论文检索

Bertille Tierny, Arthur Charpentier, Francois Hu

Linear models are widely used in high-stakes decision-making due to their interpretability, but fairness constraints like Demographic Parity (DP) create opaque effects on model coefficients and predictive bias distribution. We propose a post-processing framework that can be applied on top of any linear model to decompose bias into direct (sensitive-attribute) and indirect (correlated-features) components. Our method analytically characterizes how DP reshapes each coefficient, enabling transparent feature-level interpretation.

Gokaramaiah Thota, Nagaraju K, Sathya Babu Korra

Deep learning has advanced medical imaging, but limited interpretability hinders clinical adoption. Class activation maps (CAM) provide visual explanations, yet methods such as Score-CAM are computationally expensive, requiring a forward pass for each activation map and limiting real-time applicability despite their high fidelity. To overcome this limitation, LowRank-CAM is proposed, which aggregates activation maps into a global matrix and applies singular value decomposition (SVD) to extract dominant spatial modes. The resulting top-r low-rank attention masks, with r

Shota Takayama, Katsuhide Fujita

Although centralized training with centralized execution (CTCE) excels at multi-agent coordination, its reliance on global information limits its use in the real world. Conversely, the practical decentralized execution (CTDE) paradigm often struggles with complex coordination. This paper bridges this critical gap by introducing the Centralized-to-Decentralized (CtoD) learning concept: a novel framework for transferring the knowledge of a powerful centralized policy into a robust, practical decentralized policy. Our method, CtoD-MAT, realizes this transition through a curriculum that gradually shifts agents from centralized to decentralized control. A key innovation is our dynamic scheduling mechanism, featuring a mediator module, which ensures a robust and effective knowledge transfer. Using challenging SMAC benchmarks, we demonstrate that CtoD-MAT successfully produces competitive decentralized policies, notably solving complex coordination tasks that are difficult for standard CTDE methods.

Hiroki Takabatake, Niken Prasasti Martono, Asaomi Kuwae, Toshihiko Iuchi, Hayato Ohwada

Integrating knowledge from scientific literature is essential in biomedical research. However, the rapid growth of scientific literature makes staying up to date increasingly challenging. Retrieval-Augmented Generation (RAG) offers a promising framework, but its effectiveness in specialized biomedical domains remains unclear. In this work, we propose a two-stage retrieval pipeline for RAG, with a focus on Bordetella pertussis as a case study. Our method first applies hard filtering with synonym expansion to eliminate irrelevant passages, and then performs hybrid search, followed by reranking. We evaluate our approach using a dataset of 58 pertussis-related queries with automatic relevance judgments from multiple large language models (LLMs). Experimental results show that our pipeline improves MAP@10 by 13.4-20.4 points compared with existing methods and achieves the highest MRR@10. Furthermore, consistent improvements across different LLMs highlight the effectiveness of our approach.

Gargi Surendra Yeole, Poulomi Bhattacharya, Akshay Agarwal

Government verification systems are increasingly relying on internet-based platforms, where users authenticate their identities by uploading images captured with ordinary mobile devices. However, the rapid advancements in generative algorithms have enabled the creation of highly realistic forged ID cards that can easily bypass such verification pipelines. These forgeries are not restricted to a single modality; they may target facial imagery, textual content, or both, posing significant challenges to existing detection approaches. We present a framework that analyzes visual features for ID forgery detection by integrating feature fusion with attention mechanisms, leveraging both convolutional neural network (CNN) architectures, such as ResNet-50 and EfficientNet, and transformer-based models, including ViT-16 and Swin Transformer. This study emphasises the significance of feature fusion and attention-driven representation learning in developing robust and trustworthy ID forgery detection systems for real-world deployment.

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.

Roman Sultimov, Mikhail Mozikov, Dmitrii Abramov, Mariia Kovalchuk, Maksim Malykh, Aleksandr Volkov, Ilya Makarov, Andrei Osiptsov, Yury Maximov

Climate change is driving more frequent and severe disasters, putting people and infrastructure at risk. Protecting communities requires models that capture both natural disasters dynamics and how people behave under extreme conditions. This demo presents RESPOND, a multi-agent LLM-enhanced platform that jointly simulates natural hazards and human response. RESPOND couples high-fidelity flood AI forecasting an agent-based model of human behavior. LLM modules improve each agent decision-making, enabling context-aware reasoning over alerts, road closures, social signals, and changing water levels. The system simulates evacuation flows, resource seeking, and communication patterns producing actionable outputs for emergency management, urban planning, and policy. In the live demo one can run what-if or predicted scenarios, adjust assumptions, and observe emergent population behavior and risk hot spots in real time. By tightly coupling dynamic hazards with LLM-driven multi-agent behavior, RESPOND moves beyond fragmented tools and offers a practical, integrated platform for disaster preparedness and response.

Pirzada Suhail, Rehna Afroz Shaik, Gouranga Bala, Amit Sethi

Out-of-distribution (OOD) detection and uncertainty estimation (UE) are critical components for building safe machine learning systems. In this work, we propose a novel framework that combines network inversion with classifier training to simultaneously address both OOD detection and uncertainty estimation. We extend a standard n-class classifier by adding an (n+1)-th "garbage" class to capture outliers, initially populated with random Gaussian noise. After each training epoch, we use network inversion to reconstruct inputs for all classes; incoherent reconstructions are assigned to the garbage class for retraining. This iterative cycle of training, inversion, and exclusion continues until inverted samples resemble in-distribution data and uncertainty drops, indicating learned decision boundaries and cleaner class manifolds. At inference, the model detects OOD inputs by classifying them as garbage, with confidence scores estimating uncertainty. Unlike prior methods, this approach requires no external OOD data or post-hoc calibration, providing a simple, unified solution for robust classification, OOD detection, and uncertainty estimation.

Pirzada Suhail, Vrinda Goel, Amit Sethi

Shortcut learning, where machine learning models exploit spurious correlations in data instead of capturing meaningful features, poses a significant challenge to building generalizable models. Vision classifiers based on Convolutional Neural Networks (CNNs), Multi-Layer Perceptrons (MLPs), and Vision Transformers (ViTs) leverage distinct architectural principles to process spatial and structural information, making them differently susceptible to shortcut learning. In this study, we systematically evaluate these architectures by introducing deliberate shortcuts into the dataset that are correlated with class labels both positionally and via intensity, creating a controlled setup to assess whether models rely on these artificial cues or learn actual distinguishing features. We perform both quantitative evaluation by training on the shortcut-modified dataset and testing on two different test sets—one containing the same shortcuts and another without them—to determine the extent of reliance on shortcuts. Additionally, qualitative evaluation is performed using network inversion-based reconstruction techniques to analyze what the models internalize in their weights, aiming to reconstruct the training data as perceived by the classifiers. Further, we evaluate susceptibility to shortcut learning across different learning rates. Our analysis reveals that CNNs at lower learning rates tend to be more reserved against entirely picking up shortcut features, while ViTs, particularly those without positional encodings, almost entirely ignore the distinctive image features in the presence of shortcuts.

Minkyung Song, Soyoung Park, Sungsu Lim

Traditional recommenders often fail to disentangle the motivations behind user choices. To address this, we propose MV-LLMRec, a framework that models interactions through three views: Structural, Intent, and Conformity. MV-LLMRec leverages LLMs to generate rich semantic representations for intent and conformity, which are refined through graph propagation and dynamically fused via an attention mechanism. We evaluate MV-LLMRec on the Amazon-Movie and Amazon-Book datasets and show that it significantly outperforms state-of-the-art baselines, validating our approach.

Ravada Satyadev, Aditya Ganesh Kumar, Avinash Anand, Rajiv Ratn Shah, Zhengkui Wang, Mukesh Prasad

Bias in Large Language Models (LLMs) is increasingly addressed through fairness-oriented techniques. However, in some cases, these approaches may inadvertently remove genuine cultural differences between groups, leading to “over-normalization” or models losing important socio-cultural distinctions. In this work, we introduce OverNormEval, a benchmark designed to detect when an LLM exhibits such over-normalization. We further explore the use of Direct Preference Optimization (DPO) to mitigate over-normalization.

Kaede Saito, Ryota Higa, Hiromu Imura, Masaaki Kondo

The Pickup-and-Delivery Problem with Time Windows (PDPTW) is a time-constrained variant of the vehicle-routing problem (VRP). Complex time constraints make it difficult to solve using existing NCO methods. In this paper, we present the Feasibility-Aware Masked Transformer (FAM-Trans) specialized for PDPTW. FAM-Trans integrates a lightweight side encoder with a context-aware embedding scheme that effectively captures temporal dependencies. A dynamic key-value module continuously updates node embeddings as the route progresses. During inference, a feasibility-guided post-inference filtering strategy suppresses constraint violations without post-hoc repair. Experiments on standard PDPTW benchmarks show that FAM-Trans outperforms NCO baselines by 20~35% in solution quality and constraint satisfaction.

Rohan Saha, Tushar Shinde

Building temperature prediction is crucial for energy optimization and control in smart cities. We present a physics-enhanced XGBoost framework in a multi-stage sequential scaling approach. Starting from single-zone, single-day predictions, we progressively scale to multi-zone, multi-year forecasts using real-world data from Google's Smart Building Simulator. Our method incorporates physics-enhanced features, temporal encodings, and inter-zone interactions, achieving mean absolute errors (MAE) as low as 0.169°F for weekly multi-zone predictions. For longer horizons, we employ ensemble strategies, demonstrating robust performance up to 2.5 years. Compared to baseline models, our framework consistently improves long-term prediction fidelity. This work advances urban AI by enabling accurate long-term building dynamics modeling for downstream control tasks and bridges machine learning with physics-based modeling approaches.

Nilanjana Saha, Animesh Dutta

In social networks, revealing the structure of communities can expose sensitive groups to detection. Traditional approaches, such as DICE, attempt to hide these communities by randomly rewiring links, but this strategy is often inefficient and insecure. We propose an efficient heuristic method called CRIME (Community Rewiring for Influence and Masking Entities) to address this challenge. CRIME removes the most influential internal links, measured by edge-betweenness centrality, and adds external links with the least betweenness centrality. Experiments on real-world networks demonstrate that CRIME hides targeted communities more effectively than DICE, and also achieves faster execution and improves hiding effectiveness by up to 99.8%.

Alexander Sachuk, Vyacheslav Chukanov, Ekaterina Pchitskaya

The management and annotation of complex, multi-modal scientific data remains a major obstacle for AI-driven research due to poor reusability and scalability of current solutions. We propose SciDataMAS, a novel LLM-powered multi-agent system (MAS), which automate scientific data management through a structured data lake with provenance-based organization and an adaptive metadata taxonomy. The system uses specialized workflows for automated dataset creation, data insertion and retrieval. Experiments show the system's proficiency, with modern LLMs like GPT-5 successfully generating rich metadata schemas and filling them with high accuracy. This work provides a foundational step towards fully automated, reusable, and scalable scientific data organization which may lead to generation and accumulation by scientific community well annotated AI-ready datasets.

Jeong Hwan Ryu, Azimjon Akhtamov, Md Azher Uddin, Aziz Nasridinov

Ensuring proper use of personal protective equipment (PPE), especially helmets, is essential for workplace safety. Conventional object detectors often fail to distinguish whether a helmet is worn correctly, and existing approaches relying on single-model pipelines are prone to localization errors and false alarms. Moreover, most prior studies do not guarantee real-time performance. To resolve these challenges, we propose a lightweight multimodal approach that integrates a YOLO11-based object detector with a pose estimation model, achieving higher F1 scores and lower false alarm rates while maintaining real-time performance.

Tate Rowney, Xuning Ying

We identify a jailbreaking vulnerability in multiple open-source LLMs: by augmenting dangerous requests using certain "distractors" to obfuscate their intent, we elicit specific, actionable responses on a wide variety of harmful topics. We find that such an attack noticeably alters the contents of these models' chains of thought, including changed frequencies of seemingly unrelated n-grams and heightened ethical scrutiny about harmful requests even when their response is ultimately jailbroken.

Benjamin Richards, Pushpa Kumar Balan

Deep learning models are emerging as strong alternatives to numerical weather prediction, yet their internal representations remain poorly understood. We analyze the latent space of Microsoft’s Aurora model to test whether its embed- dings align with known physical processes. First, we show that land–sea distinctions are strongly captured, with errors mainly at coastlines. Second, we examine extreme surface temperatures using percentile-based thresholds, finding that embeddings reveal a gradient from moderate to severe events, though recall degrades at the rarest percentiles. These results suggest that Aurora’s encoder encodes physically consistent features but underestimates rare extremes. Our study combines deep learning forecasting, interpretable representation learning, and classical ML probing, illustrating how cross-disciplinary AI methods can yield insight into foundation models

Julia Rezvani, Alina Hyk, Thuyen Pham, Leonardo Marciaga, Chunyang Liao, Raffaele Vardavas, Konstantinos Mitsopoulos

Longitudinal surveys are a crucial component of behavioral research. Such surveys, however, face significant gaps in the data created by item and unit non-responses as well as semantic gaps resulting from questionnaires, assessed trends, and data collection methods evolving over time. Using 15 waves of vaccination surveys as a test-bed, we demonstrate how modern AI techniques can bridge both item and unit gaps, originating from non-response, and semantic gaps, originating from instrument evolution. We address these gaps through a two-component framework. We leverage LLM-generated semantic embeddings of survey questions to encode question meaning, enabling a Deep & Cross Network used for imputation to jointly model responses across item semantics, individual characteristics, and temporal dynamics. This structure directly addresses survey evolution by operating in learned semantic space. To overcome data scarcity, we use cluster-informed synthetic data generation via hierarchical prompting that produces synthetic responses preserving distributional properties and empirical cluster structure. Our approach achieves a strong improvement in semantic gap tasks and 80-90% synthetic data fidelity, providing practical solutions for evolving longitudinal studies.

Abdolazim Rezaei, Mehdi Sookhak

This study introduces PEFT-DML, a parameter-efficient deep metric learning framework for robust multi-modal 3D object detection in autonomous driving. Unlike conventional models that assume fixed sensor availability, PEFT-DML maps diverse modalities (LiDAR, radar, camera, IMU, GNSS) into a shared latent space, enabling reliable detection even under sensor dropout or unseen modality–class combinations. By integrating Low-Rank Adaptation (LoRA) and adapter layers, PEFT-DML achieves significant training efficiency while enhancing robustness to fast motion, weather variability, and domain shifts. Experiments on benchmarks nuScenes demonstrate superior accuracy.