Search

Web-scale visual entity recognition, the task of associating images with their corresponding entities within vast knowledge bases like Wikipedia, presents significant challenges due to the lack of clean, large-scale training data. In this paper, we propose a novel methodology to curate such a dataset, leveraging a multimodal large language model (LLM) for label verification, metadata generation, and rationale explanation. Instead of relying on the multimodal LLM to directly annotate data, which we found to be suboptimal, we prompt it to reason about potential candidate entity labels by accessing additional contextually relevant information (such as Wikipedia), resulting in more accurate annotations. We further use the multimodal LLM to enrich the dataset by generating question-answer pairs and a grounded finegrained textual description (referred to as "rationale") that explains the connection between images and their assigned entities. Experiments demonstrate that models trained on this automatically curated data achieve state-of-the-art performance on web-scale visual entity recognition tasks (e.g. +6.9% improvement in OVEN entity task), underscoring the importance of high-quality training data in this domain., Comment: NeurIPS 2024

We develop a hybrid classical-quantum method for solving the Lorenz system. We use the forward Euler method to discretize the system in time, transforming it into a system of equations. This set of equations is solved using the Variational Quantum Linear Solver (VQLS) algorithm. We present numerical results comparing the hybrid method with the classical approach for solving the Lorenz system. The simulation results demonstrate that the VQLS method can effectively compute solutions comparable to classical methods. The method is easily extended to solving similar nonlinear differential equations.

The goal of machine learning is generalization. While the No Free Lunch Theorem states that we cannot obtain theoretical guarantees for generalization without further assumptions, in practice we observe that simple models which explain the training data generalize best: a principle called Occam's razor. Despite the need for simple models, most current approaches in machine learning only minimize the training error, and at best indirectly promote simplicity through regularization or architecture design. Here, we draw a connection between Occam's razor and in-context learning: an emergent ability of certain sequence models like Transformers to learn at inference time from past observations in a sequence. In particular, we show that the next-token prediction loss used to train in-context learners is directly equivalent to a data compression technique called prequential coding, and that minimizing this loss amounts to jointly minimizing both the training error and the complexity of the model that was implicitly learned from context. Our theory and the empirical experiments we use to support it not only provide a normative account of in-context learning, but also elucidate the shortcomings of current in-context learning methods, suggesting ways in which they can be improved. We make our code available at https://github.com/3rdCore/PrequentialCode.

In this paper, we propose an asymptotic expansion conjecture for the partition functions in Teichm\"uller TQFT; we then prove this conjecture for all FAMED geometric triangulations of hyperbolic knot complements, where FAMED means that the triangulation satisfies certain combinatorial properties. Our conjecture predicts that (1) the invariant decays exponentially with decrease rate the hyperbolic volume of a cone structure determined by the prescribed angle structure and (2) the 1-loop invariant, which conjecturally is the same as the adjoint twisted Reidemeister torsion, shows up as the 1-loop term in the asymptotic expansion formula. Based on this, we connect our volume conjecture with the Casson conjecture on angle structures by relating the exponential decay rate of the invariant to the volume functional defined on certain subspace of angle structures of ideal triangulations. Furthermore, for FAMED triangulations, we prove the existence of the Jones functions in Teichm\"uller TQFT, which is expected to be an analogue of the Kashaev invariant of the knot when the manifold is a knot complement in $S^3$. Then, for FAMED geometric triangulations, we obtain an asymptotic expansion formula for the Jones function, which generalizes the Andersen-Kashaev volume conjecture in \cite{AK}. We also provide a simple argument to relate the asymptotic expansion formula of the Jones function with a weaker version of the AJ conjecture for the Teichm\"uller TQFT. Finally, we prove that the geometric ideal triangulations of hyperbolic twist knot complements constructed in \cite{BAGPN} are FAMED, which implies that these triangulations of twist knot complements satisfy all the previously mentioned results., Comment: 45 pages, 5 figures, comments welcome!

This work is dedicated to the study of a linear model arising in thermoelastic rod of homogeneous material. The system is resulting from a coupling of a heat and a wave equation in the interval $(0,1)$ with Dirichlet boundary conditions at the outer endpoints where the parabolic component is degenerating at the end point $x=0$. Two models are considered the first is with weak degeneracy and the second is with strong degeneracy. We aim to study the well-posedness and asymptotic stability of both systems using techniques from the $C_{0}$-semigroup theory and a use a frequency domain approach based on the well-known result of Pr\"uss in order to prove using some multiplier techniques that the energy of classical solutions decays uniformly as time goes to infinity.

In this paper, we study an asymptotically flat black hole spacetime with weakly nonminimally coupled monopole charge. We analytically and numerically investigate light ray propagation around such a black hole by employing the common Lagrangian formalism. Our analysis encompasses both radial and angular geodesics, for which we present analytical solutions in terms of incomplete Lauricella hypergeometric functions. Additionally, we explore the impact of the coupling constant on geodesic motion. Based on observations from the Event Horizon Telescope, we constrain the black hole parameters, resulting in a coupling constant range of $-0.5 M^2\lesssim \alpha\lesssim 0.5 M^2$. Throughout our analysis, we simulate all possible trajectories and, where necessary, perform numerical inversion of the included integrals., Comment: 16 pages, 11 figures

We found that, unlike General Relativity, the shift-symmetric subclass of Beyond Horndeski theories provides black holes with primary hair, which are thermodynamically stable and compatible with current Event Horizon Telescope observations for M87* and Sgr A* black holes. We first investigate its thermodynamic properties by studying the influence of the primary hair on the thermodynamic quantities and the local stability, imposing severe constraints in the allowed range of the primary hair values. Then, we analyze the null geodesics near this black hole, demonstrating how the scalar hair influences the shadow diameter, finding that higher values of the primary hair lead to smaller shadow sizes. Additionally, we constrain the scalar hair using the observational data, revealing its sensitivity to the choice of other black hole parameters. To further probe the observational features of the scalar hair, we simulate face-on two-dimensional images of spherically infalling accretion disks, examining how the primary scalar hair affects the black hole's shadow. Finally, we impose all relevant constraints to identify black holes that are both stable and consistent with observational data., Comment: 16 pages, 12 figures, 1 table

Background and Objective: Diabetes presents a significant challenge to healthcare due to the negative impact of poor blood sugar control on health and associated complications. Computer simulation platforms, notably exemplified by the UVA/Padova Type 1 Diabetes simulator, has emerged as a promising tool for advancing diabetes treatments by simulating patient responses in a virtual environment. The UVA Virtual Lab (UVLab) is a new simulation platform to mimic the metabolic behavior of people with Type 2 diabetes (T2D) with a large population of 6062 virtual subjects. Methods: The work introduces the Distribution-Based Population Selection (DSPS) method, a systematic approach to identifying virtual subsets that mimic the clinical behavior observed in real trials. The method transforms the sub-population selection task into a Linear Programing problem, enabling the identification of the largest representative virtual cohort. This selection process centers on key clinical outcomes in diabetes research, such as HbA1c and Fasting plasma Glucose (FPG), ensuring that the statistical properties (moments) of the selected virtual sub-population closely resemble those observed in real-word clinical trial. Results: DSPS method was applied to the insulin degludec (IDeg) arm of a phase 3 clinical trial. This method was used to select a sub-population of virtual subjects that closely mirrored the clinical trial data across multiple key metrics, including glycemic efficacy, insulin dosages, and cumulative hypoglycemia events over a 26-week period. Conclusion: The DSPS algorithm is able to select virtual sub-population within UVLab to reproduce and predict the outcomes of a clinical trial. This statistical method can bridge the gap between large population simulation platforms and previously conducted clinical trials.

Unsupervised anomaly detection is a promising technique for identifying unusual patterns in data without the need for labeled training examples. This approach is particularly valuable for early case detection in epidemic management, especially when early-stage data are scarce. This research introduces a novel hybrid method for anomaly detection that combines distance and density measures, enhancing its applicability across various infectious diseases. Our method is especially relevant in pandemic situations, as demonstrated during the COVID-19 crisis, where traditional supervised classification methods fall short due to limited data. The efficacy of our method is evaluated using COVID-19 chest X-ray data, where it significantly outperforms established unsupervised techniques. It achieves an average AUC of 77.43%, surpassing the AUC of Isolation Forest at 73.66% and KNN at 52.93%. These results highlight the potential of our hybrid anomaly detection method to improve early detection capabilities in diverse epidemic scenarios, thereby facilitating more effective and timely responses.

We give an alternative proof and some extensions of results of Carlier, Figalli and Santambrogio on polynomial upper bounds on the Brenier map between probability measures under various conditions on the densities. The proofs are based on the monotonicity of the map and various concentration inequalities, as already used by Colombo and Fathi to prove quadratic growth for transport maps from the standard Gaussian onto log-concave measures.

The first generation of cryptocurrencies introduced revolutionary concepts, yet faced challenges in privacy and regulatory compliance. While subsequent cryptocurrencies aimed to address privacy concerns (like Zcash and Monero), they often conflicted with regulatory frameworks, hindering broader adoption. In response, inspired by recent researches about privacy and accountability and incentive techniques in Blockchain, we propose IdentityChain as a novel framework that integrates privacy and accountability principles, leading to a robust system equipped with adaptable rules. IdentityChain is a KYC (Know Your Customer) service on top of a public Blockchain (e.g., Ethereum, Ton, Polygon). The goal is to maintain privacy while ensuring compliance with existing regulations. Privacy is one of the key characteristics of IdentityChain, it's crucial for preventing conflicts of interests further discussed how. Accountability is also one of the main characteristics of IdentityChain and prevents from misbehave of users. Privacy and accountability together wouldn't be possible unless advancements in cryptography.

We give a new proof of the sharp symmetrized form of Talagrand's transport-entropy inequality. Compared to stochastic proofs of other Gaussian functional inequalities, the new idea here is a certain coupling induced by time-reversed martingale representations.

Pediatric central nervous system tumors are the leading cause of cancer-related deaths in children. The five-year survival rate for high-grade glioma in children is less than 20%. The development of new treatments is dependent upon multi-institutional collaborative clinical trials requiring reproducible and accurate centralized response assessment. We present the results of the BraTS-PEDs 2023 challenge, the first Brain Tumor Segmentation (BraTS) challenge focused on pediatric brain tumors. This challenge utilized data acquired from multiple international consortia dedicated to pediatric neuro-oncology and clinical trials. BraTS-PEDs 2023 aimed to evaluate volumetric segmentation algorithms for pediatric brain gliomas from magnetic resonance imaging using standardized quantitative performance evaluation metrics employed across the BraTS 2023 challenges. The top-performing AI approaches for pediatric tumor analysis included ensembles of nnU-Net and Swin UNETR, Auto3DSeg, or nnU-Net with a self-supervised framework. The BraTSPEDs 2023 challenge fostered collaboration between clinicians (neuro-oncologists, neuroradiologists) and AI/imaging scientists, promoting faster data sharing and the development of automated volumetric analysis techniques. These advancements could significantly benefit clinical trials and improve the care of children with brain tumors.

Calculating mealtime insulin doses poses a significant challenge for individuals with Type 1 Diabetes (T1D). Doses should perfectly compensate for expected post-meal glucose excursions, requiring a profound understanding of the individual's insulin sensitivity and the meal macronutrients'. Usually, people rely on intuition and experience to develop this understanding. In this work, we demonstrate how a reinforcement learning agent, employing a self-attention encoder network, can effectively mimic and enhance this intuitive process. Trained on 80 virtual subjects from the FDA-approved UVA/Padova T1D adult cohort and tested on twenty, self-attention demonstrates superior performance compared to other network architectures. Results reveal a significant reduction in glycemic risk, from 16.5 to 9.6 in scenarios using sensor-augmented pump and from 9.1 to 6.7 in scenarios using automated insulin delivery. This new paradigm bypasses conventional therapy parameters, offering the potential to simplify treatment and promising improved quality of life and glycemic outcomes for people with T1D., Comment: 6 pages, 4 figures, Biological and Medical Systems - 12th BMS 2024 - IFAC

A corporate bond trader in a typical sell side institution such as a bank provides liquidity to the market participants by buying/selling securities and maintaining an inventory. Upon receiving a request for a buy/sell price quote (RFQ), the trader provides a quote by adding a spread over a \textit{prevalent market price}. For illiquid bonds, the market price is harder to observe, and traders often resort to available benchmark bond prices (such as MarketAxess, Bloomberg, etc.). In \cite{Bergault2023ModelingLI}, the concept of \textit{Fair Transfer Price} for an illiquid corporate bond was introduced which is derived from an infinite horizon stochastic optimal control problem (for maximizing the trader's expected P\&L, regularized by the quadratic variation). In this paper, we consider the same optimization objective, however, we approach the estimation of an optimal bid-ask spread quoting strategy in a data driven manner and show that it can be learned using Reinforcement Learning. Furthermore, we perform extensive outcome analysis to examine the reasonableness of the trained agent's behavior., Comment: Working Paper

Maintaining patient safety and the safety of healthcare workers (HCWs) in hospitals and clinics highly depends on following the proper protocol for donning and taking off personal protective equipment (PPE). HCWs can benefit from a feedback system during the putting on and removal process because the process is cognitively demanding and errors are common. Centers for Disease Control and Prevention (CDC) provided guidelines for correct PPE use which should be followed. A real time object detection along with a unique sequencing algorithms are used to identify and determine the donning and doffing process in real time. The purpose of this technical research is two-fold: The user gets real time alert to the step they missed in the sequence if they don't follow the proper procedure during donning or doffing. Secondly, the use of tiny machine learning (yolov4-tiny) in embedded system architecture makes it feasible and cost-effective to deploy in different healthcare settings.

Chronic Kidney Disease (CKD) is one of the widespread Chronic diseases with no known ultimo cure and high morbidity. Research demonstrates that progressive Chronic Kidney Disease (CKD) is a heterogeneous disorder that significantly impacts kidney structure and functions, eventually leading to kidney failure. With the progression of time, chronic kidney disease has moved from a life-threatening disease affecting few people to a common disorder of varying severity. The goal of this research is to visualize dominating features, feature scores, and values exhibited for early prognosis and detection of CKD using ensemble learning and explainable AI. For that, an AI-driven predictive analytics approach is proposed to aid clinical practitioners in prescribing lifestyle modifications for individual patients to reduce the rate of progression of this disease. Our dataset is collected on body vitals from individuals with CKD and healthy subjects to develop our proposed AI-driven solution accurately. In this regard, blood and urine test results are provided, and ensemble tree-based machine-learning models are applied to predict unseen cases of CKD. Our research findings are validated after lengthy consultations with nephrologists. Our experiments and interpretation results are compared with existing explainable AI applications in various healthcare domains, including CKD. The comparison shows that our developed AI models, particularly the Random Forest model, have identified more features as significant contributors than XgBoost. Interpretability (I), which measures the ratio of important to masked features, indicates that our XgBoost model achieved a higher score, specifically a Fidelity of 98\%, in this metric and naturally in the FII index compared to competing models.

We investigate a generalized Chaplygin-like gas with an anisotropic equation of state, characterizing a dark fluid within which a static spherically symmetric black hole is assumed. By solving the Einstein equations for this black hole spacetime, we explicitly derive the metric function. The spacetime is parametrized by two critical parameters, $\mathcal{B}$ and $\alpha$, which measure the deviation from the Schwarzschild black hole and the extent of the dark fluid's anisotropy, respectively. We explore the behavior of light rays in the vicinity of the black hole by calculating its shadow and comparing our results with the Event Horizon Telescope observations. This comparison constrains the parameters to $0 \leq \mathcal{B} < 0.03$ and $0 < \alpha < 0.1$. Additionally, we calculate the deflection angles to determine the extent to which light is bent by the black hole. These calculations are further utilized to formulate possible Einstein rings, estimating the angular radius of the rings to be approximately $37.6\,\mathrm{\mu as}$. Throughout this work, we present analytical solutions wherever feasible, and employ reliable approximations where necessary to provide comprehensive insights into the spacetime characteristics and their observable effects., Comment: 24 pages, 10 figures, 2 tables

This study provides a comprehensive analytical investigation of the bound and unbound motion of magnetized particles orbiting a Schwarzschild black hole immersed in an external asymptotically uniform magnetic field, which includes all conceivable types of bounded and unbounded orbits. In particular, for planetary orbits, we perform a comparative analysis of our findings with the observed position of the S2 star carrying magnetic dipole moment around Sagittarius A* (Sgr A*). We found maximum and minimum values for the parameter of magnetic interaction between the magnetic dipole of the star and the external magnetic field, as well as the energy and angular momentum of the S2 star. As a result, we obtain estimations of the magnetic dipole of the star in order of $10^6 \rm \ G\cdot cm^{3}$. Additionally, we explore deflecting trajectories akin to gravitational Rutherford scattering. In obtaining the solutions for the orbital equations, we articulate the elliptic integrals and Jacobi elliptic functions, and our study is augmented by illustrative figures and simulations., Comment: 17 pages, 10 figures, 6 tables

We describe the design and results from the BraTS 2023 Intracranial Meningioma Segmentation Challenge. The BraTS Meningioma Challenge differed from prior BraTS Glioma challenges in that it focused on meningiomas, which are typically benign extra-axial tumors with diverse radiologic and anatomical presentation and a propensity for multiplicity. Nine participating teams each developed deep-learning automated segmentation models using image data from the largest multi-institutional systematically expert annotated multilabel multi-sequence meningioma MRI dataset to date, which included 1000 training set cases, 141 validation set cases, and 283 hidden test set cases. Each case included T2, T2/FLAIR, T1, and T1Gd brain MRI sequences with associated tumor compartment labels delineating enhancing tumor, non-enhancing tumor, and surrounding non-enhancing T2/FLAIR hyperintensity. Participant automated segmentation models were evaluated and ranked based on a scoring system evaluating lesion-wise metrics including dice similarity coefficient (DSC) and 95% Hausdorff Distance. The top ranked team had a lesion-wise median dice similarity coefficient (DSC) of 0.976, 0.976, and 0.964 for enhancing tumor, tumor core, and whole tumor, respectively and a corresponding average DSC of 0.899, 0.904, and 0.871, respectively. These results serve as state-of-the-art benchmarks for future pre-operative meningioma automated segmentation algorithms. Additionally, we found that 1286 of 1424 cases (90.3%) had at least 1 compartment voxel abutting the edge of the skull-stripped image edge, which requires further investigation into optimal pre-processing face anonymization steps., Comment: 16 pages, 11 tables, 10 figures, MICCAI

The 2024 Brain Tumor Segmentation Meningioma Radiotherapy (BraTS-MEN-RT) challenge aims to advance automated segmentation algorithms using the largest known multi-institutional dataset of radiotherapy planning brain MRIs with expert-annotated target labels for patients with intact or postoperative meningioma that underwent either conventional external beam radiotherapy or stereotactic radiosurgery. Each case includes a defaced 3D post-contrast T1-weighted radiotherapy planning MRI in its native acquisition space, accompanied by a single-label "target volume" representing the gross tumor volume (GTV) and any at-risk postoperative site. Target volume annotations adhere to established radiotherapy planning protocols, ensuring consistency across cases and institutions. For preoperative meningiomas, the target volume encompasses the entire GTV and associated nodular dural tail, while for postoperative cases, it includes at-risk resection cavity margins as determined by the treating institution. Case annotations were reviewed and approved by expert neuroradiologists and radiation oncologists. Participating teams will develop, containerize, and evaluate automated segmentation models using this comprehensive dataset. Model performance will be assessed using an adapted lesion-wise Dice Similarity Coefficient and the 95% Hausdorff distance. The top-performing teams will be recognized at the Medical Image Computing and Computer Assisted Intervention Conference in October 2024. BraTS-MEN-RT is expected to significantly advance automated radiotherapy planning by enabling precise tumor segmentation and facilitating tailored treatment, ultimately improving patient outcomes., Comment: 14 pages, 9 figures, 1 table

Gliomas are the most common malignant primary brain tumors in adults and one of the deadliest types of cancer. There are many challenges in treatment and monitoring due to the genetic diversity and high intrinsic heterogeneity in appearance, shape, histology, and treatment response. Treatments include surgery, radiation, and systemic therapies, with magnetic resonance imaging (MRI) playing a key role in treatment planning and post-treatment longitudinal assessment. The 2024 Brain Tumor Segmentation (BraTS) challenge on post-treatment glioma MRI will provide a community standard and benchmark for state-of-the-art automated segmentation models based on the largest expert-annotated post-treatment glioma MRI dataset. Challenge competitors will develop automated segmentation models to predict four distinct tumor sub-regions consisting of enhancing tissue (ET), surrounding non-enhancing T2/fluid-attenuated inversion recovery (FLAIR) hyperintensity (SNFH), non-enhancing tumor core (NETC), and resection cavity (RC). Models will be evaluated on separate validation and test datasets using standardized performance metrics utilized across the BraTS 2024 cluster of challenges, including lesion-wise Dice Similarity Coefficient and Hausdorff Distance. Models developed during this challenge will advance the field of automated MRI segmentation and contribute to their integration into clinical practice, ultimately enhancing patient care., Comment: 10 pages, 4 figures, 1 table

Deep learning classifiers are prone to latching onto dominant confounders present in a dataset rather than on the causal markers associated with the target class, leading to poor generalization and biased predictions. Although explainability via counterfactual image generation has been successful at exposing the problem, bias mitigation strategies that permit accurate explainability in the presence of dominant and diverse artifacts remain unsolved. In this work, we propose the DeCoDEx framework and show how an external, pre-trained binary artifact detector can be leveraged during inference to guide a diffusion-based counterfactual image generator towards accurate explainability. Experiments on the CheXpert dataset, using both synthetic artifacts and real visual artifacts (support devices), show that the proposed method successfully synthesizes the counterfactual images that change the causal pathology markers associated with Pleural Effusion while preserving or ignoring the visual artifacts. Augmentation of ERM and Group-DRO classifiers with the DeCoDEx generated images substantially improves the results across underrepresented groups that are out of distribution for each class. The code is made publicly available at https://github.com/NimaFathi/DeCoDEx., Comment: Accepted to Medical Imaging with Deep Learning (MIDL) 2024

Charge transfer is a fundamental interface process that can be harnessed for light detection, photovoltaics, and photosynthesis. Recently, charge transfer was exploited in nanophotonics to alter plasmon polaritons by involving additional non-polaritonic materials to activate the charge transfer. Yet, direct charge transfer between polaritonic materials hasn't been demonstrated. We report the direct charge transfer in pure polaritonic van der Waals (vdW) heterostructures of $\alpha$-MoO$_3$/graphene. We extracted the Fermi energy of 0.6 eV for graphene by infrared nano-imaging of charge transfer hyperbolic polaritons in the vdW heterostructure. This unusually high Fermi energy is attributed to the charge transfer between graphene and $\alpha$-MoO$_3$. Moreover, we have observed charge transfer hyperbolic polaritons in multiple energy-momentum dispersion branches with a wavelength elongation of up to 150%. With support from the DFT calculation, we find that the charge transfer between graphene and $\alpha$-MoO$_3$, absent in mechanically assembled vdW heterostructures, is attributed to the relatively pristine heterointerface preserved in the epitaxially grown vdW heterostructure. The direct charge transfer and charge transfer hyperbolic polaritons demonstrated in our work hold great promise for developing nano-optical circuits, computational devices, communication systems, and light and energy manipulation devices.

We resolve a question of Carrapatoso et al. on Gaussian optimality for the sharp constant in Poincar\'e-Korn inequalities, under a moment constraint. We also prove stability, showing that measures with near-optimal constant are quantitatively close to standard Gaussian.

Pediatric tumors of the central nervous system are the most common cause of cancer-related death in children. The five-year survival rate for high-grade gliomas in children is less than 20%. Due to their rarity, the diagnosis of these entities is often delayed, their treatment is mainly based on historic treatment concepts, and clinical trials require multi-institutional collaborations. Here we present the CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs challenge, focused on pediatric brain tumors with data acquired across multiple international consortia dedicated to pediatric neuro-oncology and clinical trials. The CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs challenge brings together clinicians and AI/imaging scientists to lead to faster development of automated segmentation techniques that could benefit clinical trials, and ultimately the care of children with brain tumors., Comment: arXiv admin note: substantial text overlap with arXiv:2305.17033

In a recent work, Klartag gave an improved version of Lichnerowicz' spectral gap bound for uniformly log-concave measures, which improves on the classical estimate by taking into account the covariance matrix. We analyze the equality cases in Klartag's bound, showing that it can be further improved whenever the measure has no Gaussian factor. Additionally, we give a quantitative improvement for log-concave measures with finite Fisher information.

In this paper, we propose a novel warm restart technique using a new logarithmic step size for the stochastic gradient descent (SGD) approach. For smooth and non-convex functions, we establish an $O(\frac{1}{\sqrt{T}})$ convergence rate for the SGD. We conduct a comprehensive implementation to demonstrate the efficiency of the newly proposed step size on the ~FashionMinst,~ CIFAR10, and CIFAR100 datasets. Moreover, we compare our results with nine other existing approaches and demonstrate that the new logarithmic step size improves test accuracy by $0.9\%$ for the CIFAR100 dataset when we utilize a convolutional neural network (CNN) model.

In this work, we introduce the Skorokhod energy of a simply connected domain. We show that among all domains solving the planar Skorokhod embedding problem, Gross solution generates the domain with the minimal Skorokhod energy.

In the era of personalized education, the provision of comprehensible explanations for learning recommendations is of a great value to enhance the learner's understanding and engagement with the recommended learning content. Large language models (LLMs) and generative AI in general have recently opened new doors for generating human-like explanations, for and along learning recommendations. However, their precision is still far away from acceptable in a sensitive field like education. To harness the abilities of LLMs, while still ensuring a high level of precision towards the intent of the learners, this paper proposes an approach to utilize knowledge graphs (KG) as a source of factual context, for LLM prompts, reducing the risk of model hallucinations, and safeguarding against wrong or imprecise information, while maintaining an application-intended learning context. We utilize the semantic relations in the knowledge graph to offer curated knowledge about learning recommendations. With domain-experts in the loop, we design the explanation as a textual template, which is filled and completed by the LLM. Domain experts were integrated in the prompt engineering phase as part of a study, to ensure that explanations include information that is relevant to the learner. We evaluate our approach quantitatively using Rouge-N and Rouge-L measures, as well as qualitatively with experts and learners. Our results show an enhanced recall and precision of the generated explanations compared to those generated solely by the GPT model, with a greatly reduced risk of generating imprecise information in the final learning explanation.

In this paper, we address web-scale visual entity recognition, specifically the task of mapping a given query image to one of the 6 million existing entities in Wikipedia. One way of approaching a problem of such scale is using dual-encoder models (eg CLIP), where all the entity names and query images are embedded into a unified space, paving the way for an approximate k-NN search. Alternatively, it is also possible to re-purpose a captioning model to directly generate the entity names for a given image. In contrast, we introduce a novel Generative Entity Recognition (GER) framework, which given an input image learns to auto-regressively decode a semantic and discriminative ``code'' identifying the target entity. Our experiments demonstrate the efficacy of this GER paradigm, showcasing state-of-the-art performance on the challenging OVEN benchmark. GER surpasses strong captioning, dual-encoder, visual matching and hierarchical classification baselines, affirming its advantage in tackling the complexities of web-scale recognition., Comment: CVPR2024

This paper introduces SceneCraft, a Large Language Model (LLM) Agent converting text descriptions into Blender-executable Python scripts which render complex scenes with up to a hundred 3D assets. This process requires complex spatial planning and arrangement. We tackle these challenges through a combination of advanced abstraction, strategic planning, and library learning. SceneCraft first models a scene graph as a blueprint, detailing the spatial relationships among assets in the scene. SceneCraft then writes Python scripts based on this graph, translating relationships into numerical constraints for asset layout. Next, SceneCraft leverages the perceptual strengths of vision-language foundation models like GPT-V to analyze rendered images and iteratively refine the scene. On top of this process, SceneCraft features a library learning mechanism that compiles common script functions into a reusable library, facilitating continuous self-improvement without expensive LLM parameter tuning. Our evaluation demonstrates that SceneCraft surpasses existing LLM-based agents in rendering complex scenes, as shown by its adherence to constraints and favorable human assessments. We also showcase the broader application potential of SceneCraft by reconstructing detailed 3D scenes from the Sintel movie and guiding a video generative model with generated scenes as intermediary control signal.