbnb pricing in major European cities, employing a comprehensive dataset sourced from Kaggle. We utilize advanced regression techniques, including linear, polynomial, and random forest models, to analyze a diverse array of determinants, such as location characteristics, property types, and host-related factors. Our findings reveal nuanced insights into the variables most significantly impacting pricing, highlighting the varying roles of geographical, structural, and host-specific attributes. This research not only sheds light on the complex pricing landscape of Airbnb accommodations in Europe but also offers valuable implications for hosts seeking to optimize pricing strategies and for travelers aiming to understand pricing trends. Furthermore, the study contributes to the broader discourse on pricing mechanisms in the shared economy, suggesting avenues for future research in this rapidly evolving sector.

In this project, we have explored machine learning approaches for predicting hearing loss thresholds on the brain's gray matter 3D images. We have solved the problem statement in two phases. In the first phase, we used a 3D CNN model to reduce high-dimensional input into latent space and decode it into an original image to represent the input in rich feature space. In the second phase, we utilized this model to reduce input into rich features and used these features to train standard machine learning models for predicting hearing thresholds. We have experimented with autoencoders and variational autoencoders in the first phase for dimensionality reduction and explored random forest, XGBoost and multi-layer perceptron for regressing the thresholds. We split the given data set into training and testing sets and achieved an 8.80 range and 22.57 range for PT500 and PT4000 on the test set, respectively. We got the lowest RMSE using multi-layer perceptron among the other models. Our approach leverages the unique capabilities of VAEs to capture complex, non-linear relationships within high-dimensional neuroimaging data. We rigorously evaluated the models using various metrics, focusing on the root mean squared error (RMSE). The results highlight the efficacy of the multi-layer neural network model, which outperformed other techniques in terms of accuracy. This project advances the application of data mining in medical diagnostics and enhances our understanding of age-related hearing loss through innovative machine-learning frameworks.

The increased importance of cybersecurity in autonomous machinery is becoming evident in the forestry domain. Forestry worksites are becoming more complex with the involvement of multiple systems and system of systems. Hence, there is a need to investigate how to address cybersecurity challenges for autonomous systems of systems in the forestry domain. Using a literature review and adapting standards from similar domains, as well as collaborative sessions with domain experts, we identify challenges towards CE-certified autonomous forestry machines focusing on cybersecurity and safety. Furthermore, we discuss the relationship between safety and cybersecurity risk assessment and their relation to AI, highlighting the need for a holistic methodology for their assurance.

The increasing demand for computational photography and imaging on mobile platforms has led to the widespread development and integration of advanced image sensors with novel algorithms in camera systems. However, the scarcity of high-quality data for research and the rare opportunity for in-depth exchange of views from industry and academia constrain the development of mobile intelligent photography and imaging (MIPI). Building on the achievements of the previous MIPI Workshops held at ECCV 2022 and CVPR 2023, we introduce our third MIPI challenge including three tracks focusing on novel image sensors and imaging algorithms. In this paper, we summarize and review the Nighttime Flare Removal track on MIPI 2024. In total, 170 participants were successfully registered, and 14 teams submitted results in the final testing phase. The developed solutions in this challenge achieved state-of-the-art performance on Nighttime Flare Removal. More details of this challenge and the link to the dataset can be found at https://mipi-challenge.org/MIPI2024/., Comment: CVPR 2024 Mobile Intelligent Photography and Imaging (MIPI) Workshop--Nighttime Flare Removal Challenge Report. Website: https://mipi-challenge.org/MIPI2024/

The compilation and analysis of radiological images poses numerous challenges for researchers. The sheer volume of data as well as the computational needs of algorithms capable of operating on images are extensive. Additionally, the assembly of these images alone is difficult, as these exams may differ widely in terms of clinical context, structured annotation available for model training, modality, and patient identifiers. In this paper, we describe our experiences and challenges in establishing a trusted collection of radiology images linked to the United States Department of Veterans Affairs (VA) electronic health record database. We also discuss implications in making this repository research-ready for medical investigators. Key insights include uncovering the specific procedures required for transferring images from a clinical to a research-ready environment, as well as roadblocks and bottlenecks in this process that may hinder future efforts at automation.

Mathematical equations have been unreasonably effective in describing complex natural phenomena across various scientific disciplines. However, discovering such insightful equations from data presents significant challenges due to the necessity of navigating extremely high-dimensional combinatorial and nonlinear hypothesis spaces. Traditional methods of equation discovery, commonly known as symbolic regression, largely focus on extracting equations from data alone, often neglecting the rich domain-specific prior knowledge that scientists typically depend on. To bridge this gap, we introduce LLM-SR, a novel approach that leverages the extensive scientific knowledge and robust code generation capabilities of Large Language Models (LLMs) to discover scientific equations from data in an efficient manner. Specifically, LLM-SR treats equations as programs with mathematical operators and combines LLMs' scientific priors with evolutionary search over equation programs. The LLM iteratively proposes new equation skeleton hypotheses, drawing from its physical understanding, which are then optimized against data to estimate skeleton parameters. We demonstrate LLM-SR's effectiveness across three diverse scientific domains, where it discovers physically accurate equations that provide significantly better fits to in-domain and out-of-domain data compared to the well-established symbolic regression baselines. Incorporating scientific prior knowledge also enables LLM-SR to search the equation space more efficiently than baselines. Code is available at: https://github.com/deep-symbolic-mathematics/LLM-SR

The study of small ($<$300 m) near-Earth objects (NEOs) is important because they are more closely related than larger objects to the precursors of meteorites that fall on Earth. Collisions of these bodies with Earth are also more frequent. Although such collisions cannot produce massive extinction events, they can still produce significant local damage. Here we present the results of a photometric and spectroscopic survey of small NEOs, which include near-infrared (NIR) spectra of 84 objects with a mean diameter of 126 m and photometric data of 59 objects with a mean diameter of 87 m. We found that S-complex asteroids are the most abundant among the NEOs, comprising $\sim$66\% of the sample. Most asteroids in the S-complex were found to have compositions consistent with LL-chondrites. Our study revealed the existence of NEOs with spectral characteristics similar to those in the S-complex, but that could be hidden within the C- or X-complex due to their weak absorption bands. We suggest that the presence of metal or shock-darkening could be responsible for the attenuation of the absorption bands. These objects have been grouped into a new subclass within the S-complex called Sx-types. The dynamical modeling showed that 83\% of the NEOs escaped from the $\nu_{6}$ resonance, 16\% from the 3:1 and just 1\% from the 5:2 resonance. Lightcurves and rotational periods were derived from the photometric data. No clear trend between the axis ratio and the absolute magnitude or rotational period of the NEOs was found., Comment: 61 pages, 43 figures, 5 tables. Accepted for publication in the Planetary Science Journal

We present the first results on the spatial distribution of star formation in 454 star-forming galaxies at $4.8

In recent years, there has been increasing interest in network diffusion models and related problems. The most popular of these are the independent cascade and linear threshold models. Much of the recent experimental work done on these models requires a large number of simulations conducted on large graphs, a computationally expensive task suited for low-level languages. However, many researchers prefer the use of higher-level languages (such as Python) for their flexibility and shorter development times. Moreover, in many research tasks, these simulations are the most computationally intensive task, so it would be desirable to have a library for these with an interface to a high-level language with the performance of a low-level language. To fill this niche, we introduce CyNetDiff, a Python library with components written in Cython to provide improved performance for these computationally intensive diffusion tasks., Comment: 4 pages, 3 figures, and 2 tables

Recent work has developed optimization procedures to find token sequences, called adversarial triggers, which can elicit unsafe responses from aligned language models. These triggers are believed to be universally transferable, i.e., a trigger optimized on one model can jailbreak other models. In this paper, we concretely show that such adversarial triggers are not universal. We extensively investigate trigger transfer amongst 13 open models and observe inconsistent transfer. Our experiments further reveal a significant difference in robustness to adversarial triggers between models Aligned by Preference Optimization (APO) and models Aligned by Fine-Tuning (AFT). We find that APO models are extremely hard to jailbreak even when the trigger is optimized directly on the model. On the other hand, while AFT models may appear safe on the surface, exhibiting refusals to a range of unsafe instructions, we show that they are highly susceptible to adversarial triggers. Lastly, we observe that most triggers optimized on AFT models also generalize to new unsafe instructions from five diverse domains, further emphasizing their vulnerability. Overall, our work highlights the need for more comprehensive safety evaluations for aligned language models.

The right to be forgotten (RTBF) seeks to safeguard individuals from the enduring effects of their historical actions by implementing machine-learning techniques. These techniques facilitate the deletion of previously acquired knowledge without requiring extensive model retraining. However, they often overlook a critical issue: unlearning processes bias. This bias emerges from two main sources: (1) data-level bias, characterized by uneven data removal, and (2) algorithm-level bias, which leads to the contamination of the remaining dataset, thereby degrading model accuracy. In this work, we analyze the causal factors behind the unlearning process and mitigate biases at both data and algorithmic levels. Typically, we introduce an intervention-based approach, where knowledge to forget is erased with a debiased dataset. Besides, we guide the forgetting procedure by leveraging counterfactual examples, as they maintain semantic data consistency without hurting performance on the remaining dataset. Experimental results demonstrate that our method outperforms existing machine unlearning baselines on evaluation metrics.

Underwater images taken from autonomous underwater vehicles (AUV's) often suffer from low light, high turbidity, poor contrast, motion-blur and excessive light scattering and hence require image enhancement techniques for object recognition. Machine learning methods are being increasingly used for object recognition under such adverse conditions. These enhanced object recognition methods of images taken from AUV's has potential applications in underwater pipeline and optical fibre surveillance, ocean bed resource extraction, ocean floor mapping, underwater species exploration, etc. While the classical machine learning methods are very efficient in terms of accuracy, they require large datasets and high computational time for image classification. In the current work, we use quantum-classical hybrid machine learning methods for real-time under-water object recognition on-board an AUV for the first time. We use real-time motion-blurred and low-light images taken from an on-board camera of AUV built in-house and apply existing hybrid machine learning methods for object recognition. Our hybrid methods consist of quantum encoding and flattening of classical images using quantum circuits and sending them to classical neural networks for image classification. The results of hybrid methods carried out using Pennylane based quantum simulators both on GPU and using pre-trained models on an on-board NVIDIA GPU chipset are compared with results from corresponding classical machine learning methods. We observe that the hybrid quantum machine learning methods show an efficiency greater than 65\% and reduction in run-time by one-thirds and require 50\% smaller dataset sizes for training the models compared to classical machine learning methods. We hope that our work opens up further possibilities in quantum enhanced real-time computer vision in autonomous vehicles.

Face-morphing attacks are a growing concern for biometric researchers, as they can be used to fool face recognition systems (FRS). These attacks can be generated at the image level (supervised) or representation level (unsupervised). Previous unsupervised morphing attacks have relied on generative adversarial networks (GANs). More recently, researchers have used linear interpolation of StyleGAN-encoded images to generate morphing attacks. In this paper, we propose a new method for generating high-quality morphing attacks using StyleGAN disentanglement. Our approach, called MLSD-GAN, spherically interpolates the disentangled latents to produce realistic and diverse morphing attacks. We evaluate the vulnerability of MLSD-GAN on two deep-learning-based FRS techniques. The results show that MLSD-GAN poses a significant threat to FRS, as it can generate morphing attacks that are highly effective at fooling these systems.

We present results from the JWST First Reionization Epoch Spectroscopically Complete Observations survey (FRESCO) on the star forming sequence of galaxies at $1.09.5 M_\odot$ that are lower than found in many earlier studies by up to 0.6 dex, but in good agreement with recent results obtained with the Prospector fitting framework. The difference log(SFR(Pa$\alpha$)-SFR(Prospector)) is -0.09 $\pm$ 0.04 dex at $10^{10-11} M_\odot$. We also measure the empirical relation between Paschen-$\alpha$ luminosity and rest-frame H band magnitude and find that the scatter is only 0.04 dex lower than that of the SFR-M* relation and is much lower than the systematic differences among relations in the literature due to various methods of converting observed measurements to physical properties. We additionally identify examples of sources -- that, with standard cutoffs via the UVJ diagram, would be deemed quiescent -- with significant, typically extended, Paschen-$\alpha$ emission. Our results may be indicative of the potential unification of methods used to derive the star forming sequence with careful selection of star forming galaxies and independent star formation rate and stellar mass indicators., Comment: 17 pages, 9 figures. Accepted for publication in ApJ

The challenge of imbalanced soil nutrient datasets significantly hampers accurate predictions of soil fertility. To tackle this, a new method is suggested in this research, combining Uniform Manifold Approximation and Projection (UMAP) with Least Absolute Shrinkage and Selection Operator (LASSO). The main aim is to counter the impact of uneven data distribution and improve soil fertility models' predictive precision. The model introduced uses Sparse Attention Regression, effectively incorporating pertinent features from the imbalanced dataset. UMAP is utilized initially to reduce data complexity, unveiling hidden structures and important patterns. Following this, LASSO is applied to refine features and enhance the model's interpretability. The experimental outcomes highlight the effectiveness of the UMAP and LASSO hybrid approach. The proposed model achieves outstanding performance metrics, reaching a predictive accuracy of 98%, demonstrating its capability in accurate soil fertility predictions. Additionally, it showcases a Precision of 91.25%, indicating its adeptness in identifying fertile soil instances accurately. The Recall metric stands at 90.90%, emphasizing the model's ability to capture true positive cases effectively., Comment: There is an error in the result section

Invasive ductal carcinoma (IDC) is the most prevalent form of breast cancer. Breast tissue histopathological examination is critical in diagnosing and classifying breast cancer. Although existing methods have shown promising results, there is still room for improvement in the classification accuracy and generalization of IDC using histopathology images. We present a novel approach, Supervised Contrastive Vision Transformer (SupCon-ViT), for improving the classification of invasive ductal carcinoma in terms of accuracy and generalization by leveraging the inherent strengths and advantages of both transfer learning, i.e., pre-trained vision transformer, and supervised contrastive learning. Our results on a benchmark breast cancer dataset demonstrate that SupCon-Vit achieves state-of-the-art performance in IDC classification, with an F1-score of 0.8188, precision of 0.7692, and specificity of 0.8971, outperforming existing methods. In addition, the proposed model demonstrates resilience in scenarios with minimal labeled data, making it highly efficient in real-world clinical settings where labelled data is limited. Our findings suggest that supervised contrastive learning in conjunction with pre-trained vision transformers appears to be a viable strategy for an accurate classification of IDC, thus paving the way for a more efficient and reliable diagnosis of breast cancer through histopathological image analysis., Comment: 8 pages, 7 figures

Automatic white balancing (AWB), one of the first steps in an integrated signal processing (ISP) pipeline, aims to correct the color cast induced by the scene illuminant. An incorrect white balance (WB) setting or AWB failure can lead to an undesired blue or red tint in the rendered sRGB image. To address this, recent methods pose the post-capture WB correction problem as an image-to-image translation task and train deep neural networks to learn the necessary color adjustments at a lower resolution. These low resolution outputs are post-processed to generate high resolution WB corrected images, forming a bottleneck in the end-to-end run time. In this paper we present a 3D Lookup Table (LUT) based WB correction model called WB LUTs that can generate high resolution outputs in real time. We introduce a contrastive learning framework with a novel hard sample mining strategy, which improves the WB correction quality of baseline 3D LUTs by 25.5%. Experimental results demonstrate that the proposed WB LUTs perform competitively against state-of-the-art models on two benchmark datasets while being 300 times faster using 12.7 times less memory. Our model and code are available at https://github.com/skrmanne/3DLUT_sRGB_WB.

Osteoclast cell image analysis plays a key role in osteoporosis research, but it typically involves extensive manual image processing and hand annotations by a trained expert. In the last few years, a handful of machine learning approaches for osteoclast image analysis have been developed, but none have addressed the full instance segmentation task required to produce the same output as that of the human expert led process. Furthermore, none of the prior, fully automated algorithms have publicly available code, pretrained models, or annotated datasets, inhibiting reproduction and extension of their work. We present a new dataset with ~2*10^5 expert annotated mouse osteoclast masks, together with a deep learning instance segmentation method which works for both in vitro mouse osteoclast cells on plastic tissue culture plates and human osteoclast cells on bone chips. To our knowledge, this is the first work to automate the full osteoclast instance segmentation task. Our method achieves a performance of 0.82 mAP_0.5 (mean average precision at intersection-over-union threshold of 0.5) in cross validation for mouse osteoclasts. We present a novel nuclei-aware osteoclast instance segmentation training strategy (NOISe) based on the unique biology of osteoclasts, to improve the model's generalizability and boost the mAP_0.5 from 0.60 to 0.82 on human osteoclasts. We publish our annotated mouse osteoclast image dataset, instance segmentation models, and code at github.com/michaelwwan/noise to enable reproducibility and to provide a public tool to accelerate osteoporosis research.

In this paper, we present EdgeRelight360, an approach for real-time video portrait relighting on mobile devices, utilizing text-conditioned generation of 360-degree high dynamic range image (HDRI) maps. Our method proposes a diffusion-based text-to-360-degree image generation in the HDR domain, taking advantage of the HDR10 standard. This technique facilitates the generation of high-quality, realistic lighting conditions from textual descriptions, offering flexibility and control in portrait video relighting task. Unlike the previous relighting frameworks, our proposed system performs video relighting directly on-device, enabling real-time inference with real 360-degree HDRI maps. This on-device processing ensures both privacy and guarantees low runtime, providing an immediate response to changes in lighting conditions or user inputs. Our approach paves the way for new possibilities in real-time video applications, including video conferencing, gaming, and augmented reality, by allowing dynamic, text-based control of lighting conditions., Comment: Camera-ready version (CVPR workshop - EDGE'24)

Recently, event-based vision sensors have gained attention for autonomous driving applications, as conventional RGB cameras face limitations in handling challenging dynamic conditions. However, the availability of real-world and synthetic event-based vision datasets remains limited. In response to this gap, we present SEVD, a first-of-its-kind multi-view ego, and fixed perception synthetic event-based dataset using multiple dynamic vision sensors within the CARLA simulator. Data sequences are recorded across diverse lighting (noon, nighttime, twilight) and weather conditions (clear, cloudy, wet, rainy, foggy) with domain shifts (discrete and continuous). SEVD spans urban, suburban, rural, and highway scenes featuring various classes of objects (car, truck, van, bicycle, motorcycle, and pedestrian). Alongside event data, SEVD includes RGB imagery, depth maps, optical flow, semantic, and instance segmentation, facilitating a comprehensive understanding of the scene. Furthermore, we evaluate the dataset using state-of-the-art event-based (RED, RVT) and frame-based (YOLOv8) methods for traffic participant detection tasks and provide baseline benchmarks for assessment. Additionally, we conduct experiments to assess the synthetic event-based dataset's generalization capabilities. The dataset is available at https://eventbasedvision.github.io/SEVD

This paper introduces CRITICAL, a novel closed-loop framework for autonomous vehicle (AV) training and testing. CRITICAL stands out for its ability to generate diverse scenarios, focusing on critical driving situations that target specific learning and performance gaps identified in the Reinforcement Learning (RL) agent. The framework achieves this by integrating real-world traffic dynamics, driving behavior analysis, surrogate safety measures, and an optional Large Language Model (LLM) component. It is proven that the establishment of a closed feedback loop between the data generation pipeline and the training process can enhance the learning rate during training, elevate overall system performance, and augment safety resilience. Our evaluations, conducted using the Proximal Policy Optimization (PPO) and the HighwayEnv simulation environment, demonstrate noticeable performance improvements with the integration of critical case generation and LLM analysis, indicating CRITICAL's potential to improve the robustness of AV systems and streamline the generation of critical scenarios. This ultimately serves to hasten the development of AV agents, expand the general scope of RL training, and ameliorate validation efforts for AV safety., Comment: 7 pages, 5 figures