论文检索

Yang Yan, Matthew W. Chen, Jiayi Lyu, Chen Zhao, Hao Gao, Zhong Chen

Radiotherapy (RT) is a cornerstone of cancer treatment. Following RT, patient-reported outcomes (PROs) collected via standardized questionnaires are crucial for monitoring patients' quality of life and side effects. However, traditional statistical and machine learning methods, which rely on structured numerical data, often fail to capture semantic meaning within patients' health status. To address this, we developed a novel framework using zero- and few-shot large language models (LLMs) to identify patients experiencing mild to severe depression. Furthermore, classification performance is enhanced through parameter-efficient fine-tuning. Experiments on a prostate cancer PRO dataset for depression have demonstrated that our fine-tuned LLMs consistently outperformed other baseline methods across key evaluation metrics.

Egor Suraveikin, Dastan Omirzak, Roman Sultimov, Yury Maximov

The contextual multi-armed bandit problem underlies applications in recommendations, e-commerce, finance, and healthcare, where balancing exploration and exploitation is critical. While algorithms such as Upper Confidence Bound (UCB) and Thompson Sampling (TS) achieve strong theoretical guarantees, they often incur heavy computational cost from high-dimensional parameter estimation. We propose a new approach that combines reward sampling with online stochastic optimization. At each round, the algorithm samples hypothetical rewards for all actions and selects the action with the largest draw; the observed reward then updates the model via stochastic optimization. This design is both simple and efficient, preserving exploration while avoiding the pitfalls of greedy behavior on near-duplicate arms. Across synthetic and real-world datasets, our method attains near-optimal reward more quickly and with substantially lower computation than TS and UCB, demonstrating that sampling directly in reward space can improve both statistical efficiency and scalability.

Suraj Prasad, Navyansh Mahla, Sunny Gupta, Amit Sethi

Existing federated prompt learning methods for vision-language models like CLIP rely solely on text-based prompts and final-layer visual features, missing crucial multiscale visual details and client-specific style variations. This limits generalization across non-IID distributions and novel classes. We introduce FedCSAP (Federated Cross-Modal Style-Aware Prompt Generation), which harnesses multiscale features from CLIP's vision encoder alongside domain-aware style statistics from client data. By fusing these visual representations with textual context, FedCSAP generates adaptive, context-aware prompts that enhance robustness across seen and unseen classes. Our privacy-preserving approach operates through local training and global aggregation, effectively handling heterogeneous client distributions. Experiments on multiple image classification datasets demonstrate that FedCSAP significantly outperforms existing federated prompt learning methods in both accuracy and generalization.

Ha-Hieu Pham, Minh Le, Han Huynh, Nguyen Quoc Khanh Le, Huy-Hieu Pham

Semi-supervised semantic segmentation (SSSS) is vital in computational pathology, where dense annotations are costly and limited. Existing methods often rely on pixel-level consistency, which propagates noisy pseudo-labels and produces fragmented or topologically invalid masks. We propose Topology Graph Consistency (TGC), a framework that integrates graph-theoretic constraints by aligning Laplacian spectra, component counts, and adjacency statistics between prediction graphs and references. This enforces global topology and improves segmentation accuracy. Experiments on GlaS and CRAG demonstrate that TGC achieves state-of-the-art performance under 5–10% supervision and significantly narrows the gap to full supervision.

Yuto Morimoto, Zhipeng Wang, Koji Yasuda

Transformer models have achieved remarkable success across diverse deep learning fields, including natural language processing (NLP) and computer vision (CV). One drawback of these models is that the computational cost of the softmax attention, the core component of the transformer, exhibits quadratic complexity in both time and memory. As data scales up various attempts have been reported to overcome this bottleneck. The objective of this study is to propose a novel attention mechanism, "Cumulant Attention", that systematically balances efficiency and accuracy. This proposal introduces a statistical-mechanics perspective and a reliable approximation based on cumulant expansion into the attention layer. The low-order variant reduces computational complexity to linear order, similar to the linear attention, while keeping nonlinearity of the softmax attention. We evaluate several variants on CV tasks, including image classification with ViT on ImageNet-100 and video classification with ViViT on UCF-101. Experimental results demonstrate that the cumulant attention outperforms the linear attention and achieves accuracy comparable to the softmax attention. These findings validate the effectiveness of our approach and highlight future directions, including scaling to larger models, extending to other modalities, and optimizing implementations for GPU hardware.

Aline Cambri Fredere, Gabriel De Oliveira Ramos, Luciano Garim Garcia, Mateus da Rocha Simionato, José Manuel Marques Teixeira de Oliveira, Ariane Santos da Silveira

Machine learning applications in reservoir modeling are hindered by the limited availability of well log data, a common challenge in the oil and gas industry. We propose VAEc-tMC, a domain-informed Conditional Variational Autoencoder that generates synthetic well-log data conditioned on rock type. Addressing a critical gap by existing generative models that rely solely on statistical reconstruction, our model embeds geological domain knowledge into the latent space, and optimizes a modified objective with an adaptive Student-t reconstruction loss and a beta-weighted KL regularizer, improving stability under heavy-tailed data. When used for data augmentation, the synthetic samples preserve inter-log dependencies and substantially enhance downstream classification, accuracy 39→63%, F1-score 36→68%, AUC 0.46→0.80 on a held-out well. Beyond the geological context, the proposed approach illustrates a generalizable strategy where domain-aware generative models with adaptive loss functions provide a robust solution for data-efficient learning in scientific domains facing data scarcity, noise, and heavy-tailed distributions.

Adit Desai, Sudipta Roy, Mohna Chakraborty

Vision-Language Models (VLMs) are increasingly deployed across downstream tasks, yet their training data often encode social biases that surface in outputs. Unlike humans, who interpret images through contextual and social cues, VLMs process them through statistical associations, often leading to reasoning that diverges from human reasoning. By analyzing how a VLM reasons, we can understand how inherent biases are perpetuated and can adversely affect downstream performance. To examine this gap, we systematically analyze social biases in five open-source VLMs for an occupation prediction task, on the FairFace dataset. Across 32 occupations and three different prompting styles, we elicit both predictions and reasoning. Our findings show that the biased reasoning patterns systematically underlie intersectional disparities, highlighting the need to align VLM reasoning with human values before downstream deployment.

Krishi Chawda, Jean Erik Delanois, Giri P Krishnan, Maksim Bazhenov

One of the central challenges in deep learning is that models trained on new tasks often overfit and lose the ability to generalize. This issue arises because gradient descent often converges to solutions in regions of the loss landscape that are sharp near their minima. High sharpness leads to rapid performance loss when test data are perturbed or statistically shifted. Although sharpness has been linked to generalization, few methods directly target it to improve generalization. Here we demonstrate that an unsupervised, sleep-like replay algorithm identifies low loss regions with lower sharpness leading to improvement in generalization to distortions, including Gaussian and salt-and-pepper noise. Our study identifies loss-function sharpness as a unifying measure for generalizable learning and robustness, and points to new principles for designing resilient AI systems.

Zijian Zhao

Recently, deep Reinforcement Learning (RL) methods have been widely used in labor management within transportation gig markets, such as ride-hailing, food delivery, and express delivery. Compared to traditional rule-based and optimization-based methods, RL can capture more information about long-term uncertainty and environmental dynamics, leading to better and non-myopic strategies. However, deep learning methods have long been criticized for their low interpretability, raising concerns about algorithmic discrimination in gig markets. Currently, most works focus on this issue from the perspective of statistical analysis and surveys. However, the underlying reasons related to the algorithms remain unclear, as most companies do not disclose their algorithms. This lack of transparency can hinder governments from designing efficient management policies to address these problems. To fill this research gap, this thesis proposal aims to develop appropriate RL methods to mimic the labor management behavior of transportation gig platforms and to propose effective policies that protect the rights of gig workers.

Depanshu Sani

Nature is inherently structured! The entities in the real world are naturally organized in rich relationships. For example, dolphins and sharks, despite their striking visual resemblance in body shape and fins, are actually from entirely different branches of the animal hierarchy, i.e., mammals and fishes, respectively. This remarkable similarity is a prime example of ‘convergent evolution’, where unrelated species develop similar features because they face similar environmental challenges. This illustrates how nature’s underlying organization often transcends superficial visual resemblances. Although humans intuitively grasp and utilize these profound natural constraints, they are typically underutilized in most AI systems. As a result, trained AI models tend to align with statistical patterns in the data, such as sampling biases or class imbalance, rather than adhering to the underlying relational consistency. This thesis argues that AI systems must evolve beyond learning “flat” feature representations, which are domain-agnostic and derived purely from data correlations, to “explicitly model the domain-specific structural relationships”. A key benefit of encoding relational priors in the learning process is that it can inject domain knowledge as an inductive bias, leading to more robust and reliable models. My research investigates incorporating domain knowledge by leveraging “graph-based structural priors” that explicitly model relational constraints in various visual recognition tasks. This work spans three distinct dimensions of visual recognition, progressing from coarse-level (image-level) to fine-grained (scene-level) understanding. My research highlights a crucial limitation in existing AI models: they often fail to incorporate real-world constraints, leading to significant errors. I show that even powerful, pre-trained neural networks can make severe mistakes due to a lack of domain knowledge. I argue that standard metrics like top-1 accuracy, precision, and recall are insufficient for evaluating model robustness, and propose a new metric based on rank order of the predictions as a better indicator of reliability. The benchmark on various large-scale datasets confirms that existing solutions do not sufficiently capture the domain knowledge, which is often available as a taxonomy tree, motivating our design of better learning frameworks. I also examine complex visual re-identification (Re-ID) tasks, such as monitoring animals in the wild. I find that existing foundational models struggle with new species and environments. This challenge is compounded by the high cost of manual annotation for adapting these systems to new settings. While existing unsupervised learning methods can help reduce the need for extensive labeling, they often suffer from under- and over-segmentation errors, which led me to develop more effective active learning strategies. Finally, I address the limitations of the classic Kalman filter, a widely used tool for dynamic systems. I point out that this filter makes a flawed assumption that the movement of each individual object is independent of its dynamic surroundings. In the real world, this is rarely the case. I demonstrate the need for a new filtering mechanism that not only considers an object’s past movements but also its spatial relationship with other dynamic entities in its environment. In my analysis, I observed the vision foundation models for all recognition tasks, i.e., classification, detection, and segmentation, lack the domain knowledge. I believe that our learning framework, which was designed specifically for classification, can be adapted for other recognition tasks. I speculate that a unified learning framework can be designed that can be leveraged for making vision foundation models aware of the available taxonomy.

Aniket Roy

The rapid advancement of generative models has created new opportunities for addressing core challenges in computer vision, including data scarcity, image quality, and efficient personalization. My research develops principled, resource- aware methods that enable models to generalize effectively from limited supervision, adapt efficiently to new concepts, and generate high-fidelity visual content. I first address few-shot learning through augmentation-driven uncertainty- guided mixup, improving robustness in data-constrained regimes. Building on this, I propose caption-guided multi-modal augmentation techniques that enrich visual diversity while mitigating real-to-synthetic domain gaps. To enhance the quality and realism of generated images, I introduce diffusion models grounded in natural image statistics, yielding perceptually aligned outputs suitable for downstream tasks. To advance personalization, I develop parameter-efficient mechanisms for combining low-rank adapters, enabling fine-grained control over content and style without retraining. I further extend personalization to a zero-shot setting through a training-free textual-inversion-based method that customizes arbitrary objects directly within the diffusion process. Finally, I present a frequency-guided multi-LoRA fusion framework that leverages wavelet-domain cues and timestep-aware weighting for accurate, training-free concept composition. Collectively, these contributions move toward a unified vision of generative models that are efficient, adaptive, and capable of high-quality, customizable image synthesis.

Maxime Meyer

Transformers have reshaped modern artificial intelligence, yet their theoretical foundations remain incomplete. This thesis investigates the approximation power and memory limitations of transformers. I combine tools from approximation theory and statistical learning theory to provide provable guarantees on expressivity, memorization capacity, and inherent architectural constraints. My contributions include the first rigorous proof of memory bottlenecks in prompt tuning and new results on the expressivity of transformers. The long-term goal of my doctoral research is to develop a principled theoretical framework that grounds the empirical behavior of large-scale transformer models in formal approximation-theoretic results.

Katherine S. Moore, Helen Zhang, Irene Lee

Adolescents struggle to understand bias and representation in AI, particularly the concept of how datasets used in machine learning can be representative of populations or not. Within early experiments in teaching about investigating bias in AI systems using the Developing AI Literacy (DAILy) curriculum, we observed participating youth struggling to understand what it meant to be represented in the output of AI tools. For example, when using Google Image Search with prompts such as “physicist” and “outdoor recreation,” participating youth did not understand the question, “Are you represented in this outcome?” We saw an opportunity to address this challenge using the Kapor Foundation's Responsible AI and Tech Justice Guide. Drawing insights from three of the six core components of the framework presented in the guide, we developed Games of Representation (GR), a series of three card-based activities using SET game cards to teach concepts of population, sample, dataset, and representation. Through game play, players manipulate datasets, role-play as stakeholders with competing interests, and explore real-world scenarios where representation matters. The GR games and corresponding guide provide educators, families, and care providers with flexible, hands-on activities for guided, playful conversations with adolescents about AI ethics. This work contributes practical resources for K-12 AI education while addressing critical gaps in youth understanding of statistical bias and stakeholder influence in AI development.

Maria Kasinidou, Styliani Kleanthous, Jahna Otterbacher, Evgenia Christoforou

As AI technologies grow more influential in shaping modern life, there is an urgent need to make AI literacy accessible beyond academic and technical communities. This paper presents the design, delivery, and evaluation of an online AI course targeting the general public. The course combined asynchronous lectures, interactive live sessions, and reflective assignments. Of the 343 people who registered, 169 completed the program. Using validated instruments administered before and after the course, we measured changes in participants’ attitudes toward AI and their AI literacy. Our findings revealed statistically significant changes in AI literacy, specifically in awareness, usage, and evaluation constructs, as well as a rise in positive attitudes toward AI. High satisfaction scores and qualitative feedback further support the course’s effectiveness. These findings reinforce the importance of inclusive, scalable educational interventions for empowering the public to navigate AI technologies.

Chibuike E. Ugwu, Roschelle Fritz, Diane J. Cook, Jana Doppa

Urinary tract infection (UTI) flare-ups pose a significant health risk for older adults with chronic conditions. These infections often go unnoticed until they become severe, making early detection through innovative smart home technologies crucial. Traditional machine learning (ML) approaches relying on simple binary classification for UTI detection offer limited utility to nurses and practitioners as they lack insight into prediction uncertainty, hindering informed clinical decision-making. This paper presents a clinician-in-the-loop (CIL) smart home system that leverages ambient sensor data to extract meaningful behavioral markers, train robust predictive ML models, and calibrate them to enable uncertainty-aware decision support. The system incorporates a statistically valid uncertainty quantification method called Conformal-Calibrated Interval (CCI), which quantifies uncertainty and abstains from making predictions ("I don’t know") when the ML model's confidence is low. Evaluated on real-world data from eight smart homes, our method outperforms baseline methods in recall and other classification metrics while maintaining the lowest abstention proportion and interval width. A survey of 42 nurses confirms that our system's outputs are valuable for guiding clinical decision-making, underscoring their practical utility in improving informed decisions and effectively managing UTIs and other condition flare-ups in older adults.

Arpit Tiwari, Bhavuk Singhal, Anshu Aditya, Aryan Tiwari, Shubham Jain, Debashis Mukherjee, Debdoot Mukherjee

In e-commerce logistics, accurate geospatial clustering is essential for optimizing resource allocation, manpower planning, and delivery network design. However, existing density-based clustering approaches, particularly their reliance on heuristic parameter tuning, have been underexplored in datasets with significant density variations, limiting robustness and scalability. This study presents an unsupervised framework that extends DBSCAN by leveraging Gaussian Mixture Models (GMM). First, we propose a method that systematically identifies suitable clustering scales through statistical modeling. Second, the approach iteratively applies DBSCAN to extract clusters from dense to sparse regions, overcoming single-parameter limitations. Finally, we validate the method through large-scale offline experiments using data from over 200 last-mile dispatch centers (LMDC). The results demonstrate the framework’s effectiveness in identifying heterogeneous geographic demand patterns and supporting workforce planning and operational benchmarking. This framework provides a scalable solution to a critical challenge in e-commerce logistics, offering a valuable reference for strategic and operational decision-making.

Qiming Guo, Bishal Khatri, Wenbo Sun, Jinwen Tang, Hua Zhang, Wenlu Wang

Underground pipeline leaks and infiltrations pose significant threats to water security and environmental safety. Traditional manual inspection methods provide limited coverage and delayed response, often missing critical anomalies. This paper proposes AquaSentinel, a novel physics-informed AI system for real-time anomaly detection in urban underground water pipeline networks. We introduce four key innovations: (1) strategic sparse sensor deployment at high-centrality nodes combined with physics-based state augmentation to achieve network-wide observability from minimal infrastructure; (2) the RTCA (Real-Time Cumulative Anomaly) detection algorithm, which employs dual-threshold monitoring with adaptive statistics to distinguish transient fluctuations from genuine anomalies; (3) a Mixture of Experts (MoE) ensemble of spatiotemporal graph neural networks that provides robust predictions by dynamically weighting model contributions; (4) causal flow-based leak localization that traces anomalies upstream to identify source nodes and affected pipe segments. Our system strategically deploys sensors at critical network junctions and leverages physics-based modeling to propagate measurements to unmonitored nodes, creating virtual sensors that enhance data availability across the entire network. Experimental evaluation using 110 leak scenarios demonstrates that AquaSentinel achieves 100% detection accuracy. This work advances pipeline monitoring by demonstrating that physics-informed sparse sensing can match the performance of dense deployments at a fraction of the cost, providing a practical solution for aging urban infrastructure.

Yang Xi, Orelia Pi, Miaomiao Zhang, Rebecca Xiong, Jacqueline Lane, Nihar B Shah

There is growing interest in applying artificial intelligence (AI) to automate and support complex decision-making tasks. However, it remains unclear how algorithms compare to human judgment in contexts requiring semantic understanding and domain expertise. We examine this in the context of the judge assignment problem, matching submissions to suitably qualified judges. Specifically, we tackled this problem at the Harvard President’s Innovation Challenge, the university’s premier venture competition awarding over $500,000 to student and alumni startups. This setting represents a real-world environment where high-quality judge assignment is essential. We developed an AI-based judge assignment algorithm, the Hybrid Lexical-Semantic Similarity Ensemble (HLSE), and deployed it at the competition. We then evaluated its performance against human expert assignments using blinded match-quality scores from judges on 309 judge-venture pairs. Using a Mann-Whitney U statistic-based test, we found no statistically significant difference in assignment quality between the two approaches (AUC=0.48, p=0.40); on average, algorithmic matches were rated 3.90 and manual matches 3.94 on a 5-point scale, where 5 indicates an excellent match. Furthermore, manual assignments that previously required a full week could be automated in several hours by the algorithm during deployment. These results demonstrate that HLSE achieves human-expert-level matching quality while offering greater scalability and efficiency, underscoring the potential of AI-driven solutions to support and enhance human decision-making for judge assignment in high-stakes settings.

Chinmay Soni, Shivam Chourasia, Gaurav Kumar, Hitesh Kapoor

Applying large, proprietary API-based language models to text-to-SQL tasks poses a significant industry challenge: reliance on massive, schema-heavy prompts results in prohibitive per-token API costs and high latency, hindering scalable production deployment. We present a specialized, self-hosted 8B-parameter model designed for a conversational bot in CriQ, a sister app to Dream11—India’s largest fantasy sports platform with over 250 million users—that answers user queries about cricket statistics. Our novel two-phase supervised fine-tuning approach enables the model to internalize the entire database schema, eliminating the need for long-context prompts. This reduces input tokens by over 99%, from a 17k-token baseline to fewer than 100, and replaces costly external API calls with efficient local inference. The resulting system achieves 98.4% execution success and 92.5% semantic accuracy, substantially outperforming a prompt-engineered baseline using Google’s Gemini Flash 2.0 (95.6% execution, 89.4% semantic accuracy). These results demonstrate a practical path toward high-precision, low-latency text-to-SQL applications using domain-specialized, self-hosted language models in large-scale production environments.

Abhishek Divekar, Anirban Majumder

Evaluating the quality of search systems traditionally requires a significant number of human relevance annotations. In recent times, several systems have explored the usage of Large Language Models (LLMs) as automated judges for this task while their inherent biases prevent direct use for metric estimation. We present a statistical framework extending Prediction-Powered Inference (PPI) that combines minimal human annotations with LLM judgments to produce reliable estimates of metrics which require sub-instance annotations. Our method requires as few as 100 human-annotated queries and 10,000 unlabeled examples, reducing annotation requirements significantly compared to traditional approaches. We formulate our proposed framework (PRECISE) for inference of relevance uplift for an LLM-based query reformulation application, extending PPI to sub-instance annotations at the query-document level. By reformulating the metric-integration space, we reduced the computational complexity from O(2^|C|) to O(2^K), where |C| represents corpus size (in order of millions). Detailed experiments across prominent retrieval datasets demonstrate that our method reduces the variance of estimates for the business-critical Precision@K metric, while effectively correcting for LLM bias in low-resource settings.