3462 papers
This paper employs an equilibrium model to demonstrate that while news feed algorithms prioritizing viral stories can enhance information aggregation, they also risk creating self-perpetuating steady states where rational users collectively share and reinforce incorrect information, highlighting critical implications for platform design.
This paper proposes a novel statistical learning framework for multi-item auctions that utilizes nonparametric density estimation and credible intervals to implement two cost-reducing strategies, which maintain key economic properties like incentive compatibility and fairness while outperforming alternative methods in both revenue maximization and implementation efficiency.
This paper proposes a mutual conditional blended-target domain adaptation framework that aligns categorical distributions and rectifies classifier bias through uncertainty-guided discrimination and low-level feature augmentation, achieving state-of-the-art performance even without explicit domain labels and under label distribution shifts.
This paper examines how various methodological decisions and configuration parameters in YouTube audits significantly impact the accuracy of inferred algorithmic biases, ultimately offering strategies to optimize audit overhead without compromising scientific validity.
This paper investigates the many-to-many bipartite matching problem with ties and lower quotas, proving that while a maximum-size critical relaxed-stable matching is NP-hard to compute, a -approximation can be achieved in polynomial time.
The paper introduces altiro3D, a free library that synthesizes realistic 3D experiences and novel views from a single RGB image or video by combining monocular depth estimation, inpainting, and optimized projection algorithms to generate multi-viewpoint light fields for free-view displays.
This survey reviews the application of utility theory to cognitive modeling in robotics, tracing its evolution from behavior-based approaches to value systems that guide decision-making, learning, and cooperation in single and multi-agent environments, while identifying current limitations and proposing future research directions.
This paper presents an analytical MAC-layer model for 5G NR Sidelink Mode 2 that explicitly incorporates standardized Semi-Persistent Scheduling features to derive closed-form expressions for packet reception ratio, which are validated against ns-3 simulations to provide design insights for enhancing 6G sidelink reliability.
This paper investigates the complexity of the Distance- Dominating Set Reconfiguration problem for under Token Jumping and Token Sliding rules, establishing a PSPACE-complete to P complexity dichotomy on split graphs, providing a linear-time algorithm for trees, and extending hardness results to planar graphs with maximum degree three and various other graph classes.
This paper proposes and validates a loop-based algorithm for the online, conflict-free scheduling and routing of automated guided vehicles in pickup and delivery systems, demonstrating its superior or comparable performance to exact, greedy, and metaheuristic methods in terms of solution quality and computational efficiency.
This paper introduces PD-REAL, a novel large-scale RGB-D dataset for unsupervised anomaly detection based on Play-Doh models, and proposes a multi-scale teacher-student framework with hierarchical distillation that leverages 3D information to achieve superior detection accuracy compared to existing methods.
This paper proposes CA-Jaccard, a novel camera-aware Jaccard distance metric that enhances person re-identification reliability by introducing camera-aware k-reciprocal nearest neighbors and camera-aware local query expansion to mitigate the negative impact of camera variations on neighbor selection.
This paper proposes a joint user association and resource allocation framework for Adaptive Semantic Communication in 5G and beyond networks, which dynamically adjusts DNN-based transceivers to address user heterogeneity and maximizes system utility under energy and latency constraints through a decomposed, polynomial-time algorithm.
Through an analysis of Wikipedia's Flagged Revisions initiative, this paper identifies how restructuring community-based moderation is hindered by conflicts between new systems and existing social norms, as well as the complex costs and assessment difficulties arising from the intricate relationship between platforms and self-governed communities.
DivCon introduces a divide-and-conquer framework that decouples text-to-image generation into simplified numerical/spatial reasoning and progressive object synthesis steps, enabling lightweight models to achieve superior layout accuracy and perceptual quality for complex multi-object prompts without relying on closed-source large language models.
This paper presents a comprehensive survey and benchmark of deepfake generation and detection, unifying task definitions, reviewing state-of-the-art methods across four key generation fields and forgery detection, and analyzing current challenges and future research directions.
This paper introduces a new one-pass algorithm for weighted reservoir sampling with replacement from data streams of unknown size, which provides a representative sample at any time without post-processing and is proven to be both correct and efficient compared to state-of-the-art methods.
This paper proposes three high-quality, controlled test sets (Hadrian, Eclipse, and ND-Twins) designed to challenge face verification models on natural variations in facial attributes and similar-looking identities, while introducing "Goldilocks" rules to ensure balanced difficulty and demographic fairness without artificially degrading image quality.
This paper proposes RDM, a recurrent diffusion model that leverages Normalizing Flows to condition generation on preceding noisy frames, enabling efficient, long-duration human motion synthesis with reduced computational costs while maintaining high alignment with text prompts.
This paper proposes a method to foster implicit communication in human-robot interaction by modulating inter-agent influence through Transfer Entropy within a reward framework, demonstrating that enhancing influence improves collaboration while resisting it promotes independence, as validated through simulations and real-world experiments.