Search

We introduce Phi-4-Mini and Phi-4-Multimodal, compact yet highly capable language and multimodal models. Phi-4-Mini is a 3.8-billion-parameter language model trained on high-quality web and synthetic data, significantly outperforming recent open-source models of similar size and matching the performance of models twice its size on math and coding tasks requiring complex reasoning. This achievement is driven by a carefully curated synthetic data recipe emphasizing high-quality math and coding datasets. Compared to its predecessor, Phi-3.5-Mini, Phi-4-Mini features an expanded vocabulary size of 200K tokens to better support multilingual applications, as well as group query attention for more efficient long-sequence generation. Phi-4-Multimodal is a multimodal model that integrates text, vision, and speech/audio input modalities into a single model. Its novel modality extension approach leverages LoRA adapters and modality-specific routers to allow multiple inference modes combining various modalities without interference. For example, it now ranks first in the OpenASR leaderboard to date, although the LoRA component of the speech/audio modality has just 460 million parameters. Phi-4-Multimodal supports scenarios involving (vision + language), (vision + speech), and (speech/audio) inputs, outperforming larger vision-language and speech-language models on a wide range of tasks. Additionally, we experiment to further train Phi-4-Mini to enhance its reasoning capabilities. Despite its compact 3.8-billion-parameter size, this experimental version achieves reasoning performance on par with or surpassing significantly larger models, including DeepSeek-R1-Distill-Qwen-7B and DeepSeek-R1-Distill-Llama-8B., Comment: 39 pages

Temporal awareness is crucial in many information retrieval tasks, particularly in scenarios where the relevance of documents depends on their alignment with the query's temporal context. Traditional retrieval methods such as BM25 and Dense Passage Retrieval (DPR) excel at capturing lexical and semantic relevance but fall short in addressing time-sensitive queries. To bridge this gap, we introduce the temporal retrieval model that integrates explicit temporal signals by incorporating query timestamps and document dates into the representation space. Our approach ensures that retrieved passages are not only topically relevant but also temporally aligned with user intent. We evaluate our approach on two large-scale benchmark datasets, ArchivalQA and ChroniclingAmericaQA, achieving substantial performance gains over standard retrieval baselines. In particular, our model improves Top-1 retrieval accuracy by 6.63% and NDCG@10 by 3.79% on ArchivalQA, while yielding a 9.56% boost in Top-1 retrieval accuracy and 4.68% in NDCG@10 on ChroniclingAmericaQA. Additionally, we introduce a time-sensitive negative sampling strategy, which refines the model's ability to distinguish between temporally relevant and irrelevant documents during training. Our findings highlight the importance of explicitly modeling time in retrieval systems and set a new standard for handling temporally grounded queries.

Knowledge-intensive tasks, particularly open-domain question answering (ODQA), document reranking, and retrieval-augmented language modeling, require a balance between retrieval accuracy and generative flexibility. Traditional retrieval models such as BM25 and Dense Passage Retrieval (DPR), efficiently retrieve from large corpora but often lack semantic depth. Generative models like GPT-4-o provide richer contextual understanding but face challenges in maintaining factual consistency. In this work, we conduct a systematic evaluation of retrieval-based, generation-based, and hybrid models, with a primary focus on their performance in ODQA and related retrieval-augmented tasks. Our results show that dense retrievers, particularly DPR, achieve strong performance in ODQA with a top-1 accuracy of 50.17\% on NQ, while hybrid models improve nDCG@10 scores on BEIR from 43.42 (BM25) to 52.59, demonstrating their strength in document reranking. Additionally, we analyze language modeling tasks using WikiText-103, showing that retrieval-based approaches like BM25 achieve lower perplexity compared to generative and hybrid methods, highlighting their utility in retrieval-augmented generation. By providing detailed comparisons and practical insights into the conditions where each approach excels, we aim to facilitate future optimizations in retrieval, reranking, and generative models for ODQA and related knowledge-intensive applications., Comment: work on progress

Thematic analysis of social media posts provides a major understanding of public discourse, yet traditional methods often struggle to capture the complexity and nuance of unstructured, large-scale text data. This study introduces a novel methodology for thematic analysis that integrates tweet embeddings from pre-trained language models, dimensionality reduction using and matrix factorization, and generative AI to identify and refine latent themes. Our approach clusters compressed tweet representations and employs generative AI to extract and articulate themes through an agentic Chain of Thought (CoT) prompting, with a secondary LLM for quality assurance. This methodology is applied to tweets from the autistic community, a group that increasingly uses social media to discuss their experiences and challenges. By automating the thematic extraction process, the aim is to uncover key insights while maintaining the richness of the original discourse. This autism case study demonstrates the utility of the proposed approach in improving thematic analysis of social media data, offering a scalable and adaptable framework that can be applied to diverse contexts. The results highlight the potential of combining machine learning and Generative AI to enhance the depth and accuracy of theme identification in online communities.

Optical Character Recognition (OCR) plays a crucial role in digitizing historical and multilingual documents, yet OCR errors -- imperfect extraction of the text, including character insertion, deletion and permutation -- can significantly impact downstream tasks like question-answering (QA). In this work, we introduce a multilingual QA dataset MultiOCR-QA, designed to analyze the effects of OCR noise on QA systems' performance. The MultiOCR-QA dataset comprises 60K question-answer pairs covering three languages, English, French, and German. The dataset is curated from OCR-ed old documents, allowing for the evaluation of OCR-induced challenges on question answering. We evaluate MultiOCR-QA on various levels and types of OCR errors to access the robustness of LLMs in handling real-world digitization errors. Our findings show that QA systems are highly prone to OCR induced errors and exhibit performance degradation on noisy OCR text.

Large Language Models (LLMs) are revolutionizing information retrieval, with chatbots becoming an important source for answering user queries. As by their design, LLMs prioritize generating correct answers, the value of highly plausible yet incorrect answers (candidate answers) tends to be overlooked. However, such answers can still prove useful, for example, they can play a crucial role in tasks like Multiple-Choice Question Answering (MCQA) and QA Robustness Assessment (QARA). Existing QA datasets primarily focus on correct answers without explicit consideration of the plausibility of other candidate answers, limiting opportunity for more nuanced evaluations of models. To address this gap, we introduce PlausibleQA, a large-scale dataset comprising 10,000 questions and 100,000 candidate answers, each annotated with plausibility scores and justifications for their selection. Additionally, the dataset includes 900,000 justifications for pairwise comparisons between candidate answers, further refining plausibility assessments. We evaluate PlausibleQA through human assessments and empirical experiments, demonstrating its utility in MCQA and QARA analysis. Our findings show that plausibility-aware approaches are effective for MCQA distractor generation and QARA. We release PlausibleQA as a resource for advancing QA research and enhancing LLM performance in distinguishing plausible distractors from correct answers., Comment: Submitted to SIGIR 2025

This document summarizes the main ideas of the finite element method (FEM) theory and constitutive relations as implemented in the PHIMATS code (\href{https://github.com/ahcomat/PHIMATS.git}{GitHub Repository}). Rather than detailing the derivations or specific models, this document focuses on the key mathematical foundations and numerical strategies used within the implementation. For in-depth theoretical discussions, the reader is encouraged to consult the references. For citing this document, please use ... Hands-on examples can be found in CaseStudies directory on the GitHub repository. .

Despite progress in Arabic large language models, such as Jais and AceGPT, their evaluation on commonsense reasoning has largely relied on machine-translated datasets, which lack cultural depth and may introduce Anglocentric biases. Commonsense reasoning is shaped by geographical and cultural contexts, and existing English datasets fail to capture the diversity of the Arab world. To address this, we introduce \datasetname, a commonsense reasoning dataset in Modern Standard Arabic (MSA), covering cultures of 13 countries across the Gulf, Levant, North Africa, and the Nile Valley. The dataset was built from scratch by engaging native speakers to write and validate culturally relevant questions for their respective countries. \datasetname spans 12 daily life domains with 54 fine-grained subtopics, reflecting various aspects of social norms, traditions, and everyday experiences. Zero-shot evaluations show that open-weight language models with up to 32B parameters struggle to comprehend diverse Arab cultures, with performance varying across regions. These findings highlight the need for more culturally aware models and datasets tailored to the Arabic-speaking world.

To date, no observational confirmation of dark matter particles has been found. In this paper, we put forward an alternative approach to inferring evidence for dark matter through modified gravity, without invoking fundamental dark matter particles. Specifically, we explore the possibility of extracting signatures of Kaluza-Klein gravity through the gravitational Aharonov-Bohm effect. Kaluza-Klein theory has recently been proposed as an alternative to the dark sector, and predicts a tower of particles, including spin-0 and spin-1 gravitons alongside the usual spin-2 gravitons, which can gravitationally couple to matter. We thus analyze a quantum system in free fall around a gravitating body in the presence of a modified Yukawa-like gravitational potential, and determine the gravitational phase induced by the additional degrees of freedom introduced by the Kaluza-Klein model. Our results reveal that, in addition to the usual result from General Relativity, the quantum wave function of the system exhibits an additional effect: a splitting of the energy levels with a new quantum number due to the extra vector gravitational degrees of freedom. The energy splitting difference between general relativity and Kaluza-Klein gravity is found to be of the order of meV for an atomic system and eV for a nuclear system. Similar values also arise in generic modified gravity models and can be feasibly tested in the future. Numerical estimates for the graviton mass are also provided, and potential imprints on gravitational waves are mentioned., Comment: v1: 13 pages, 2 figures, 4 tables

We present the first text-based image editing approach for object parts based on pre-trained diffusion models. Diffusion-based image editing approaches capitalized on the deep understanding of diffusion models of image semantics to perform a variety of edits. However, existing diffusion models lack sufficient understanding of many object parts, hindering fine-grained edits requested by users. To address this, we propose to expand the knowledge of pre-trained diffusion models to allow them to understand various object parts, enabling them to perform fine-grained edits. We achieve this by learning special textual tokens that correspond to different object parts through an efficient token optimization process. These tokens are optimized to produce reliable localization masks at each inference step to localize the editing region. Leveraging these masks, we design feature-blending and adaptive thresholding strategies to execute the edits seamlessly. To evaluate our approach, we establish a benchmark and an evaluation protocol for part editing. Experiments show that our approach outperforms existing editing methods on all metrics and is preferred by users 77-90% of the time in conducted user studies., Comment: Project page: https://partedit.github.io/PartEdit/

Neuromorphic vision sensors, commonly referred to as event cameras, have recently gained relevance for applications requiring high-speed, high dynamic range and low-latency data acquisition. Unlike traditional frame-based cameras that capture 2D images, event cameras generate a massive number of pixel-level events, composed by spatiotemporal and polarity information, with very high temporal resolution, thus demanding highly efficient coding solutions. Existing solutions focus on lossless coding of event data, assuming that no distortion is acceptable for the target use cases, mostly including computer vision tasks. One promising coding approach exploits the similarity between event data and point clouds, thus allowing to use current point cloud coding solutions to code event data, typically adopting a two-point clouds representation, one for each event polarity. This paper proposes a novel lossy Deep Learning-based Joint Event data Coding (DL-JEC) solution adopting a single-point cloud representation, thus enabling to exploit the correlation between the spatiotemporal and polarity event information. DL-JEC can achieve significant compression performance gains when compared with relevant conventional and DL-based state-of-the-art event data coding solutions. Moreover, it is shown that it is possible to use lossy event data coding with its reduced rate regarding lossless coding without compromising the target computer vision task performance, notably for event classification. The use of novel adaptive voxel binarization strategies, adapted to the target task, further enables DL-JEC to reach a superior performance.

Retrieval, re-ranking, and retrieval-augmented generation (RAG) are critical components of modern applications in information retrieval, question answering, or knowledge-based text generation. However, existing solutions are often fragmented, lacking a unified framework that easily integrates these essential processes. The absence of a standardized implementation, coupled with the complexity of retrieval and re-ranking workflows, makes it challenging for researchers to compare and evaluate different approaches in a consistent environment. While existing toolkits such as Rerankers and RankLLM provide general-purpose reranking pipelines, they often lack the flexibility required for fine-grained experimentation and benchmarking. In response to these challenges, we introduce Rankify, a powerful and modular open-source toolkit designed to unify retrieval, re-ranking, and RAG within a cohesive framework. Rankify supports a wide range of retrieval techniques, including dense and sparse retrievers, while incorporating state-of-the-art re-ranking models to enhance retrieval quality. Additionally, Rankify includes a collection of pre-retrieved datasets to facilitate benchmarking, available at Huggingface (https://huggingface.co/datasets/abdoelsayed/reranking-datasets-light). To encourage adoption and ease of integration, we provide comprehensive documentation (http://rankify.readthedocs.io/), an open-source implementation on GitHub (https://github.com/DataScienceUIBK/rankify), and a PyPI package for easy installation (https://pypi.org/project/rankify/). As a unified and lightweight framework, Rankify allows researchers and practitioners to advance retrieval and re-ranking methodologies while ensuring consistency, scalability, and ease of use., Comment: Work in Progress

Large Language Models (LLMs) are transforming how people find information, and many users turn nowadays to chatbots to obtain answers to their questions. Despite the instant access to abundant information that LLMs offer, it is still important to promote critical thinking and problem-solving skills. Automatic hint generation is a new task that aims to support humans in answering questions by themselves by creating hints that guide users toward answers without directly revealing them. In this context, hint evaluation focuses on measuring the quality of hints, helping to improve the hint generation approaches. However, resources for hint research are currently spanning different formats and datasets, while the evaluation tools are missing or incompatible, making it hard for researchers to compare and test their models. To overcome these challenges, we introduce HintEval, a Python library that makes it easy to access diverse datasets and provides multiple approaches to generate and evaluate hints. HintEval aggregates the scattered resources into a single toolkit that supports a range of research goals and enables a clear, multi-faceted, and reliable evaluation. The proposed library also includes detailed online documentation, helping users quickly explore its features and get started. By reducing barriers to entry and encouraging consistent evaluation practices, HintEval offers a major step forward for facilitating hint generation and analysis research within the NLP/IR community., Comment: Submitted to SIGIR 2025

Retrieval-Augmented Generation (RAG) models have drawn considerable attention in modern open-domain question answering. The effectiveness of RAG depends on the quality of the top retrieved documents. However, conventional retrieval methods sometimes fail to rank the most relevant documents at the top. In this paper, we introduce ASRank, a new re-ranking method based on scoring retrieved documents using zero-shot answer scent which relies on a pre-trained large language model to compute the likelihood of the document-derived answers aligning with the answer scent. Our approach demonstrates marked improvements across several datasets, including NQ, TriviaQA, WebQA, ArchivalQA, HotpotQA, and Entity Questions. Notably, ASRank increases Top-1 retrieval accuracy on NQ from $19.2\%$ to $46.5\%$ for MSS and $22.1\%$ to $47.3\%$ for BM25. It also shows strong retrieval performance on several datasets compared to state-of-the-art methods (47.3 Top-1 by ASRank vs 35.4 by UPR by BM25)., Comment: Accepted At NAACL 2025

Anomaly detection from images captured using camera sensors is one of the mainstream applications at the industrial level. Particularly, it maintains the quality and optimizes the efficiency in production processes across diverse industrial tasks, including advanced manufacturing and aerospace engineering. Traditional anomaly detection workflow is based on a manual inspection by human operators, which is a tedious task. Advances in intelligent automated inspection systems have revolutionized the Industrial Anomaly Detection (IAD) process. Recent vision-based approaches can automatically extract, process, and interpret features using computer vision and align with the goals of automation in industrial operations. In light of the shift in inspection methodologies, this survey reviews studies published since 2019, with a specific focus on vision-based anomaly detection. The components of an IAD pipeline that are overlooked in existing surveys are presented, including areas related to data acquisition, preprocessing, learning mechanisms, and evaluation. In addition to the collected publications, several scientific and industry-related challenges and their perspective solutions are highlighted. Popular and relevant industrial datasets are also summarized, providing further insight into inspection applications. Finally, future directions of vision-based IAD are discussed, offering researchers insight into the state-of-the-art of industrial inspection.

Would not it be much more convenient for everybody to try on clothes by only looking into a mirror ? The answer to that problem is virtual try-on, enabling users to digitally experiment with outfits. The core challenge lies in realistic image-to-image translation, where clothing must fit diverse human forms, poses, and figures. Early methods, which used 2D transformations, offered speed, but image quality was often disappointing and lacked the nuance of deep learning. Though GAN-based techniques enhanced realism, their dependence on paired data proved limiting. More adaptable methods offered great visuals but demanded significant computing power and time. Recent advances in diffusion models have shown promise for high-fidelity translation, yet the current crop of virtual try-on tools still struggle with detail loss and warping issues. To tackle these challenges, this paper proposes EfficientVITON, a new virtual try-on system leveraging the impressive pre-trained Stable Diffusion model for better images and deployment feasibility. The system includes a spatial encoder to maintain clothings finer details and zero cross-attention blocks to capture the subtleties of how clothes fit a human body. Input images are carefully prepared, and the diffusion process has been tweaked to significantly cut generation time without image quality loss. The training process involves two distinct stages of fine-tuning, carefully incorporating a balance of loss functions to ensure both accurate try-on results and high-quality visuals. Rigorous testing on the VITON-HD dataset, supplemented with real-world examples, has demonstrated that EfficientVITON achieves state-of-the-art results., Comment: 7 pages

Knowledge graphs are an efficient method for representing and connecting information across various concepts, useful in reasoning, question answering, and knowledge base completion tasks. They organize data by linking points, enabling researchers to combine diverse information sources into a single database. This interdisciplinary approach helps uncover new research questions and ideas. Knowledge graphs create a web of data points (nodes) and their connections (edges), which enhances navigation, comprehension, and utilization of data for multiple purposes. They capture complex relationships inherent in unstructured data sources, offering a semantic framework for diverse entities and their attributes. Strategies for developing knowledge graphs include using seed data, named entity recognition, and relationship extraction. These graphs enhance chatbot accuracy and include multimedia data for richer information. Creating high-quality knowledge graphs involves both automated methods and human oversight, essential for accurate and comprehensive data representation.

Understanding hydrogen-grain boundary (GB) interactions is critical to the analysis of hydrogen embrittlement in metals. This work presents a mesoscale fully kinetic model to investigate the effect of GB misorientation on hydrogen diffusion and trapping using phase-field based representative volume elements (RVEs). The flux equation consists of three terms: a diffusive term and two terms for high and low angle grain boundary (H/LAGB) trapping. Uptake simulations showed that decreasing the grain size resulted in higher hydrogen content due to increasing the GB density. Permeation simulations showed that GBs are high flux paths due to their higher enrichment with hydrogen. Since HAGBs have higher enrichment than LAGBs, due to their higher trap-binding energy, they generally have the highest hydrogen flux. Nevertheless, the flux shows a convoluted behavior as it depends on the local concentration, alignment of GB with external concentration gradient as well as the GB network connectivity. Finally, decreasing the grain size resulted in a larger break-through time and a larger steady-state exit flux.

Hydrogen grain boundary (GB) trapping is widely accepted as the main cause for hydrogen induced intergranular failure. Several studies were conducted to unveil the role of GBs on hydrogen transport; however, a clear understanding is yet to be attained. This is due to the limitations of the state-of-the-art experimental procedures for such highly kinetic processes. In this study, we aim at providing a deeper understanding of hydrogen-GB interactions using full-field representative volume element (RVE). The phase-field method is chosen for generating RVEs, since it is the an appropriate numerical tool to represent GBs. A novel fully-kinetic formulation for hydrogen diffusion and GB trapping is presented, which is compatible with the phase-field based RVEs. GB diffusivity ($D_\mathrm{gb}$) and trap-binding energy ($E_\mathrm{gb}$) were used as parameters to understand the interactions between diffusion and GB trapping. Uptake and permeation simulations were performed with constant and gradient occupancy boundary conditions respectively. In both cases, increasing $E_\mathrm{gb}$, increased the hydrogen GB occupancy. The permeation simulations showed that the hydrogen flux along the GBs increased with increasing both, $D_\mathrm{gb}$ and, surprisingly, $E_\mathrm{gb}$. Since trapping increases the hydrogen occupancy along GBs, it also increases the occupancy gradients, resulting in a higher flux. This led to the conclusion that, in the case of an external occupancy gradient, GB trapping and diffusion cooperate, rather than compete, to increase the hydrogen flux. On the other hand, the decisive factor for the retention of hydrogen at the GBs in permeation simulations was $D_\mathrm{gb}$ rather than $E_\mathrm{gb}$.

This paper presents ERPA, an innovative Robotic Process Automation (RPA) model designed to enhance ID data extraction and optimize Optical Character Recognition (OCR) tasks within immigration workflows. Traditional RPA solutions often face performance limitations when processing large volumes of documents, leading to inefficiencies. ERPA addresses these challenges by incorporating Large Language Models (LLMs) to improve the accuracy and clarity of extracted text, effectively handling ambiguous characters and complex structures. Benchmark comparisons with leading platforms like UiPath and Automation Anywhere demonstrate that ERPA significantly reduces processing times by up to 94 percent, completing ID data extraction in just 9.94 seconds. These findings highlight ERPA's potential to revolutionize document automation, offering a faster and more reliable alternative to current RPA solutions., Comment: 6 pages , 2 figures, 1 algorithm

Street view imagery (SVI) has been instrumental in many studies in the past decade to understand and characterize street features and the built environment. Researchers across a variety of domains, such as transportation, health, architecture, human perception, and infrastructure have employed different methods to analyze SVI. However, these applications and image-processing procedures have not been standardized, and solutions have been implemented in isolation, often making it difficult for others to reproduce existing work and carry out new research. Using SVI for research requires multiple technical steps: accessing APIs for scalable data collection, preprocessing images to standardize formats, implementing computer vision models for feature extraction, and conducting spatial analysis. These technical requirements create barriers for researchers in urban studies, particularly those without extensive programming experience. We developed ZenSVI, a free and open-source Python package that integrates and implements the entire process of SVI analysis, supporting a wide range of use cases. Its end-to-end pipeline includes downloading SVI from multiple platforms (e.g., Mapillary and KartaView) efficiently, analyzing metadata of SVI, applying computer vision models to extract target features, transforming SVI into different projections (e.g., fish-eye and perspective) and different formats (e.g., depth map and point cloud), visualizing analyses with maps and plots, and exporting outputs to other software tools. We demonstrated its use in Singapore through a case study of data quality assessment and clustering analysis in a streamlined manner. Our software improves the transparency, reproducibility, and scalability of research relying on SVI and supports researchers in conducting urban analyses efficiently. Its modular design facilitates extensions of the package for new use cases.

This paper introduces LMRPA, a novel Large Model-Driven Robotic Process Automation (RPA) model designed to greatly improve the efficiency and speed of Optical Character Recognition (OCR) tasks. Traditional RPA platforms often suffer from performance bottlenecks when handling high-volume repetitive processes like OCR, leading to a less efficient and more time-consuming process. LMRPA allows the integration of Large Language Models (LLMs) to improve the accuracy and readability of extracted text, overcoming the challenges posed by ambiguous characters and complex text structures.Extensive benchmarks were conducted comparing LMRPA to leading RPA platforms, including UiPath and Automation Anywhere, using OCR engines like Tesseract and DocTR. The results are that LMRPA achieves superior performance, cutting the processing times by up to 52\%. For instance, in Batch 2 of the Tesseract OCR task, LMRPA completed the process in 9.8 seconds, where UiPath finished in 18.1 seconds and Automation Anywhere finished in 18.7 seconds. Similar improvements were observed with DocTR, where LMRPA outperformed other automation tools conducting the same process by completing tasks in 12.7 seconds, while competitors took over 20 seconds to do the same. These findings highlight the potential of LMRPA to revolutionize OCR-driven automation processes, offering a more efficient and effective alternative solution to the existing state-of-the-art RPA models., Comment: 10 pages , 1 figure , 1 algorithm

Cryptic crosswords are puzzles that rely on general knowledge and the solver's ability to manipulate language on different levels, dealing with various types of wordplay. Previous research suggests that solving such puzzles is challenging even for modern NLP models, including Large Language Models (LLMs). However, there is little to no research on the reasons for their poor performance on this task. In this paper, we establish the benchmark results for three popular LLMs: Gemma2, LLaMA3 and ChatGPT, showing that their performance on this task is still significantly below that of humans. We also investigate why these models struggle to achieve superior performance. We release our code and introduced datasets at https://github.com/bodasadallah/decrypting-crosswords., Comment: COLING 2025. arXiv admin note: text overlap with arXiv:2403.12094

Image reflection removal is crucial for restoring image quality. Distorted images can negatively impact tasks like object detection and image segmentation. In this paper, we present a novel approach for image reflection removal using a single image. Instead of focusing on model architecture, we introduce a new training technique that can be generalized to image-to-image problems, with input and output being similar in nature. This technique is embodied in our multi-step loss mechanism, which has proven effective in the reflection removal task. Additionally, we address the scarcity of reflection removal training data by synthesizing a high-quality, non-linear synthetic dataset called RefGAN using Pix2Pix GAN. This dataset significantly enhances the model's ability to learn better patterns for reflection removal. We also utilize a ranged depth map, extracted from the depth estimation of the ambient image, as an auxiliary feature, leveraging its property of lacking depth estimations for reflections. Our approach demonstrates superior performance on the SIR^2 benchmark and other real-world datasets, proving its effectiveness by outperforming other state-of-the-art models., Comment: 6 pages, 6 figures, IEEE AICCSA 2024

Mental health disorders are increasingly prevalent worldwide, creating an urgent need for innovative tools to support early diagnosis and intervention. This study explores the potential of Large Language Models (LLMs) in multimodal mental health diagnostics, specifically for detecting depression and Post Traumatic Stress Disorder through text and audio modalities. Using the E-DAIC dataset, we compare text and audio modalities to investigate whether LLMs can perform equally well or better with audio inputs. We further examine the integration of both modalities to determine if this can enhance diagnostic accuracy, which generally results in improved performance metrics. Our analysis specifically utilizes custom-formulated metrics; Modal Superiority Score and Disagreement Resolvement Score to evaluate how combined modalities influence model performance. The Gemini 1.5 Pro model achieves the highest scores in binary depression classification when using the combined modality, with an F1 score of 0.67 and a Balanced Accuracy (BA) of 77.4%, assessed across the full dataset. These results represent an increase of 3.1% over its performance with the text modality and 2.7% over the audio modality, highlighting the effectiveness of integrating modalities to enhance diagnostic accuracy. Notably, all results are obtained in zero-shot inferring, highlighting the robustness of the models without requiring task-specific fine-tuning. To explore the impact of different configurations on model performance, we conduct binary, severity, and multiclass tasks using both zero-shot and few-shot prompts, examining the effects of prompt variations on performance. The results reveal that models such as Gemini 1.5 Pro in text and audio modalities, and GPT-4o mini in the text modality, often surpass other models in balanced accuracy and F1 scores across multiple tasks.

We propose a novel zero-shot approach for keypoint detection on 3D shapes. Point-level reasoning on visual data is challenging as it requires precise localization capability, posing problems even for powerful models like DINO or CLIP. Traditional methods for 3D keypoint detection rely heavily on annotated 3D datasets and extensive supervised training, limiting their scalability and applicability to new categories or domains. In contrast, our method utilizes the rich knowledge embedded within Multi-Modal Large Language Models (MLLMs). Specifically, we demonstrate, for the first time, that pixel-level annotations used to train recent MLLMs can be exploited for both extracting and naming salient keypoints on 3D models without any ground truth labels or supervision. Experimental evaluations demonstrate that our approach achieves competitive performance on standard benchmarks compared to supervised methods, despite not requiring any 3D keypoint annotations during training. Our results highlight the potential of integrating language models for localized 3D shape understanding. This work opens new avenues for cross-modal learning and underscores the effectiveness of MLLMs in contributing to 3D computer vision challenges., Comment: Project website is accessible at https://sites.google.com/view/zerokey

This paper presents DynRank, a novel framework for enhancing passage retrieval in open-domain question-answering systems through dynamic zero-shot question classification. Traditional approaches rely on static prompts and pre-defined templates, which may limit model adaptability across different questions and contexts. In contrast, DynRank introduces a dynamic prompting mechanism, leveraging a pre-trained question classification model that categorizes questions into fine-grained types. Based on these classifications, contextually relevant prompts are generated, enabling more effective passage retrieval. We integrate DynRank into existing retrieval frameworks and conduct extensive experiments on multiple QA benchmark datasets., Comment: Accepted at Coling2025

Existing Large Multimodal Models (LMMs) generally focus on only a few regions and languages. As LMMs continue to improve, it is increasingly important to ensure they understand cultural contexts, respect local sensitivities, and support low-resource languages, all while effectively integrating corresponding visual cues. In pursuit of culturally diverse global multimodal models, our proposed All Languages Matter Benchmark (ALM-bench) represents the largest and most comprehensive effort to date for evaluating LMMs across 100 languages. ALM-bench challenges existing models by testing their ability to understand and reason about culturally diverse images paired with text in various languages, including many low-resource languages traditionally underrepresented in LMM research. The benchmark offers a robust and nuanced evaluation framework featuring various question formats, including true/false, multiple choice, and open-ended questions, which are further divided into short and long-answer categories. ALM-bench design ensures a comprehensive assessment of a model's ability to handle varied levels of difficulty in visual and linguistic reasoning. To capture the rich tapestry of global cultures, ALM-bench carefully curates content from 13 distinct cultural aspects, ranging from traditions and rituals to famous personalities and celebrations. Through this, ALM-bench not only provides a rigorous testing ground for state-of-the-art open and closed-source LMMs but also highlights the importance of cultural and linguistic inclusivity, encouraging the development of models that can serve diverse global populations effectively. Our benchmark is publicly available., Comment: A Multilingual Multimodal cultural benchmark for 100 languages

Identifying key pathological features in brain MRIs is crucial for the long-term survival of glioma patients. However, manual segmentation is time-consuming, requiring expert intervention and is susceptible to human error. Therefore, significant research has been devoted to developing machine learning methods that can accurately segment tumors in 3D multimodal brain MRI scans. Despite their progress, state-of-the-art models are often limited by the data they are trained on, raising concerns about their reliability when applied to diverse populations that may introduce distribution shifts. Such shifts can stem from lower quality MRI technology (e.g., in sub-Saharan Africa) or variations in patient demographics (e.g., children). The BraTS-2024 challenge provides a platform to address these issues. This study presents our methodology for segmenting tumors in the BraTS-2024 SSA and Pediatric Tumors tasks using MedNeXt, comprehensive model ensembling, and thorough postprocessing. Our approach demonstrated strong performance on the unseen validation set, achieving an average Dice Similarity Coefficient (DSC) of 0.896 on the BraTS-2024 SSA dataset and an average DSC of 0.830 on the BraTS Pediatric Tumor dataset. Additionally, our method achieved an average Hausdorff Distance (HD95) of 14.682 on the BraTS-2024 SSA dataset and an average HD95 of 37.508 on the BraTS Pediatric dataset. Our GitHub repository can be accessed here: Project Repository : https://github.com/python-arch/BioMbz-Optimizing-Brain-Tumor-Segmentation-with-MedNeXt-BraTS-2024-SSA-and-Pediatrics

In this paper, we present a novel approach for fluid dynamic simulations by harnessing the capabilities of Physics-Informed Neural Networks (PINNs) guided by the newly unveiled principle of minimum pressure gradient (PMPG). In a PINN formulation, the physics problem is converted into a minimization problem (typically least squares). The PMPG asserts that for incompressible flows, the total magnitude of the pressure gradient over the domain must be minimum at every time instant, turning fluid mechanics into minimization problems, making it an excellent choice for PINNs formulation. Following the PMPG, the proposed PINN formulation seeks to construct a neural network for the flow field that minimizes Nature's cost function for incompressible flows in contrast to traditional PINNs that minimize the residuals of the Navier-Stokes equations. This technique eliminates the need to train a separate pressure model, thereby reducing training time and computational costs. We demonstrate the effectiveness of this approach through a case study of inviscid flow around a cylinder, showing its ability to capture the underlying physics, while reducing computational cost and training time. The proposed approach outperforms the traditional PINNs approach in terms of Root Mean Square Error, training time, convergence rate, and compliance with physical metrics. While demonstrated on a simple geometry, the methodology is extendable to more complex flow fields (e.g., Three-Dimensional, unsteady, viscous flows) within the incompressible realm, which is the region of applicability of the PMPG.

Here, we present the outcomes from the second Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry, which engaged participants across global hybrid locations, resulting in 34 team submissions. The submissions spanned seven key application areas and demonstrated the diverse utility of LLMs for applications in (1) molecular and material property prediction; (2) molecular and material design; (3) automation and novel interfaces; (4) scientific communication and education; (5) research data management and automation; (6) hypothesis generation and evaluation; and (7) knowledge extraction and reasoning from scientific literature. Each team submission is presented in a summary table with links to the code and as brief papers in the appendix. Beyond team results, we discuss the hackathon event and its hybrid format, which included physical hubs in Toronto, Montreal, San Francisco, Berlin, Lausanne, and Tokyo, alongside a global online hub to enable local and virtual collaboration. Overall, the event highlighted significant improvements in LLM capabilities since the previous year's hackathon, suggesting continued expansion of LLMs for applications in materials science and chemistry research. These outcomes demonstrate the dual utility of LLMs as both multipurpose models for diverse machine learning tasks and platforms for rapid prototyping custom applications in scientific research., Comment: Updating author information, the submission remains largely unchanged. 98 pages total

Inaccuracies in polygraph tests often lead to wrongful convictions, false information, and bias, all of which have significant consequences for both legal and political systems. Recently, analyzing facial micro-expressions has emerged as a method for detecting deception; however, current models have not reached high accuracy and generalizability. The purpose of this study is to aid in remedying these problems. The unique multimodal transformer architecture used in this study improves upon previous approaches by using auditory inputs, visual facial micro-expressions, and manually transcribed gesture annotations, moving closer to a reliable non-invasive lie detection model. Visual and auditory features were extracted using the Vision Transformer and OpenSmile models respectively, which were then concatenated with the transcriptions of participants micro-expressions and gestures. Various models were trained for the classification of lies and truths using these processed and concatenated features. The CNN Conv1D multimodal model achieved an average accuracy of 95.4%. However, further research is still required to create higher-quality datasets and even more generalized models for more diverse applications., Comment: 11 pages, 18 figures

This paper proposes a machine learning approach for classifying classical and new Egyptian music by composer and generating new similar music. The proposed system utilizes a convolutional neural network (CNN) for classification and a CNN autoencoder for generation. The dataset used in this project consists of new and classical Egyptian music pieces composed by different composers. To classify the music by composer, each sample is normalized and transformed into a mel spectrogram. The CNN model is trained on the dataset using the mel spectrograms as input features and the composer labels as output classes. The model achieves 81.4\% accuracy in classifying the music by composer, demonstrating the effectiveness of the proposed approach. To generate new music similar to the original pieces, a CNN autoencoder is trained on a similar dataset. The model is trained to encode the mel spectrograms of the original pieces into a lower-dimensional latent space and then decode them back into the original mel spectrogram. The generated music is produced by sampling from the latent space and decoding the samples back into mel spectrograms, which are then transformed into audio. In conclusion, the proposed system provides a promising approach to classifying and generating classical Egyptian music, which can be applied in various musical applications, such as music recommendation systems, music production, and music education.

In spite of the recent progress in speech processing, the majority of world languages and dialects remain uncovered. This situation only furthers an already wide technological divide, thereby hindering technological and socioeconomic inclusion. This challenge is largely due to the absence of datasets that can empower diverse speech systems. In this paper, we seek to mitigate this obstacle for a number of Arabic dialects by presenting Casablanca, a large-scale community-driven effort to collect and transcribe a multi-dialectal Arabic dataset. The dataset covers eight dialects: Algerian, Egyptian, Emirati, Jordanian, Mauritanian, Moroccan, Palestinian, and Yemeni, and includes annotations for transcription, gender, dialect, and code-switching. We also develop a number of strong baselines exploiting Casablanca. The project page for Casablanca is accessible at: www.dlnlp.ai/speech/casablanca.

In the realm of computer vision, the perception and reconstruction of the 3D world through vision signals heavily rely on camera intrinsic parameters, which have long been a subject of intense research within the community. In practical applications, without a strong scene geometry prior like the Manhattan World assumption or special artificial calibration patterns, monocular focal length estimation becomes a challenging task. In this paper, we propose a method for monocular focal length estimation using category-level object priors. Based on two well-studied existing tasks: monocular depth estimation and category-level object canonical representation learning, our focal solver takes depth priors and object shape priors from images containing objects and estimates the focal length from triplets of correspondences in closed form. Our experiments on simulated and real world data demonstrate that the proposed method outperforms the current state-of-the-art, offering a promising solution to the long-standing monocular focal length estimation problem.

Interactions between active individuals in animal collectives lead to emergent responses that remain elusive in synthetic soft matter. Here, shape-morphing polymers are used to create bio-inspired transient solids that self-assemble with controlled mechanical properties and disassemble on demand. Dilute-suspensions of magnetic, heat-responsive liquid crystal elastomer ribbons mechanically interlock, inducing reversible aggregation. A mathematical model is developed that sheds light on the role of topological mechanisms in aggregation. Aggregation was favored for ribbons with moderate curvature at 25C above crosslinking temperature as compared to flat ribbons or higher curvature ribbons at higher temperatures. The ribbon suspensions reversibly transition between fluid- and solid-like states, exhibiting up to 6 orders-of-magnitude increase in the storage moduli of the entangled aggregates compared with the liquid dispersions. Controlled dissociation is induced by imparting kinetic energy to the individual ribbons at high magnetic field rotation speeds (> 200 RPM). Ribbon shape and the medium in which dissociation occurs were shown to govern disassembly. Imparting dynamic collective behaviors into synthetic systems may enable a range of potential applications from bio-inspired soft robotics to injectable biomaterials., Comment: 16 pages, 6 figures

Detecting and answering ambiguous questions has been a challenging task in open-domain question answering. Ambiguous questions have different answers depending on their interpretation and can take diverse forms. Temporally ambiguous questions are one of the most common types of such questions. In this paper, we introduce TEMPAMBIQA, a manually annotated temporally ambiguous QA dataset consisting of 8,162 open-domain questions derived from existing datasets. Our annotations focus on capturing temporal ambiguity to study the task of detecting temporally ambiguous questions. We propose a novel approach by using diverse search strategies based on disambiguated versions of the questions. We also introduce and test non-search, competitive baselines for detecting temporal ambiguity using zero-shot and few-shot approaches., Comment: Accepted at EMNLP 2024 Findings

Automatic Question Answering (QA) systems rely on contextual information to provide accurate answers. Commonly, contexts are prepared through either retrieval-based or generation-based methods. The former involves retrieving relevant documents from a corpus like Wikipedia, whereas the latter uses generative models such as Large Language Models (LLMs) to generate the context. In this paper, we introduce a novel context preparation approach called HINTQA, which employs Automatic Hint Generation (HG) techniques. Unlike traditional methods, HINTQA prompts LLMs to produce hints about potential answers for the question rather than generating relevant context. We evaluate our approach across three QA datasets including TriviaQA, NaturalQuestions, and Web Questions, examining how the number and order of hints impact performance. Our findings show that the HINTQA surpasses both retrieval-based and generation-based approaches. We demonstrate that hints enhance the accuracy of answers more than retrieved and generated contexts., Comment: Accepted at EMNLP 2024

Tracing a student's knowledge growth given the past exercise answering is a vital objective in automatic tutoring systems to customize the learning experience. Yet, achieving this objective is a non-trivial task as it involves modeling the knowledge state across multiple knowledge components (KCs) while considering their temporal and relational dynamics during the learning process. Knowledge tracing methods have tackled this task by either modeling KCs' temporal dynamics using recurrent models or relational dynamics across KCs and questions using graph models. Albeit, there is a lack of methods that could learn joint embedding between relational and temporal dynamics of the task. Moreover, many methods that count for the impact of a student's forgetting behavior during the learning process use hand-crafted features, limiting their generalization on different scenarios. In this paper, we propose a novel method that jointly models the relational and temporal dynamics of the knowledge state using a deep temporal graph memory network. In addition, we propose a generic technique for representing a student's forgetting behavior using temporal decay constraints on the graph memory module. We demonstrate the effectiveness of our proposed method using multiple knowledge tracing benchmarks while comparing it to state-of-the-art methods.

Large language models have shown promise in various domains, including healthcare. In this study, we conduct a comprehensive evaluation of LLMs in the context of mental health tasks using social media data. We explore the zero-shot (ZS) and few-shot (FS) capabilities of various LLMs, including GPT-4, Llama 3, Gemini, and others, on tasks such as binary disorder detection, disorder severity evaluation, and psychiatric knowledge assessment. Our evaluation involved 33 models testing 9 main prompt templates across the tasks. Key findings revealed that models like GPT-4 and Llama 3 exhibited superior performance in binary disorder detection, with accuracies reaching up to 85% on certain datasets. Moreover, prompt engineering played a crucial role in enhancing model performance. Notably, the Mixtral 8x22b model showed an improvement of over 20%, while Gemma 7b experienced a similar boost in performance. In the task of disorder severity evaluation, we observed that FS learning significantly improved the model's accuracy, highlighting the importance of contextual examples in complex assessments. Notably, the Phi-3-mini model exhibited a substantial increase in performance, with balanced accuracy improving by over 6.80% and mean average error dropping by nearly 1.3 when moving from ZS to FS learning. In the psychiatric knowledge task, recent models generally outperformed older, larger counterparts, with the Llama 3.1 405b achieving an accuracy of 91.2%. Despite promising results, our analysis identified several challenges, including variability in performance across datasets and the need for careful prompt engineering. Furthermore, the ethical guards imposed by many LLM providers hamper the ability to accurately evaluate their performance, due to tendency to not respond to potentially sensitive queries.

The concept of digital twins has attracted significant attention across various domains, particularly within the built environment. However, there is a sheer volume of definitions and the terminological consensus remains out of reach. The lack of a universally accepted definition leads to ambiguities in their conceptualization and implementation, and may cause miscommunication for both researchers and practitioners. We employed Natural Language Processing (NLP) techniques to systematically extract and analyze definitions of digital twins from a corpus of more than 15,000 full-text articles spanning diverse disciplines. The study compares these findings with insights from an expert survey that included 52 experts. The study identifies concurrence on the components that comprise a ``Digital Twin'' from a practical perspective across various domains, contrasting them with those that do not, to identify deviations. We investigate the evolution of digital twin definitions over time and across different scales, including manufacturing, building, and urban/geospatial perspectives. We extracted the main components of Digital Twins using Text Frequency Analysis and N-gram analysis. Subsequently, we identified components that appeared in the literature and conducted a Chi-square test to assess the significance of each component in different domains. Our analysis identified key components of digital twins and revealed significant variations in definitions based on application domains, such as manufacturing, building, and urban contexts. The analysis of DT components reveal two major groups of DT types: High-Performance Real-Time (HPRT) DTs, and Long-Term Decision Support (LTDS) DTs. Contrary to common assumptions, we found that components such as simulation, AI/ML, real-time capabilities, and bi-directional data flow are not yet fully mature in the digital twins of the built environment.

Accurate loss reserving is crucial in Property and Casualty (P&C) insurance for financial stability, regulatory compliance, and effective risk management. We propose a novel micro-level Cox model based on hidden Markov models (HMMs). Initially formulated as a continuous-time model, it addresses the complexity of incorporating temporal dependencies and policyholder risk attributes. However, the continuous-time model faces significant challenges in maximizing the likelihood and fitting right-truncated reporting delays. To overcome these issues, we introduce two discrete-time versions: one incorporating unsystematic randomness in reporting delays through a Dirichlet distribution and one without. We provide the EM algorithm for parameter estimation for all three models and apply them to an auto-insurance dataset to estimate IBNR claim counts. Our results show that while all models perform well, the discrete-time versions demonstrate superior performance by jointly modeling delay and frequency, with the Dirichlet-based model capturing additional variability in reporting delays. This approach enhances the accuracy and reliability of IBNR reserving, offering a flexible framework adaptable to different levels of granularity within an insurance portfolio.

This study utilizes mathematical modeling to offer computational insights into biological heat transfer within elastic skin tissues. This heat transfer is driven by a moving heat source that relies on various relaxation times. Time delay parameters were incorporated based on these relaxation times, highlighting the importance of understanding heat transfer mechanisms and thermo-mechanical interactions to ensure the effectiveness of thermal treatment procedures. Given the significant impact of different variables on thermal relaxation times, their effects were analyzed on the distributions of displacement, thermal stress, and temperature in living tissues. By applying advanced mathematical techniques such as Laplace transforms, precise evaluations of these distributions were achieved. The results are presented graphically, with a focus on enhancing treatment outcomes by deepening our understanding of the behavior of living tissues in thermal environments., Comment: Some of the results contain errors due to mistakes in the equations

We propose a diffusion-based approach for Text-to-Image (T2I) generation with interactive 3D layout control. Layout control has been widely studied to alleviate the shortcomings of T2I diffusion models in understanding objects' placement and relationships from text descriptions. Nevertheless, existing approaches for layout control are limited to 2D layouts, require the user to provide a static layout beforehand, and fail to preserve generated images under layout changes. This makes these approaches unsuitable for applications that require 3D object-wise control and iterative refinements, e.g., interior design and complex scene generation. To this end, we leverage the recent advancements in depth-conditioned T2I models and propose a novel approach for interactive 3D layout control. We replace the traditional 2D boxes used in layout control with 3D boxes. Furthermore, we revamp the T2I task as a multi-stage generation process, where at each stage, the user can insert, change, and move an object in 3D while preserving objects from earlier stages. We achieve this through our proposed Dynamic Self-Attention (DSA) module and the consistent 3D object translation strategy. Experiments show that our approach can generate complicated scenes based on 3D layouts, boosting the object generation success rate over the standard depth-conditioned T2I methods by 2x. Moreover, it outperforms other methods in comparison in preserving objects under layout changes. Project Page: \url{https://abdo-eldesokey.github.io/build-a-scene/}, Comment: Project Page: https://abdo-eldesokey.github.io/build-a-scene/

Computer vision has advanced research methodologies, enhancing system services across various fields. It is a core component in traffic monitoring systems for improving road safety; however, these monitoring systems don't preserve the privacy of pedestrians who appear in the videos, potentially revealing their identities. Addressing this issue, our paper introduces Video-to-Text Pedestrian Monitoring (VTPM), which monitors pedestrian movements at intersections and generates real-time textual reports, including traffic signal and weather information. VTPM uses computer vision models for pedestrian detection and tracking, achieving a latency of 0.05 seconds per video frame. Additionally, it detects crossing violations with 90.2% accuracy by incorporating traffic signal data. The proposed framework is equipped with Phi-3 mini-4k to generate real-time textual reports of pedestrian activity while stating safety concerns like crossing violations, conflicts, and the impact of weather on their behavior with latency of 0.33 seconds. To enhance comprehensive analysis of the generated textual reports, Phi-3 medium is fine-tuned for historical analysis of these generated textual reports. This fine-tuning enables more reliable analysis about the pedestrian safety at intersections, effectively detecting patterns and safety critical events. The proposed VTPM offers a more efficient alternative to video footage by using textual reports reducing memory usage, saving up to 253 million percent, eliminating privacy issues, and enabling comprehensive interactive historical analysis.

The debut of chatGPT and BARD has popularized instruction following text generation using LLMs, where a user can interrogate an LLM using natural language requests and obtain natural language answers that matches their requests. Training LLMs to respond in this manner requires a large number of worked out examples of user requests (aka prompts) with corresponding gold responses. In this paper, we introduce two methods for creating such prompts for Arabic cheaply and quickly. The first methods entails automatically translating existing prompt datasets from English, such as PromptSource and Super-NaturalInstructions, and then using machine translation quality estimation to retain high quality translations only. The second method involves creating natural language prompts on top of existing Arabic NLP datasets. Using these two methods we were able to create more than 67.4 million Arabic prompts that cover a variety of tasks including summarization, headline generation, grammar checking, open/closed question answering, creative writing, etc. We show that fine tuning an open 7 billion parameter large language model, namely base Qwen2 7B, enables it to outperform a state-of-the-art 70 billion parameter instruction tuned model, namely Llama3 70B, in handling Arabic prompts.