3818 papers
The paper proposes DeAR, a fine-grained adaptation framework for Vision-Language Models that decomposes attention heads into functional roles (Attribute, Generalization, and Mixed) using a Concept Entropy metric to selectively isolate task-specific learning from generalization capabilities, thereby achieving superior performance across diverse tasks while preserving zero-shot robustness.
This paper presents a validated digital twin of the Frontier supercomputer's liquid cooling system to demonstrate that a ramp-constrained, joint optimization of flow rate and supply temperature can achieve 27.8% energy savings, significantly outperforming flow-only strategies by addressing the gap between theoretical optima and operational deployability.
This technical report extends the empirical validation of the Explainability Solution Space (ESS) framework by demonstrating its domain-independent applicability and systematic adaptability to diverse governance roles and stakeholder configurations through a cross-domain evaluation involving both employee attrition and urban resource allocation systems.
This paper proposes and evaluates static and adaptive traffic scheduling schemes—including threshold, heuristic, and reinforcement learning-based approaches—to optimize energy efficiency and delivery ratios for energy-constrained optical LEO satellite downlinks facing weather-related disruptions.
HarmonyCell is an end-to-end agent framework that automates single-cell perturbation modeling by combining an LLM-driven semantic unifier to resolve metadata incompatibilities and an adaptive Monte Carlo Tree Search engine to synthesize architectures that handle distribution shifts, thereby achieving high execution success and outperforming expert baselines without manual engineering.
This paper proposes a novel LLM-driven closed-loop framework that maps natural language instructions to executable rules and semantically annotates options to enhance the data efficiency, interpretability, and cross-environment transferability of Deep Reinforcement Learning, with experimental validation showing superior performance in constraint compliance and skill reuse.
The paper proposes the MSP framework, which mitigates hairstyle distraction and preserves structural information through Hairstyle-Oriented Augmentation, Cloth-Preserved Random Erasing, and Region-based Parsing Attention to achieve state-of-the-art performance in cloth-changing person re-identification.
This paper evaluates DINOv3 as a frozen backbone for blueberry robotic harvesting tasks, finding that while it excels in segmentation through stable patch-level representations, its detection performance is limited by scale variation and spatial aggregation challenges, suggesting it functions best as a semantic backbone requiring downstream spatial modeling tailored to fruit structures.
This paper proposes an event-driven safe and resilient control framework that integrates adaptive attack-resilient strategies with data-driven human driver estimation to ensure collision-free and stable lane-changing maneuvers for automated vehicles in mixed traffic under exponentially unbounded false data injection attacks.
This paper proposes Generalized Per-Agent Advantage Estimation (GPAE), a novel multi-agent reinforcement learning framework that enhances sample efficiency and coordination by utilizing a per-agent value iteration operator and a double-truncated importance sampling scheme to enable stable off-policy learning without direct Q-function estimation.
This paper introduces an agentified assessment framework that utilizes an assessor agent to ensure reproducible and robust evaluation of logical reasoning systems, demonstrating its effectiveness by benchmarking an auto-formalization agent that achieves 86.70% accuracy on a solver-verified FOLIO dataset, significantly outperforming a chain-of-thought baseline.
This paper introduces the Required-edge Cycle Cover Problem (RCCP) and a corresponding flow model to establish an ASP-completeness framework that resolves open complexity questions for Constraint Graph Satisfiability and Kakuro while proving the ASP-completeness of several other pencil-and-paper puzzles.
This paper presents Mica, a confidential computing architecture built on Arm CCA that decouples confidentiality from trust by enabling tenants to explicitly define, restrict, and attest communication paths between distrustful TEE components, thereby preventing sensitive data leakage without significantly expanding the trusted computing base.
This paper introduces LDP-Slicing, a lightweight, training-free framework that overcomes the utility limitations of applying Local Differential Privacy to high-dimensional images by decomposing pixel values into binary bit-planes and integrating perceptual obfuscation and optimized budget allocation to achieve rigorous privacy with high downstream task performance.
This paper introduces RISCBench, a benchmark suite and methodology that quantifies orchestration efficiency in heterogeneous RISC-V systems using a new Sustained Instantaneous Throughput (SIT) metric to address the limitations of conventional performance indicators in FPGA and accelerator-class platforms.
This paper presents an empirical review comparing binary floating-point to decimal string conversion algorithms, highlighting that modern techniques like Schubfach and Dragonbox offer significant speedups over legacy methods like Dragon4, though many implementations still fail to consistently generate the shortest possible decimal strings.
This design-science study introduces and validates the GSI D-Hub, an AI-powered platform that leverages explainable algorithms and synthetic data to enhance transparency, trust, and decision-making within multi-stakeholder global development ecosystems.
This study evaluates the vulnerability of Sub-Saharan African migrants to AI-enabled deception, finding that prior exposure to targeting is the strongest predictor of risk, while confidence in identifying AI content and high verification effort serve as significant protective factors.
This paper proposes an ethics-by-design control architecture that operationalizes AI governance across the entire lifecycle by embedding philosophical reasoning into a triple-gate enforcement structure (Metric, Governance, and Eco) with measurable triggers and audit trails, thereby translating normative commitments into testable controls compatible with existing MLOps pipelines and major regulatory frameworks like the EU AI Act and NIST RMF.
Using causal inference on a dataset of 530 papers, this study quantifies statistically significant disadvantages in academic peer review rankings for authors from minority racial groups, female authors, and those affiliated with institutions in the Global South, highlighting the urgent need for fairness interventions in both traditional and AI-driven assessment systems.