Rajiv Ramnath

Amin Karimi Monsefi, Kishore Prakash Sailaja, Ali Alilooee et al.

In this paper, we introduce DetailCLIP: A Detail-Oriented CLIP to address the limitations of contrastive learning-based vision-language models, particularly CLIP, in handling detail-oriented and fine-grained tasks like segmentation. While CLIP and its variants excel in the global alignment of image and text representations, they often struggle to capture the fine-grained details necessary for precise segmentation. To overcome these challenges, we propose a novel framework that employs patch-level comparison of self-distillation and pixel-level reconstruction losses, enhanced with an attention-based token removal mechanism. This approach selectively retains semantically relevant tokens, enabling the model to focus on the image's critical regions aligned with the specific functions of our model, including textual information processing, patch comparison, and image reconstruction, ensuring that the model learns high-level semantics and detailed visual features. Our experiments demonstrate that DetailCLIP surpasses existing CLIP-based and traditional self-supervised learning (SSL) models in segmentation accuracy and exhibits superior generalization across diverse datasets. DetailCLIP represents a significant advancement in vision-language modeling, offering a robust solution for tasks that demand high-level semantic understanding and detailed feature extraction. https://github.com/KishoreP1/DetailCLIP.

Ahmad Mohammadshirazi, Aida Nadafian, Amin Karimi Monsefi et al.

Cost-effective sensors are capable of real-time capturing a variety of air quality-related modalities from different pollutant concentrations to indoor/outdoor humidity and temperature. Machine learning (ML) models are capable of performing air-quality "ahead-of-time" approximations. Undoubtedly, accurate indoor air quality approximation significantly helps provide a healthy indoor environment, optimize associated energy consumption, and offer human comfort. However, it is crucial to design an ML architecture to capture the domain knowledge, so-called problem physics. In this study, we propose six novel physics-based ML models for accurate indoor pollutant concentration approximations. The proposed models include an adroit combination of state-space concepts in physics, Gated Recurrent Units, and Decomposition techniques. The proposed models were illustrated using data collected from five offices in a commercial building in California. The proposed models are shown to be less complex, computationally more efficient, and more accurate than similar state-of-the-art transformer-based models. The superiority of the proposed models is due to their relatively light architecture (computational efficiency) and, more importantly, their ability to capture the underlying highly nonlinear patterns embedded in the often contaminated sensor-collected indoor air quality temporal data.

Max Foreback, Evan Imata, Vincent Ragusa et al.

Designing scientific instrumentation often requires exploring large, highly constrained design spaces using computationally expensive physics simulations. These simulators pose substantial challenges for integrating evolutionary computation (EC) into scientific design workflows. EC typically requires numerous design evaluations, making the integration of slow, low-throughput simulators challenging, as they are optimized for accuracy and ease of use rather than throughput. We present ECLIPSE, an evolutionary computation framework built to interface directly with complex, domain-specific simulation tools while supporting flexible geometric and parametric representations of scientific hardware. ECLIPSE provides a modular architecture consisting of (1) Individuals, which encode hardware designs using domain-aware, physically constrained representations; (2) Evaluators, which prepare simulation inputs, invoke external simulators, and translate the simulator's outputs into fitness measures; and (3) Evolvers, which implement EC algorithms suitable for this domain. We evolve solutions for two novel space-science applications: 3D antennas optimized for directional sensitivity and spacecraft geometries optimized for drag reduction. Notably, we identify antennas with directional sensitivity roughly comparable to the expected sensitivity of two-antenna interferometric arrays, representing potential cost-savings. ECLIPSE enables interdisciplinary teams of physicists, engineers, and EC researchers to collaboratively explore designs for scientific hardware while leveraging existing domain-specific simulation software.

Amin Karimi Monsefi, Mengxi Zhou, Nastaran Karimi Monsefi et al.

We present a novel frequency-based Self-Supervised Learning (SSL) approach that significantly enhances its efficacy for pre-training. Prior work in this direction masks out pre-defined frequencies in the input image and employs a reconstruction loss to pre-train the model. While achieving promising results, such an implementation has two fundamental limitations as identified in our paper. First, using pre-defined frequencies overlooks the variability of image frequency responses. Second, pre-trained with frequency-filtered images, the resulting model needs relatively more data to adapt to naturally looking images during fine-tuning. To address these drawbacks, we propose FOurier transform compression with seLf-Knowledge distillation (FOLK), integrating two dedicated ideas. First, inspired by image compression, we adaptively select the masked-out frequencies based on image frequency responses, creating more suitable SSL tasks for pre-training. Second, we employ a two-branch framework empowered by knowledge distillation, enabling the model to take both the filtered and original images as input, largely reducing the burden of downstream tasks. Our experimental results demonstrate the effectiveness of FOLK in achieving competitive performance to many state-of-the-art SSL methods across various downstream tasks, including image classification, few-shot learning, and semantic segmentation.

Mridul Khurana, Amin Karimi Monsefi, Justin Lee et al.

Accurately generating images across the Tree of Life is difficult: there are over 10M distinct species on Earth, many of which differ only by subtle visual traits. Despite the remarkable progress in text-to-image synthesis, existing models often fail to capture the fine-grained visual cues that define species identity, even when their outputs appear photo-realistic. To this end, we propose TaxaAdapter, a simple and lightweight approach that incorporates Vision Taxonomy Models (VTMs) such as BioCLIP to guide fine-grained species generation. Our method injects VTM embeddings into a frozen text-to-image diffusion model, improving species-level fidelity while preserving flexible text control over attributes such as pose, style, and background. Extensive experiments demonstrate that TaxaAdapter consistently improves morphology fidelity and species-identity accuracy over strong baselines, with a cleaner architecture and training recipe. To better evaluate these improvements, we also introduce a multimodal Large Language Model-based metric that summarizes trait-level descriptions from generated and real images, providing a more interpretable measure of morphological consistency. Beyond this, we observe that TaxaAdapter exhibits strong generalization capabilities, enabling species synthesis in challenging regimes such as few-shot species with only a handful of training images and even species unseen during training. Overall, our results highlight that VTMs are a key ingredient for scalable, fine-grained species generation.

Amin Karimi Monsefi, Sobhan Moosavi, Rajiv Ramnath

Road construction projects maintain transportation infrastructures. These projects range from the short-term (e.g., resurfacing or fixing potholes) to the long-term (e.g., adding a shoulder or building a bridge). Deciding what the next construction project is and when it is to be scheduled is traditionally done through inspection by humans using special equipment. This approach is costly and difficult to scale. An alternative is the use of computational approaches that integrate and analyze multiple types of past and present spatiotemporal data to predict location and time of future road constructions. This paper reports on such an approach, one that uses a deep-neural-network-based model to predict future constructions. Our model applies both convolutional and recurrent components on a heterogeneous dataset consisting of construction, weather, map and road-network data. We also report on how we addressed the lack of adequate publicly available data - by building a large scale dataset named "US-Constructions", that includes 6.2 million cases of road constructions augmented by a variety of spatiotemporal attributes and road-network features, collected in the contiguous United States (US) between 2016 and 2021. Using extensive experiments on several major cities in the US, we show the applicability of our work in accurately predicting future constructions - an average f1-score of 0.85 and accuracy 82.2% - that outperform baselines. Additionally, we show how our training pipeline addresses spatial sparsity of data.

Jamuna S. Murthy, Amin Karimi Monsefi, Rajiv Ramnath

Controllable multimodal generation is commonly formulated as an inference-time conditioning problem using prompts, guidance, or auxiliary modules. While effective, such approaches do not explicitly structure how semantic attributes evolve, which can lead to identity drift and inconsistent cross-modal behavior. We propose Controlla, a modular factorized-control framework that treats controllability as a property of structured latent geometry. Controlla learns identity and attribute factors from multimodal inputs and aligns them with graph priors using graph-constrained optimal transport, encouraging attributes to follow graph-consistent trajectories while preserving reference identity. To evaluate this setting, we construct AffectHuman-43K, a leakage-aware multimodal benchmark for reference-grounded affective control, and introduce geometry-aware metrics for trajectory consistency and latent disentanglement. Experiments show consistent improvements in controllability, identity preservation, and cross-modal alignment, with additional analyses on graph sensitivity, extensibility, and robustness.

Amin Karimi Monsefi, Abolfazl Meyarian, Mridul Khurana et al.

Animals are described as effectively camouflaged when they blend seamlessly with their surrounding, yet no standardized quantitative measure of this seamlessness exists. We address this gap by framing camouflage evaluation as a visual localization problem: a well-camouflaged animal is one that remains difficult to detect even when its category is known. We introduce SeamCam (Seamless Camouflage), a metric that quantifies how detectable an animal is from the available visual evidence. Given an image and a target species, SeamCam generates category-conditioned detection proposals, extracts segmentation masks, and identifies the subset whose collective union yields the highest IoU with the ground-truth mask. The SeamCam score is one minus this maximum recoverable localization signal, where a higher score indicates stronger camouflage (i.e., lower detectability). In a human two-alternative forced-choice study with 94 participants and 2,390 comparisons, SeamCam achieves 78.82% agreement with human camouflage difficulty judgments, outperforming state-of-the-art by about 25%. We then demonstrate SeamCam's utility as a preference signal for Direct Preference Optimization (DPO) to fine-tune a diffusion-based inpainting model for camouflage generation. This offers an affordable training approach with an objective explicitly suited for camouflage generation, unlike typical diffusion models. To support rigorous benchmarking, we further introduce CamFG-1.5k, a curated dataset of 1,521 high-resolution images in which animals are fully visible prior to camouflage generation, enabling unbiased evaluation by controlling for occlusion artifacts present in existing datasets. https://7amin.github.io/SeamCam/

Ahmad Mohammadshirazi, Pinaki Prasad Guha Neogi, Ser-Nam Lim et al.

Document Visual Question Answering (VQA) demands robust integration of text detection, recognition, and spatial reasoning to interpret complex document layouts. In this work, we introduce DLaVA, a novel, training-free pipeline that leverages Multimodal Large Language Models (MLLMs) for zero-shot answer localization in order to improve trustworthiness, interpretability, and explainability. By leveraging an innovative OCR-free approach that organizes text regions with unique bounding box IDs, the proposed method preserves spatial contexts without relying on iterative OCR or chain-of-thought reasoning, thus substantially reducing the computational complexity. We further enhance the evaluation protocol by integrating Intersection over Union (IoU) metrics alongside Average Normalized Levenshtein Similarity (ANLS), thereby ensuring that not only textual accuracy is considered, but spatial accuracy is taken into account, ultimately reducing the risks of AI hallucinations and improving trustworthiness. Experiments on benchmark datasets demonstrate competitive performance compared to state-of-the-art techniques, with significantly lower computational complexity and enhanced accuracies and reliability for high-stakes applications. The code and datasets utilized in this study for DLaVA are accessible at: https://github.com/ahmad-shirazi/AnnotMLLM.

Abolfazl Meyarian, Amin Karimi Monsefi, Rajiv Ramnath et al.

Flow-matching video generators produce temporally coherent, high-fidelity outputs yet routinely violate elementary physics because their reconstruction objectives penalize per-frame deviations without distinguishing physically consistent dynamics from impossible ones. Contrastive flow matching offers a principled remedy by pushing apart velocity-field trajectories of differing conditions, but we identify a fundamental obstacle in the text-conditioned video setting: semantic-physics entanglement. Because natural-language prompts couple scene content with physical behavior, naive negative sampling draws conditions whose velocity fields largely overlap with the positive sample's, causing the contrastive gradient to directly oppose the flow-matching objective. We formalize this gradient conflict, deriving a precise alignment condition that reveals when contrastive learning helps versus harms training. Guided by this analysis, we introduce DiReCT (Disentangled Regularization of Contrastive Trajectories), a lightweight post-training framework that decomposes the contrastive signal into two complementary scales: a macro-contrastive term that draws partition-exclusive negatives from semantically distant regions for interference-free global trajectory separation, and a micro-contrastive term that constructs hard negatives sharing full scene semantics with the positive sample but differing along a single, LLM-perturbed axis of physical behavior; spanning kinematics, forces, materials, interactions, and magnitudes. A velocity-space distributional regularizer helps to prevent catastrophic forgetting of pretrained visual quality. When applied to Wan 2.1-1.3B, our method improves the physical commonsense score on VideoPhy by 16.7% and 11.3% compared to the baseline and SFT, respectively, without increasing training time.

Pinaki Prasad Guha Neogi, Ahmad Mohammadshirazi, Rajiv Ramnath

Traffic accidents are rare, yet high-impact events that require long-context multimodal reasoning for accurate risk forecasting. In this paper, we introduce ALCo-FM, a unified adaptive long-context foundation model that computes a volatility pre-score to dynamically select context windows for input data and encodes and fuses these multimodal data via shallow cross attention. Following a local GAT layer and a BigBird-style sparse global transformer over H3 hexagonal grids, coupled with Monte Carlo dropout for confidence, the model yields superior, well-calibrated predictions. Trained on data from 15 US cities with a class-weighted loss to counter label imbalance, and fine-tuned with minimal data on held-out cities, ALCo-FM achieves 0.94 accuracy, 0.92 F1, and an ECE of 0.04, outperforming more than 20 state-of-the-art baselines in large-scale urban risk prediction. Code and dataset are available at: https://github.com/PinakiPrasad12/ALCo-FM

Ahmad Mohammadshirazi, Ali Nosrati Firoozsalari, Mengxi Zhou et al.

Automating the annotation of scanned documents is challenging, requiring a balance between computational efficiency and accuracy. DocParseNet addresses this by combining deep learning and multi-modal learning to process both text and visual data. This model goes beyond traditional OCR and semantic segmentation, capturing the interplay between text and images to preserve contextual nuances in complex document structures. Our evaluations show that DocParseNet significantly outperforms conventional models, achieving mIoU scores of 49.12 on validation and 49.78 on the test set. This reflects a 58% accuracy improvement over state-of-the-art baseline models and an 18% gain compared to the UNext baseline. Remarkably, DocParseNet achieves these results with only 2.8 million parameters, reducing the model size by approximately 25 times and speeding up training by 5 times compared to other models. These metrics, coupled with a computational efficiency of 0.039 TFLOPs (BS=1), highlight DocParseNet's high performance in document annotation. The model's adaptability and scalability make it well-suited for real-world corporate document processing applications. The code is available at https://github.com/ahmad-shirazi/DocParseNet

Ahmad Mohammadshirazi, Pinaki Prasad Guha Neogi, Rajiv Ramnath

Time series forecasting often demands a trade-off between accuracy and efficiency. While recent Transformer models have improved forecasting capabilities, they come with high computational costs. Linear-based models have shown better accuracy than Transformers but still fall short of ideal performance. We propose PIAD-SRNN, a physics-informed adaptive decomposition state-space RNN, that separates seasonal and trend components and embeds domain equations in a recurrent framework. We evaluate PIAD-SRNN's performance on indoor air quality datasets, focusing on CO2 concentration prediction across various forecasting horizons, and results demonstrate that it consistently outperforms SoTA models in both long-term and short-term time series forecasting, including transformer-based architectures, in terms of both MSE and MAE. Besides proposing PIAD-SRNN which balances accuracy with efficiency, this paper also provides four curated datasets. Code and data: https://github.com/ahmad-shirazi/DSSRNN

Amin Karimi Monsefi, Pouya Shiri, Ahmad Mohammadshirazi et al.

Reducing traffic accidents is a crucial global public safety concern. Accident prediction is key to improving traffic safety, enabling proactive measures to be taken before a crash occurs, and informing safety policies, regulations, and targeted interventions. Despite numerous studies on accident prediction over the past decades, many have limitations in terms of generalizability, reproducibility, or feasibility for practical use due to input data or problem formulation. To address existing shortcomings, we propose CrashFormer, a multi-modal architecture that utilizes comprehensive (but relatively easy to obtain) inputs such as the history of accidents, weather information, map images, and demographic information. The model predicts the future risk of accidents on a reasonably acceptable cadence (i.e., every six hours) for a geographical location of 5.161 square kilometers. CrashFormer is composed of five components: a sequential encoder to utilize historical accidents and weather data, an image encoder to use map imagery data, a raw data encoder to utilize demographic information, a feature fusion module for aggregating the encoded features, and a classifier that accepts the aggregated data and makes predictions accordingly. Results from extensive real-world experiments in 10 major US cities show that CrashFormer outperforms state-of-the-art sequential and non-sequential models by 1.8% in F1-score on average when using ``sparse'' input data.

Amin Karimi Monsefi, Payam Karisani, Mengxi Zhou et al.

Standard modern machine-learning-based imaging methods have faced challenges in medical applications due to the high cost of dataset construction and, thereby, the limited labeled training data available. Additionally, upon deployment, these methods are usually used to process a large volume of data on a daily basis, imposing a high maintenance cost on medical facilities. In this paper, we introduce a new neural network architecture, termed LoGoNet, with a tailored self-supervised learning (SSL) method to mitigate such challenges. LoGoNet integrates a novel feature extractor within a U-shaped architecture, leveraging Large Kernel Attention (LKA) and a dual encoding strategy to capture both long-range and short-range feature dependencies adeptly. This is in contrast to existing methods that rely on increasing network capacity to enhance feature extraction. This combination of novel techniques in our model is especially beneficial in medical image segmentation, given the difficulty of learning intricate and often irregular body organ shapes, such as the spleen. Complementary, we propose a novel SSL method tailored for 3D images to compensate for the lack of large labeled datasets. The method combines masking and contrastive learning techniques within a multi-task learning framework and is compatible with both Vision Transformer (ViT) and CNN-based models. We demonstrate the efficacy of our methods in numerous tasks across two standard datasets (i.e., BTCV and MSD). Benchmark comparisons with eight state-of-the-art models highlight LoGoNet's superior performance in both inference time and accuracy.

Amin Karimi Monsefi, Mridul Khurana, Rajiv Ramnath et al.

We propose TaxaDiffusion, a taxonomy-informed training framework for diffusion models to generate fine-grained animal images with high morphological and identity accuracy. Unlike standard approaches that treat each species as an independent category, TaxaDiffusion incorporates domain knowledge that many species exhibit strong visual similarities, with distinctions often residing in subtle variations of shape, pattern, and color. To exploit these relationships, TaxaDiffusion progressively trains conditioned diffusion models across different taxonomic levels -- starting from broad classifications such as Class and Order, refining through Family and Genus, and ultimately distinguishing at the Species level. This hierarchical learning strategy first captures coarse-grained morphological traits shared by species with common ancestors, facilitating knowledge transfer before refining fine-grained differences for species-level distinction. As a result, TaxaDiffusion enables accurate generation even with limited training samples per species. Extensive experiments on three fine-grained animal datasets demonstrate that outperforms existing approaches, achieving superior fidelity in fine-grained animal image generation. Project page: https://amink8.github.io/TaxaDiffusion/

Biplob Biswas, Rajiv Ramnath

Expansion-enhanced sparse lexical representation improves information retrieval (IR) by minimizing vocabulary mismatch problems during lexical matching. In this paper, we explore the potential of jointly learning dense semantic representation and combining it with the lexical one for ranking candidate information. We present a hybrid information retrieval mechanism that maximizes lexical and semantic matching while minimizing their shortcomings. Our architecture consists of dual hybrid encoders that independently encode queries and information elements. Each encoder jointly learns a dense semantic representation and a sparse lexical representation augmented by a learnable term expansion of the corresponding text through contrastive learning. We demonstrate the efficacy of our model in single-stage ranking of a benchmark product question-answering dataset containing the typical heterogeneous information available on online product pages. Our evaluation demonstrates that our hybrid approach outperforms independently trained retrievers by 10.95% (sparse) and 2.7% (dense) in MRR@5 score. Moreover, our model offers better interpretability and performs comparably to state-of-the-art cross encoders while reducing response time by 30% (latency) and cutting computational load by approximately 38% (FLOPs).

Pinaki Prasad Guha Neogi, Ahmad Mohammadshirazi, Rajiv Ramnath

Smart buildings generate vast streams of sensor and control data, but facility managers often lack clear explanations for anomalous energy usage. We propose InsightBuild, a two-stage framework that integrates causality analysis with a fine-tuned large language model (LLM) to provide human-readable, causal explanations of energy consumption patterns. First, a lightweight causal inference module applies Granger causality tests and structural causal discovery on building telemetry (e.g., temperature, HVAC settings, occupancy) drawn from Google Smart Buildings and Berkeley Office datasets. Next, an LLM, fine-tuned on aligned pairs of sensor-level causes and textual explanations, receives as input the detected causal relations and generates concise, actionable explanations. We evaluate InsightBuild on two real-world datasets (Google: 2017-2022; Berkeley: 2018-2020), using expert-annotated ground-truth causes for a held-out set of anomalies. Our results demonstrate that combining explicit causal discovery with LLM-based natural language generation yields clear, precise explanations that assist facility managers in diagnosing and mitigating energy inefficiencies.

Ahmad Mohammadshirazi, Pinaki Prasad Guha Neogi, Dheeraj Kulshrestha et al.

Document visual question answering (DocVQA) requires models to jointly reason over textual content and spatial layout, yet current systems exhibit a sharp accuracy--efficiency trade-off: large teacher models achieve strong grounding but are too expensive for deployment, while compact students suffer substantial drops in localization performance. We propose DocVAL, a validated chain-of-thought distillation framework that transfers the spatial reasoning ability of a large teacher into a deployable student VLM through three key components: (1) teacher supervision with validation-time text detection to filter and denoise training signals, (2) a multi-module validator (VAL) that enforces answer correctness and geometric consistency while producing fine-grained, pixel-level error feedback, and (3) a two-stage student training scheme that first learns from validated CoT traces and then undergoes iterative refinement driven by VAL feedback. Our student (Gemma-3 12B) achieves 91.4\% ANLS and 82.4\% mAP on DocVQA as a pure VLM requiring no text detection or OCR at inference. Extensive ablations demonstrate that validated feedback contributes 6.3 mAP gain and iterative refinement accounts for 9.7 mAP improvement. We release 95k high-quality, validator-verified CoT traces to advance spatial reasoning research in document understanding.

Ahmad Mohammadshirazi, Pinaki Prasad Guha Neogi, Dheeraj Kulshrestha et al.

Document Visual Question Answering (VQA) requires models to not only extract accurate textual answers but also precisely localize them within document images, a capability critical for interpretability in high-stakes applications. However, existing systems achieve strong textual accuracy while producing unreliable spatial grounding, or sacrifice performance for interpretability. We present ARIAL (Agentic Reasoning for Interpretable Answer Localization), a modular framework that orchestrates specialized tools through an LLM-based planning agent to achieve both precise answer extraction and reliable spatial grounding. ARIAL decomposes Document VQA into structured subtasks: OCR-based text extraction with TrOCR, retrieval-augmented context selection using semantic search, answer generation via a fine-tuned Gemma 3-27B model, and explicit bounding-box localization through text-to-region alignment. This modular architecture produces transparent reasoning traces, enabling tool-level auditability and independent component optimization. We evaluate ARIAL on four benchmarks (DocVQA, FUNSD, CORD, and SROIE) using both textual accuracy (ANLS) and spatial precision (mAP at IoU 0.50 to 0.95). ARIAL achieves state-of-the-art results across all datasets: 88.7 ANLS and 50.1 mAP on DocVQA, 90.0 ANLS and 50.3 mAP on FUNSD, 85.5 ANLS and 60.2 mAP on CORD, and 93.1 ANLS on SROIE, surpassing the previous best method (DLaVA) by +2.8 ANLS and +3.9 mAP on DocVQA. Our work demonstrates how agentic orchestration of specialized tools can simultaneously improve performance and interpretability, providing a pathway toward trustworthy, explainable document AI systems.

Pinaki Prasad Guha Neogi, Ahmad Mohammadshirazi, Dheeraj Kulshrestha et al.

Mixture-of-Experts (MoE) architectures are increasingly adopted in large language models (LLMs) for their scalability and efficiency. However, their modular structure introduces a unique vulnerability: adversaries can attempt to compress or repurpose models by pruning experts and cheaply fine-tuning the remainder, effectively bypassing licensing and security constraints. In this paper, we systematically study the prunability of MoE-LLMs under task-specific usage. We first develop an expert attribution framework that identifies the subset of experts most responsible for a given task, then evaluate the performance trade-offs of pruning and re-aligning these experts using active learning-driven fine-tuning. Our findings reveal a critical knowledge loss--recovery trade-off: while certain experts can be isolated to retain task accuracy, significant degradation occurs without targeted re-alignment. Based on this analysis, we propose defense strategies that aim to make MoE models harder to compress and fine-tune without authorization, including entangled expert training and selective fine-tuning protocols that resist unauthorized adaptation. By positioning expert pruning as both a threat vector and a defense target, this work highlights the dual-use nature of MoE modularity and provides the first systematic evaluation framework for secure specialization of MoE-LLMs.

Ahmad Mohammadshirazi, Pinaki Prasad Guha Neogi, Dheeraj Kulshrestha et al.

Document Visual Question Answering (DocVQA) requires models to jointly understand textual semantics, spatial layout, and visual features. Current methods struggle with explicit spatial relationship modeling, inefficiency with high-resolution documents, multi-hop reasoning, and limited interpretability. We propose MGA-VQA, a multi-modal framework that integrates token-level encoding, spatial graph reasoning, memory-augmented inference, and question-guided compression. Unlike prior black-box models, MGA-VQA introduces interpretable graph-based decision pathways and structured memory access for enhanced reasoning transparency. Evaluation across six benchmarks (FUNSD, CORD, SROIE, DocVQA, STE-VQA, and RICO) demonstrates superior accuracy and efficiency, with consistent improvements in both answer prediction and spatial localization.

Xiang Li, Gagan Agrawal, Ruoming Jin et al.

We consider the problem of constructing embeddings of large attributed graphs and supporting multiple downstream learning tasks. We develop a graph embedding method, which is based on extending deep metric and unbiased contrastive learning techniques to 1) work with attributed graphs, 2) enabling a mini-batch based approach, and 3) achieving scalability. Based on a multi-class tuplet loss function, we present two algorithms -- DMT for semi-supervised learning and DMAT-i for the unsupervised case. Analyzing our methods, we provide a generalization bound for the downstream node classification task and for the first time relate tuplet loss to contrastive learning. Through extensive experiments, we show high scalability of representation construction, and in applying the method for three downstream tasks (node clustering, node classification, and link prediction) better consistency over any single existing method.

Xiang Li, Gagan Agrawal, Rajiv Ramnath et al.

Graph-level representations (and clustering/classification based on these representations) are required in a variety of applications. Examples include identifying malicious network traffic, prediction of protein properties, and many others. Often, data has to stay in isolated local systems (i.e., cannot be centrally shared for analysis) due to a variety of considerations like privacy concerns, lack of trust between the parties, regulations, or simply because the data is too large to be shared sufficiently quickly. This points to the need for federated learning for graph-level representations, a topic that has not been explored much, especially in an unsupervised setting. Addressing this problem, this paper presents a new framework we refer to as Federated Contrastive Learning of Graph-level Representations (FCLG). As the name suggests, our approach builds on contrastive learning. However, what is unique is that we apply contrastive learning at two levels. The first application is for local unsupervised learning of graph representations. The second level is to address the challenge associated with data distribution variation (i.e. the ``Non-IID issue") when combining local models. Through extensive experiments on the downstream task of graph-level clustering, we demonstrate FCLG outperforms baselines (which apply existing federated methods on existing graph-level clustering methods) with significant margins.

Noushin Behboudi, Sobhan Moosavi, Rajiv Ramnath

Traffic accidents pose a severe global public health issue, leading to 1.19 million fatalities annually, with the greatest impact on individuals aged 5 to 29 years old. This paper addresses the critical need for advanced predictive methods in road safety by conducting a comprehensive review of recent advancements in applying machine learning (ML) techniques to traffic accident analysis and prediction. It examines 191 studies from the last five years, focusing on predicting accident risk, frequency, severity, duration, as well as general statistical analysis of accident data. To our knowledge, this study is the first to provide such a comprehensive review, covering the state-of-the-art across a wide range of domains related to accident analysis and prediction. The review highlights the effectiveness of integrating diverse data sources and advanced ML techniques to improve prediction accuracy and handle the complexities of traffic data. By mapping the current landscape and identifying gaps in the literature, this study aims to guide future research towards significantly reducing traffic-related deaths and injuries by 2030, aligning with the World Health Organization (WHO) targets.

Sobhan Moosavi, Rajiv Ramnath

Driving risk prediction has been a topic of much research over the past few decades to minimize driving risk and increase safety. The use of demographic information in risk prediction is a traditional solution with applications in insurance planning, however, it is difficult to capture true driving behavior via such coarse-grained factors. Therefor, the use of telematics data has gained a widespread popularity over the past decade. While most of the existing studies leverage demographic information in addition to telematics data, our objective is to maximize the use of telematics as well as contextual information (e.g., road-type) to build a risk prediction framework with real-world applications. We contextualize telematics data in a variety of forms, and then use it to develop a risk classifier, assuming that there are some weak risk labels available (e.g., past traffic citation records). Before building a risk classifier though, we employ a novel data-driven process to augment weak risk labels. Extensive analysis and results based on real-world data from multiple major cities in the United States demonstrate usefulness of the proposed framework.

Xiang Li, Dong Li, Ruoming Jin et al.

Web-based interactions can be frequently represented by an attributed graph, and node clustering in such graphs has received much attention lately. Multiple efforts have successfully applied Graph Convolutional Networks (GCN), though with some limits on accuracy as GCNs have been shown to suffer from over-smoothing issues. Though other methods (particularly those based on Laplacian Smoothing) have reported better accuracy, a fundamental limitation of all the work is a lack of scalability. This paper addresses this open problem by relating the Laplacian smoothing to the Generalized PageRank and applying a random-walk based algorithm as a scalable graph filter. This forms the basis for our scalable deep clustering algorithm, RwSL, where through a self-supervised mini-batch training mechanism, we simultaneously optimize a deep neural network for sample-cluster assignment distribution and an autoencoder for a clustering-oriented embedding. Using 6 real-world datasets and 6 clustering metrics, we show that RwSL achieved improved results over several recent baselines. Most notably, we show that RwSL, unlike all other deep clustering frameworks, can continue to scale beyond graphs with more than one million nodes, i.e., handle web-scale. We also demonstrate how RwSL could perform node clustering on a graph with 1.8 billion edges using only a single GPU.

Sobhan Moosavi, Pravar D. Mahajan, Srinivasan Parthasarathy et al.

Identifying driving styles is the task of analyzing the behavior of drivers in order to capture variations that will serve to discriminate different drivers from each other. This task has become a prerequisite for a variety of applications, including usage-based insurance, driver coaching, driver action prediction, and even in designing autonomous vehicles; because driving style encodes essential information needed by these applications. In this paper, we present a deep-neural-network architecture, we term D-CRNN, for building high-fidelity representations for driving style, that combine the power of convolutional neural networks (CNN) and recurrent neural networks (RNN). Using CNN, we capture semantic patterns of driver behavior from trajectories (such as a turn or a braking event). We then find temporal dependencies between these semantic patterns using RNN to encode driving style. We demonstrate the effectiveness of these techniques for driver identification by learning driving style through extensive experiments conducted on several large, real-world datasets, and comparing the results with the state-of-the-art deep-learning and non-deep-learning solutions. These experiments also demonstrate a useful example of bias removal, by presenting how we preprocess the input data by sampling dissimilar trajectories for each driver to prevent spatial memorization. Finally, this paper presents an analysis of the contribution of different attributes for driver identification; we find that engine RPM, Speed, and Acceleration are the best combination of features.

Manirupa Das, Juanxi Li, Eric Fosler-Lussier et al.

Novel contexts may often arise in complex querying scenarios such as in evidence-based medicine (EBM) involving biomedical literature, that may not explicitly refer to entities or canonical concept forms occurring in any fact- or rule-based knowledge source such as an ontology like the UMLS. Moreover, hidden associations between candidate concepts meaningful in the current context, may not exist within a single document, but within the collection, via alternate lexical forms. Therefore, inspired by the recent success of sequence-to-sequence neural models in delivering the state-of-the-art in a wide range of NLP tasks, we develop a novel sequence-to-set framework with neural attention for learning document representations that can effect term transfer within the corpus, for semantically tagging a large collection of documents. We demonstrate that our proposed method can be effective in both a supervised multi-label classification setup for text categorization, as well as in a unique unsupervised setting with no human-annotated document labels that uses no external knowledge resources and only corpus-derived term statistics to drive the training. Further, we show that semi-supervised training using our architecture on large amounts of unlabeled data can augment performance on the text categorization task when limited labeled data is available. Our approach to generate document encodings employing our sequence-to-set models for inference of semantic tags, gives to the best of our knowledge, the state-of-the-art for both, the unsupervised query expansion task for the TREC CDS 2016 challenge dataset when evaluated on an Okapi BM25--based document retrieval system; and also over the MLTM baseline (Soleimani et al, 2016), for both supervised and semi-supervised multi-label prediction tasks on the del.icio.us and Ohsumed datasets. We will make our code and data publicly available.

Renhao Cui, Gagan Agrawal, Rajiv Ramnath

Businesses communicate using Twitter for a variety of reasons -- to raise awareness of their brands, to market new products, to respond to community comments, and to connect with their customers and potential customers in a targeted manner. For businesses to do this effectively, they need to understand which content and structural elements about a tweet make it influential, that is, widely liked, followed, and retweeted. This paper presents a systematic methodology for analyzing commercial tweets, and predicting the influence on their readers. Our model, which use a combination of decoration and meta features, outperforms the prediction ability of the baseline model as well as the tweet embedding model. Further, in order to demonstrate a practical use of this work, we show how an unsuccessful tweet may be engineered (for example, reworded) to increase its potential for success.

Manirupa Das, Zhen Wang, Evan Jaffe et al.

Online customer reviews on large-scale e-commerce websites, represent a rich and varied source of opinion data, often providing subjective qualitative assessments of product usage that can help potential customers to discover features that meet their personal needs and preferences. Thus they have the potential to automatically answer specific queries about products, and to address the problems of answer starvation and answer augmentation on associated consumer Q & A forums, by providing good answer alternatives. In this work, we explore several recently successful neural approaches to modeling sentence pairs, that could better learn the relationship between questions and ground truth answers, and thus help infer reviews that can best answer a question or augment a given answer. In particular, we hypothesize that our adversarial domain adaptation-based approach, due to its ability to additionally learn domain-invariant features from a large number of unlabeled, unpaired question-review samples, would perform better than our proposed baselines, at answering specific, subjective product-related queries using reviews. We validate this hypothesis using a small gold standard dataset of question-review pairs evaluated by human experts, significantly surpassing our chosen baselines. Moreover, our approach, using no labeled question-review sentence pair data for training, gives performance at par with another method utilizing labeled question-review samples for the same task.

Sobhan Moosavi, Mohammad Hossein Samavatian, Srinivasan Parthasarathy et al.

Reducing traffic accidents is an important public safety challenge, therefore, accident analysis and prediction has been a topic of much research over the past few decades. Using small-scale datasets with limited coverage, being dependent on extensive set of data, and being not applicable for real-time purposes are the important shortcomings of the existing studies. To address these challenges, we propose a new solution for real-time traffic accident prediction using easy-to-obtain, but sparse data. Our solution relies on a deep-neural-network model (which we have named DAP, for Deep Accident Prediction); which utilizes a variety of data attributes such as traffic events, weather data, points-of-interest, and time. DAP incorporates multiple components including a recurrent (for time-sensitive data), a fully connected (for time-insensitive data), and a trainable embedding component (to capture spatial heterogeneity). To fill the data gap, we have - through a comprehensive process of data collection, integration, and augmentation - created a large-scale publicly available database of accident information named US-Accidents. By employing the US-Accidents dataset and through an extensive set of experiments across several large cities, we have evaluated our proposal against several baselines. Our analysis and results show significant improvements to predict rare accident events. Further, we have shown the impact of traffic information, time, and points-of-interest data for real-time accident prediction.

Renhao Cui, Gagan Agrawal, Rajiv Ramnath

This paper presents techniques to detect the "offline" activity a person is engaged in when she is tweeting (such as dining, shopping or entertainment), in order to create a dynamic profile of the user, for uses such as better targeting of advertisements. To this end, we propose a hybrid LSTM model for rich contextual learning, along with studies on the effects of applying and combining multiple LSTM based methods with different contextual features. The hybrid model is shown to outperform a set of baselines and state-of-the-art methods. Finally, this paper presents an orthogonal validation with a real-case application. Our model generates an offline activity analysis for the followers of several well-known accounts, which is quite representative of the expected characteristics of these accounts.

Sobhan Moosavi, Arnab Nandi, Rajiv Ramnath

Telematics data is becoming increasingly available due to the ubiquity of devices that collect data during drives, for different purposes, such as usage based insurance (UBI), fleet management, navigation of connected vehicles, etc. Consequently, a variety of data-analytic applications have become feasible that extract valuable insights from the data. In this paper, we address the especially challenging problem of discovering behavior-based driving patterns from only externally observable phenomena (e.g. vehicle's speed). We present a trajectory segmentation approach capable of discovering driving patterns as separate segments, based on the behavior of drivers. This segmentation approach includes a novel transformation of trajectories along with a dynamic programming approach for segmentation. We apply the segmentation approach on a real-word, rich dataset of personal car trajectories provided by a major insurance company based in Columbus, Ohio. Analysis and preliminary results show the applicability of approach for finding significant driving patterns.

Jiankai Sun, Sobhan Moosavi, Rajiv Ramnath et al.

In this paper, we present a framework for Question Difficulty and Expertise Estimation (QDEE) in Community Question Answering sites (CQAs) such as Yahoo! Answers and Stack Overflow, which tackles a fundamental challenge in crowdsourcing: how to appropriately route and assign questions to users with the suitable expertise. This problem domain has been the subject of much research and includes both language-agnostic as well as language conscious solutions. We bring to bear a key language-agnostic insight: that users gain expertise and therefore tend to ask as well as answer more difficult questions over time. We use this insight within the popular competition (directed) graph model to estimate question difficulty and user expertise by identifying key hierarchical structure within said model. An important and novel contribution here is the application of "social agony" to this problem domain. Difficulty levels of newly posted questions (the cold-start problem) are estimated by using our QDEE framework and additional textual features. We also propose a model to route newly posted questions to appropriate users based on the difficulty level of the question and the expertise of the user. Extensive experiments on real world CQAs such as Yahoo! Answers and Stack Overflow data demonstrate the improved efficacy of our approach over contemporary state-of-the-art models. The QDEE framework also allows us to characterize user expertise in novel ways by identifying interesting patterns and roles played by different users in such CQAs.

Sobhan Moosavi, Behrooz Omidvar-Tehrani, R. Bruce Craig et al.

Because of the increasing availability of spatiotemporal data, a variety of data-analytic applications have become possible. Characterizing driving context, where context may be thought of as a combination of location and time, is a new challenging application. An example of such a characterization is finding the correlation between driving behavior and traffic conditions. This contextual information enables analysts to validate observation-based hypotheses about the driving of an individual. In this paper, we present DriveContext, a novel framework to find the characteristics of a context, by extracting significant driving patterns (e.g., a slow-down), and then identifying the set of potential causes behind patterns (e.g., traffic congestion). Our experimental results confirm the feasibility of the framework in identifying meaningful driving patterns, with improvements in comparison with the state-of-the-art. We also demonstrate how the framework derives interesting characteristics for different contexts, through real-world examples.

Daniel S. Katz, Rajiv Ramnath

This paper is a contribution to the Computational Science & Engineering Software Sustainability and Productivity Challenges (CSESSP Challenges) Workshop (https://www.nitrd.gov/csessp/), sponsored by the Networking and Information Technology Research and Development (NITRD) Software Design and Productivity (SDP) Coordinating Group, held October 15th-16th 2015 in Washington DC, USA. It introduces the role of software at the National Science Foundation (NSF) and the NSF Software Infrastructure for Sustained Innovation (SI2) program, then describes challenges that the SI2 program has identified, including funding models, career paths, incentives, training, interdisciplinary work, portability, and dissemination, as well as lesson that have been learned.