4491 papers
This paper proposes a modular, cortically inspired architecture for perceptual AI that leverages neuroscientific principles like predictive processing and specialized modules to overcome the interpretability and generalization limitations of current monolithic models, thereby enabling more transparent and human-aligned reasoning.
This paper proposes a training-centered approach that combines adversarial training with a lightweight feature-map smoothing block to generate saliency maps that are simultaneously sparse, input-stable, and output-stable, thereby enhancing their perceived trustworthiness and sufficiency.
This paper introduces Tursio, a secure, on-premises platform that empowers credit unions to query complex structured databases using natural language by leveraging Large Language Models to automatically generate semantic knowledge graphs and compliant query plans.
This study reveals that in factual verification tasks, users' trust and decision-making are primarily driven by the correctness and certainty framing of LLM rationales rather than their presentation format, highlighting the dual potential of well-designed rationales to either support decision-making or miscalibrate trust.
This paper presents a soft-rigid hybrid gripper that utilizes inflatable silicone pockets to actively modulate surface friction via internal air pressure, enabling the secure grasping of diverse objects—from heavy and slippery to fragile items—without relying on excessive normal force.
This empirical study demonstrates that maintaining end-to-end determinism in 5G-TSN networks for IIoT applications requires carefully tuning Time-Aware Shaper (TAS) transmission window offsets based on high-order percentile bounds of 5G downlink delay and jitter to prevent excessive latency or scheduling failures.
This chapter reviews the evolution of data-driven hint generation in intelligent tutoring systems, highlighting how historical student data enables the creation of next-step hints, strategic subgoals, and timely interventions, while also exploring future adaptations involving behavioral data and Large Language Models.
Faster-HEAL is a lightweight, privacy-preserving collaborative perception framework that addresses the challenges of heterogeneous autonomous vehicles by using low-rank visual prompt fine-tuning and pyramid fusion to align diverse features into a unified space, achieving superior detection performance with significantly reduced computational overhead compared to state-of-the-art methods.
FinSheet-Bench introduces a synthetic benchmark modeled on real private equity fund structures to evaluate LLMs on financial spreadsheet tasks, revealing that even the best-performing models currently lack the accuracy required for unsupervised professional use, particularly on complex, large-scale documents, and suggesting that reliable extraction will require separating document understanding from deterministic computation.
This paper presents a computational method for automatically generating mathematical proof exercises with comparable complexity levels by utilizing cut-based tableau proofs and a mechanizable rule extraction procedure to control difficulty for undergraduate discrete mathematics education.
Echo is an advanced agent that leverages code graphs, automatic query refinement, and execution feedback to generate single, high-quality issue reproduction test cases, achieving a new state-of-the-art success rate of 66.28% on the SWT-Bench Verified dataset.
This study demonstrates through numerical simulations of a spatial trust game that inter-role rewards do not linearly promote trust, as excessive rewards can trigger non-return strategies that suppress cooperation, while moderately costly rewards are most effective at consolidating trust clusters.
This paper proposes a self-supervised evolutionary learning framework that extracts individualized neurodynamic progressions and identity manifolds from unlabeled EEG data during safety-critical decision-making, enabling robust user authentication, anomaly detection, and improved generalization without relying on external labels or predefined cognitive models.
This paper introduces VisualScratchpad, an interactive inference-time analysis tool that leverages sparse autoencoders and attention mechanisms to visualize and debug vision language models by linking visual concepts to text tokens, thereby revealing previously underexplored failure modes such as limited cross-modal alignment and misleading visual concepts.
This paper proposes a lightweight, digital-twin-based framework for edge-assisted vehicle tracking and collision prediction that achieves approximately 88% accuracy by relying on object detection and K-D tree-indexed path maps instead of computationally intensive trajectory prediction models.
The paper introduces Agora, an AI-powered platform that leverages LLMs to simulate diverse human perspectives on policy issues, enabling users to practice consensus-building and demonstrating through a preliminary study that access to authentic voice explanations significantly enhances problem-solving skills and the quality of collective decisions compared to viewing aggregate data alone.
Uber's Failover Architecture (UFA) replaces its costly uniform 2x capacity model with a differentiated, criticality-based approach that opportunistically shares resources and preempts non-critical services during peak failovers, thereby reducing steady-state provisioning from 2x to 1.3x and eliminating over one million CPU cores while maintaining 99.97% availability.
This paper introduces VRxBioRelax, a real-time virtual reality biofeedback system that utilizes sEMG data to drive an immersive relaxation environment, demonstrating through extensive pre-clinical testing that its average end-to-end latency of 25.34 ms significantly meets both VR comfort and clinical benchmarks for effective muscle relaxation training.
This study argues that while federally mandated shared data systems like HMIS facilitate coordination and accountability in U.S. homelessness services, they simultaneously reinforce power asymmetries by shifting resource-constrained providers toward compliance roles and concentrating decision-making authority.
This paper demonstrates that environmental pressure in multi-agent LLM simulations follows a Yerkes-Dodson inverted-U relationship, where medium stress optimizes emergent cooperative trade while extreme pressure causes behavioral collapse, and suggests that calibrating such pressure serves as an effective curriculum design strategy for agent development.