Niloofar Yousefi

Farhan Fuad Abir, Sanjeda Sara Jennifer, Niloofar Yousefi et al.

We propose a hybrid diffusion-based augmentation framework to overcome the critical challenge of ultrasound data augmentation in breast ultrasound (BUS) datasets. Unlike conventional diffusion-based augmentations, our approach improves visual fidelity and preserves ultrasound texture by combining text-to-image generation with image-to-image (img2img) refinement, as well as fine-tuning with low-rank adaptation (LoRA) and textual inversion (TI). Our method generated realistic, class-consistent images on an open-source Kaggle breast ultrasound image dataset (BUSI). Compared to the Stable Diffusion v1.5 baseline, incorporating TI and img2img refinement reduced the Frechet Inception Distance (FID) from 45.97 to 33.29, demonstrating a substantial gain in fidelity while maintaining comparable downstream classification performance. Overall, the proposed framework effectively mitigates the low-fidelity limitations of synthetic ultrasound images and enhances the quality of augmentation for robust diagnostic modeling.

Ali Khodabandeh Yalabadi, Mehdi Yazdani-Jahromi, Niloofar Yousefi et al.

Drug-Target Interaction (DTI) prediction is vital for drug discovery, yet challenges persist in achieving model interpretability and optimizing performance. We propose a novel transformer-based model, FragXsiteDTI, that aims to address these challenges in DTI prediction. Notably, FragXsiteDTI is the first DTI model to simultaneously leverage drug molecule fragments and protein pockets. Our information-rich representations for both proteins and drugs offer a detailed perspective on their interaction. Inspired by the Perceiver IO framework, our model features a learnable latent array, initially interacting with protein binding site embeddings using cross-attention and later refined through self-attention and used as a query to the drug fragments in the drug's cross-attention transformer block. This learnable query array serves as a mediator and enables seamless information translation, preserving critical nuances in drug-protein interactions. Our computational results on three benchmarking datasets demonstrate the superior predictive power of our model over several state-of-the-art models. We also show the interpretability of our model in terms of the critical components of both target proteins and drug molecules within drug-target pairs.

Elias Hossain, Shubhashis Roy Dipta, Subash Neupane et al.

Neural NLP models are often miscalibrated, assigning high confidence to incorrect predictions, which undermines selective prediction and high-stakes deployment. Post-hoc calibration methods adjust output probabilities but leave internal computation unchanged, while ensemble and Bayesian approaches improve uncertainty at substantial training or storage cost. We propose UAT-LITE, an inference-time framework that makes self-attention uncertainty-aware using approximate Bayesian inference via Monte Carlo dropout in pretrained transformer classifiers. Token-level epistemic uncertainty is estimated from stochastic forward passes and used to modulate self-attention during contextualization, without modifying pretrained weights or training objectives. We additionally introduce a layerwise variance decomposition to diagnose how predictive uncertainty accumulates across transformer depth. Across the SQuAD 2.0 answerability, MNLI, and SST-2, UAT-LITE reduces Expected Calibration Error by approximately 20% on average relative to a fine-tuned BERT-base baseline while preserving task accuracy, and improves selective prediction and robustness under distribution shift.

Mehrdad Shoeibi, Elias Hossain, Ivan Garibay et al.

Learning from weak or proxy supervision is common when ground-truth labels are unavailable, yet robustness under distribution shift remains poorly understood, especially when the supervision mechanism itself changes. We formalize this as supervision drift, defined as changes in P(y | x, c) across contexts, and study it in CRISPR-Cas13d experiments where guide efficacy is inferred indirectly from RNA-seq responses. Using data from two human cell lines and multiple time points, we build a controlled non-IID benchmark with explicit domain and temporal shifts while keeping the weak-label construction fixed. Models achieve strong in-domain performance (ridge R^2 = 0.356, Spearman rho = 0.442) and partial cross-cell-line transfer (rho ~ 0.40). However, temporal transfer fails across all models, with negative R^2 and near-zero correlation (e.g., XGBoost R^2 = -0.155, rho = 0.056). Additional analyses confirm this pattern. Feature-label relationships remain stable across cell lines but change sharply over time, indicating that failures arise from supervision drift rather than model limitations. These findings highlight feature stability as a simple diagnostic for detecting non-transferability before deployment.

Nusrat Jahan Prottasha, Asif Mahmud, Md. Shohanur Islam Sobuj et al.

Large Language Models (LLMs) are gaining significant popularity in recent years for specialized tasks using prompts due to their low computational cost. Standard methods like prefix tuning utilize special, modifiable tokens that lack semantic meaning and require extensive training for best performance, often falling short. In this context, we propose a novel method called Semantic Knowledge Tuning (SK-Tuning) for prompt and prefix tuning that employs meaningful words instead of random tokens. This method involves using a fixed LLM to understand and process the semantic content of the prompt through zero-shot capabilities. Following this, it integrates the processed prompt with the input text to improve the model's performance on particular tasks. Our experimental results show that SK-Tuning exhibits faster training times, fewer parameters, and superior performance on tasks such as text classification and understanding compared to other tuning methods. This approach offers a promising method for optimizing the efficiency and effectiveness of LLMs in processing language tasks.

Elias Hossain, Mohammad Jahid Ibna Basher, Ivan Garibay et al.

Offline reinforcement learning (RL) can learn effective policies from fixed datasets, but deployment objectives may change after training, and in many applications the trained actor cannot be retrained because of data, cost, or governance constraints. We study deployment-time adaptation for frozen offline actors using Product-of-Experts (PoE) composition with a goal-conditioned prior. Our main practical finding is graceful degradation rather than universal performance gain: under degraded or random priors, precision-weighted composition remains anchored to the frozen actor, while additive and prior-only adaptation collapse, and a KL-budget selector often recovers a near-oracle operating point. We also make explicit a closed-form identity in the frozen-actor setting: for diagonal-Gaussian actors and priors, PoE with coefficient alpha yields the same deterministic policy as KL-regularized adaptation with beta = alpha / (1 - alpha), with posterior covariances differing only by a global scalar factor. Empirically, across four D4RL environments (3,900 MuJoCo episodes), we observe a 4/5/3 HELP/FROZEN/HURT split. Extending the analysis to six harder cells and two AntMaze diagnostics reveals an actor-competence ceiling: medium-expert remains HURT in all 9 cells at every tested alpha, while AntMaze with a behavior-cloned frozen actor yields zero success for all composition rules. Overall, PoE and KL-regularized adaptation are best viewed as a single actor-anchored safety mechanism for deployment-time steering.

Md Kowsher, Tara Esmaeilbeig, Chun-Nam Yu et al.

We propose RoCoFT, a parameter-efficient fine-tuning method for large-scale language models (LMs) based on updating only a few rows and columns of the weight matrices in transformers. Through extensive experiments with medium-size LMs like BERT and RoBERTa, and larger LMs like Bloom-7B, Llama2-7B, and Llama2-13B, we show that our method gives comparable or better accuracies than state-of-art PEFT methods while also being more memory and computation-efficient. We also study the reason behind the effectiveness of our method with tools from neural tangent kernel theory. We empirically demonstrate that our kernel, constructed using a restricted set of row and column parameters, are numerically close to the full-parameter kernel and gives comparable classification performance. Ablation studies are conducted to investigate the impact of different algorithmic choices, including the selection strategy for rows and columns as well as the optimal rank for effective implementation of our method.

Md Kowsher, Nusrat Jahan Prottasha, Prakash Bhat et al.

This paper argues that generating output tokens is more effective than using pooled representations for prediction tasks because token-level generation retains more mutual information. Since LLMs are trained on massive text corpora using next-token prediction, generation aligns naturally with their learned behavior. Using the Data Processing Inequality (DPI), we provide both theoretical and empirical evidence supporting this claim. However, autoregressive models face two key challenges when used for prediction: (1) exposure bias, where the model sees ground truth tokens during training but relies on its own predictions during inference, leading to errors, and (2) format mismatch, where discrete tokens do not always align with the tasks required output structure. To address these challenges, we introduce PredGen(Predicting Through Generating), an end to end framework that (i) uses scheduled sampling to reduce exposure bias, and (ii) introduces a task adapter to convert the generated tokens into structured outputs. Additionally, we introduce Writer-Director Alignment Loss (WDAL), which ensures consistency between token generation and final task predictions, improving both text coherence and numerical accuracy. We evaluate PredGen on multiple classification and regression benchmarks. Our results show that PredGen consistently outperforms standard baselines, demonstrating its effectiveness in structured prediction tasks.

Md Kowsher, Nusrat Jahan Prottasha, Chun-Nam Yu et al.

The success of self-attention lies in its ability to capture long-range dependencies and enhance context understanding, but it is limited by its computational complexity and challenges in handling sequential data with inherent directionality. This work introduces a shared weight self-attention-based BERT model that only learns one weight matrix for (Key, Value, and Query) representations instead of three individual matrices for each of them. Our shared weight attention reduces the training parameter size by more than half and training time by around one-tenth. Furthermore, we demonstrate higher prediction accuracy on small tasks of GLUE over the BERT baseline and in particular a generalization power on noisy and out-of-domain data. Experimental results indicate that our shared self-attention method achieves a parameter size reduction of 66.53% in the attention block. In the GLUE dataset, the shared weight self-attention-based BERT model demonstrates accuracy improvements of 0.38%, 5.81%, and 1.06% over the standard, symmetric, and pairwise attention-based BERT models, respectively. The model and source code are available at Anonymous.

Md Kowsher, Md. Shohanur Islam Sobuj, Nusrat Jahan Prottasha et al.

Time series forecasting remains a challenging task, particularly in the context of complex multiscale temporal patterns. This study presents LLM-Mixer, a framework that improves forecasting accuracy through the combination of multiscale time-series decomposition with pre-trained LLMs (Large Language Models). LLM-Mixer captures both short-term fluctuations and long-term trends by decomposing the data into multiple temporal resolutions and processing them with a frozen LLM, guided by a textual prompt specifically designed for time-series data. Extensive experiments conducted on multivariate and univariate datasets demonstrate that LLM-Mixer achieves competitive performance, outperforming recent state-of-the-art models across various forecasting horizons. This work highlights the potential of combining multiscale analysis and LLMs for effective and scalable time-series forecasting.

Elias Hossain, Md Mehedi Hasan Nipu, Maleeha Sheikh et al.

We propose MedBayes-Lite, a lightweight Bayesian enhancement for transformer-based clinical language models designed to produce reliable, uncertainty-aware predictions. Although transformers show strong potential for clinical decision support, they remain prone to overconfidence, especially in ambiguous medical cases where calibrated uncertainty is critical. MedBayes-Lite embeds uncertainty quantification directly into existing transformer pipelines without any retraining or architectural rewiring, adding no new trainable layers and keeping parameter overhead under 3 percent. The framework integrates three components: (i) Bayesian Embedding Calibration using Monte Carlo dropout for epistemic uncertainty, (ii) Uncertainty-Weighted Attention that marginalizes over token reliability, and (iii) Confidence-Guided Decision Shaping inspired by clinical risk minimization. Across biomedical QA and clinical prediction benchmarks (MedQA, PubMedQA, MIMIC-III), MedBayes-Lite consistently improves calibration and trustworthiness, reducing overconfidence by 32 to 48 percent. In simulated clinical settings, it can prevent up to 41 percent of diagnostic errors by flagging uncertain predictions for human review. These results demonstrate its effectiveness in enabling reliable uncertainty propagation and improving interpretability in medical AI systems.

Elias Hossain, Mehrdad Shoeibi, Ivan Garibay et al.

We propose CITE V.1, an agentic, evidence-grounded framework that leverages Large Language Models (LLMs) to provide transparent and reproducible interpretations of RNA-seq clusters. Unlike existing enrichment-based approaches that reduce results to broad statistical associations and LLM-only models that risk unsupported claims or fabricated citations, CITE V.1 transforms cluster interpretation by producing biologically coherent explanations explicitly anchored in the biomedical literature. The framework orchestrates three specialized agents: a Retriever that gathers domain knowledge from PubMed and UniProt, an Interpreter that formulates functional hypotheses, and Critics that evaluate claims, enforce evidence grounding, and qualify uncertainty through confidence and reliability indicators. Applied to Salmonella enterica RNA-seq data, CITE V.1 generated biologically meaningful insights supported by the literature, while an LLM-only Gemini baseline frequently produced speculative results with false citations. By moving RNA-seq analysis from surface-level enrichment to auditable, interpretable, and evidence-based hypothesis generation, CITE V.1 advances the transparency and reliability of AI in biomedicine.

Sina Abdidizaji, Md Kowsher, Niloofar Yousefi et al.

In the era of digitalization, as individuals increasingly rely on digital platforms for communication and news consumption, various actors employ linguistic strategies to influence public perception. While models have become proficient at detecting explicit patterns, which typically appear in texts as single remarks referred to as utterances, such as social media posts, malicious actors have shifted toward utilizing implicit influential verbal patterns embedded within conversations. These verbal patterns aim to mentally penetrate the victim's mind in order to influence them, enabling the actor to obtain the desired information through implicit means. This paper presents an improved approach for detecting such implicit influential patterns. Furthermore, the proposed model is capable of identifying the specific locations of these influential elements within a conversation. To achieve this, the existing dataset was augmented using the reasoning capabilities of state-of-the-art language models. Our designed framework resulted in a 6% improvement in the detection of implicit influential patterns in conversations. Moreover, this approach improved the multi-label classification tasks related to both the techniques used for influence and the vulnerability of victims by 33% and 43%, respectively.

Md Kowsher, Nusrat Jahan Prottasha, Shiyun Xu et al.

Bidirectional language models have better context understanding and perform better than unidirectional models on natural language understanding tasks, yet the theoretical reasons behind this advantage remain unclear. In this work, we investigate this disparity through the lens of the Information Bottleneck (IB) principle, which formalizes a trade-off between compressing input information and preserving task-relevant content. We propose FlowNIB, a dynamic and scalable method for estimating mutual information during training that addresses key limitations of classical IB approaches, including computational intractability and fixed trade-off schedules. Theoretically, we show that bidirectional models retain more mutual information and exhibit higher effective dimensionality than unidirectional models. To support this, we present a generalized framework for measuring representational complexity and prove that bidirectional representations are strictly more informative under mild conditions. We further validate our findings through extensive experiments across multiple models and tasks using FlowNIB, revealing how information is encoded and compressed throughout training. Together, our work provides a principled explanation for the effectiveness of bidirectional architectures and introduces a practical tool for analyzing information flow in deep language models.

Mohammad Jahid Ibna Basher, Md Kowsher, Md Saiful Islam et al.

This paper introduces BnTTS (Bangla Text-To-Speech), the first framework for Bangla speaker adaptation-based TTS, designed to bridge the gap in Bangla speech synthesis using minimal training data. Building upon the XTTS architecture, our approach integrates Bangla into a multilingual TTS pipeline, with modifications to account for the phonetic and linguistic characteristics of the language. We pre-train BnTTS on 3.85k hours of Bangla speech dataset with corresponding text labels and evaluate performance in both zero-shot and few-shot settings on our proposed test dataset. Empirical evaluations in few-shot settings show that BnTTS significantly improves the naturalness, intelligibility, and speaker fidelity of synthesized Bangla speech. Compared to state-of-the-art Bangla TTS systems, BnTTS exhibits superior performance in Subjective Mean Opinion Score (SMOS), Naturalness, and Clarity metrics.

Toktam A. Oghaz, Ece C. Mutlu, Jasser Jasser et al.

Online social media platforms are turning into the prime source of news and narratives about worldwide events. However,a systematic summarization-based narrative extraction that can facilitate communicating the main underlying events is lacking. To address this issue, we propose a novel event-based narrative summary extraction framework. Our proposed framework is designed as a probabilistic topic model, with categorical time distribution, followed by extractive text summarization. Our topic model identifies topics' recurrence over time with a varying time resolution. This framework not only captures the topic distributions from the data, but also approximates the user activity fluctuations over time. Furthermore, we define significance-dispersity trade-off (SDT) as a comparison measure to identify the topic with the highest lifetime attractiveness in a timestamped corpus. We evaluate our model on a large corpus of Twitter data, including more than one million tweets in the domain of the disinformation campaigns conducted against the White Helmets of Syria. Our results indicate that the proposed framework is effective in identifying topical trends, as well as extracting narrative summaries from text corpus with timestamped data.

Marie Alaghband, Niloofar Yousefi, Ivan Garibay

Facial expressions are important parts of both gesture and sign language recognition systems. Despite the recent advances in both fields, annotated facial expression datasets in the context of sign language are still scarce resources. In this manuscript, we introduce an annotated sequenced facial expression dataset in the context of sign language, comprising over $3000$ facial images extracted from the daily news and weather forecast of the public tv-station PHOENIX. Unlike the majority of currently existing facial expression datasets, FePh provides sequenced semi-blurry facial images with different head poses, orientations, and movements. In addition, in the majority of images, identities are mouthing the words, which makes the data more challenging. To annotate this dataset we consider primary, secondary, and tertiary dyads of seven basic emotions of "sad", "surprise", "fear", "angry", "neutral", "disgust", and "happy". We also considered the "None" class if the image's facial expression could not be described by any of the aforementioned emotions. Although we provide FePh as a facial expression dataset of signers in sign language, it has a wider application in gesture recognition and Human Computer Interaction (HCI) systems.

Niloofar Yousefi, Marie Alaghband, Ivan Garibay

With the increase of credit card usage, the volume of credit card misuse also has significantly increased. As a result, financial organizations are working hard on developing and deploying credit card fraud detection methods, in order to adapt to ever-evolving, increasingly sophisticated defrauding strategies and identifying illicit transactions as quickly as possible to protect themselves and their customers. Compounding on the complex nature of such adverse strategies, credit card fraudulent activities are rare events compared to the number of legitimate transactions. Hence, the challenge to develop fraud detection that are accurate and efficient is substantially intensified and, as a consequence, credit card fraud detection has lately become a very active area of research. In this work, we provide a survey of current techniques most relevant to the problem of credit card fraud detection. We carry out our survey in two main parts. In the first part,we focus on studies utilizing classical machine learning models, which mostly employ traditional transnational features to make fraud predictions. These models typically rely on some static physical characteristics, such as what the user knows (knowledge-based method), or what he/she has access to (object-based method). In the second part of our survey, we review more advanced techniques of user authentication, which use behavioral biometrics to identify an individual based on his/her unique behavior while he/she is interacting with his/her electronic devices. These approaches rely on how people behave (instead of what they do), which cannot be easily forged. By providing an overview of current approaches and the results reported in the literature, this survey aims to drive the future research agenda for the community in order to develop more accurate, reliable and scalable models of credit card fraud detection.

Ramya Akula, Niloofar Yousefi, Ivan Garibay

Information spreads on complex social networks extremely fast, in other words, a piece of information can go viral within no time. Often it is hard to barricade this diffusion prior to the significant occurrence of chaos, be it a social media or an online coding platform. GitHub is one such trending online focal point for any business to reach their potential contributors and customers, simultaneously. By exploiting such software development paradigm, millions of free software emerged lately in diverse communities. To understand human influence, information spread and evolution of transmitted information among assorted users in GitHub, we developed a deep neural network model: DeepFork, a supervised machine learning based approach that aims to predict information diffusion in complex social networks; considering node as well as topological features. In our empirical studies, we observed that information diffusion can be detected by link prediction using supervised learning. DeepFork outperforms other machine learning models as it better learns the discriminative patterns from the input features. DeepFork aids in understanding information spread and evolution through a bipartite network of users and repositories i.e., information flow from a user to repository to user.

Niloofar Yousefi, Cong Li, Mansooreh Mollaghasemi et al.

This paper introduces a new and effective algorithm for learning kernels in a Multi-Task Learning (MTL) setting. Although, we consider a MTL scenario here, our approach can be easily applied to standard single task learning, as well. As shown by our empirical results, our algorithm consistently outperforms the traditional kernel learning algorithms such as uniform combination solution, convex combinations of base kernels as well as some kernel alignment-based models, which have been proven to give promising results in the past. We present a Rademacher complexity bound based on which a new Multi-Task Multiple Kernel Learning (MT-MKL) model is derived. In particular, we propose a Support Vector Machine-regularized model in which, for each task, an optimal kernel is learned based on a neighborhood-defining kernel that is not restricted to be positive semi-definite. Comparative experimental results are showcased that underline the merits of our neighborhood-defining framework in both classification and regression problems.

Niloofar Yousefi, Yunwen Lei, Marius Kloft et al.

We show a Talagrand-type concentration inequality for Multi-Task Learning (MTL), using which we establish sharp excess risk bounds for MTL in terms of distribution- and data-dependent versions of the Local Rademacher Complexity (LRC). We also give a new bound on the LRC for norm regularized as well as strongly convex hypothesis classes, which applies not only to MTL but also to the standard i.i.d. setting. Combining both results, one can now easily derive fast-rate bounds on the excess risk for many prominent MTL methods, including---as we demonstrate---Schatten-norm, group-norm, and graph-regularized MTL. The derived bounds reflect a relationship akeen to a conservation law of asymptotic convergence rates. This very relationship allows for trading off slower rates w.r.t. the number of tasks for faster rates with respect to the number of available samples per task, when compared to the rates obtained via a traditional, global Rademacher analysis.

Niloofar Yousefi, Michael Georgiopoulos, Georgios C. Anagnostopoulos

When faced with learning a set of inter-related tasks from a limited amount of usable data, learning each task independently may lead to poor generalization performance. Multi-Task Learning (MTL) exploits the latent relations between tasks and overcomes data scarcity limitations by co-learning all these tasks simultaneously to offer improved performance. We propose a novel Multi-Task Multiple Kernel Learning framework based on Support Vector Machines for binary classification tasks. By considering pair-wise task affinity in terms of similarity between a pair's respective feature spaces, the new framework, compared to other similar MTL approaches, offers a high degree of flexibility in determining how similar feature spaces should be, as well as which pairs of tasks should share a common feature space in order to benefit overall performance. The associated optimization problem is solved via a block coordinate descent, which employs a consensus-form Alternating Direction Method of Multipliers algorithm to optimize the Multiple Kernel Learning weights and, hence, to determine task affinities. Empirical evaluation on seven data sets exhibits a statistically significant improvement of our framework's results compared to the ones of several other Clustered Multi-Task Learning methods.