3984 papers
This paper proposes VRec, a novel "reason-verify-recommend" paradigm that interleaves reasoning with multi-dimensional verification to mitigate reasoning degradation and enhance the effectiveness and scalability of LLM-based generative recommendation.
This paper proposes and validates a post-quantum secure federated learning framework that integrates NIST-standardized CRYSTALS-Kyber and CRYSTALS-Dilithium algorithms to protect collaborative threat intelligence from quantum attacks, achieving high detection accuracy with minimal latency while ensuring privacy compliance.
This paper introduces the Three Praxes Framework, derived from a grounded theory analysis of 90 social accessibility studies (2011–2025), to map the field's fragmented practices across Artifact, Ecosystem, and Epistemology sites and advocate for an integrated cycle where lived experiences, material realities, and theoretical knowledge collectively transform access ecosystems.
This paper proposes a novel multi-agent architecture that automates structural modeling and analysis using OpenSeesPy by decomposing complex tasks into specialized agents to effectively reduce hallucinations and error accumulation, achieving high accuracy and scalability across benchmark frame problems.
This paper proposes a framework for synthesizing tunable input-to-state safety (TISSf) controllers that explicitly incorporate general compact input constraints by deriving verifiable certificates and design conditions to guarantee input compatibility and recursive feasibility, as demonstrated in a connected cruise control application.
This paper argues that socially assistive technology should shift its goal from fostering independence to achieving "relational sovereignty," a framework that empowers disabled individuals to choose between independence and interdependence by integrating self-determination theory, symbolic interactionism, and crip technoscience into a new design matrix and set of interventions.
This paper introduces AeroPlace-Flow, a training-free framework that enables aerial manipulators to perform precise, language-grounded object placement by synthesizing goal images, grounding them into 3D space, and generating collision-aware object flows without requiring predefined poses or task-specific training.
This paper proposes reframing human-AI-robot interaction as "scaffolding" rather than autonomy, positioning humans as creative directors who define intent and steer revisions while AI mediates robotic execution to support sustained human agency and creativity in open-ended environments.
Through a Grounded Theory analysis of 25 interviews with professionals in four AI-focused teams, this study demonstrates that team diversity significantly enhances AI system development by diversifying perspectives for bias identification, fostering empathy, addressing systemic discrimination, and promoting inclusive decision-making.
This paper introduces Structured Gossip DNS, a partition-resilient name resolution system for large-scale dynamic networks that leverages DHT finger tables and passive stabilization to achieve eventual consistency with reduced message complexity and without requiring global coordination.
The paper proposes AR2-4FV, a novel framework for long-term language-guided referring in fixed-view videos that leverages a static background-derived Anchor Bank and a ReID-Gating mechanism to maintain identity continuity and accelerate re-capture during occlusions or scene exits, significantly outperforming existing baselines in re-capture rate and latency.
The paper proposes DECADE, an unsupervised diffusion model that achieves temporally consistent denoising of Rb-82 dynamic cardiac PET images without paired training data, effectively reducing noise while preserving quantitative accuracy for myocardial blood flow and flow reserve metrics.
This paper introduces MedQ-Deg, a comprehensive benchmark featuring 24,894 expert-calibrated question-answer pairs across 18 degradation types and 7 imaging modalities, which reveals that mainstream medical multimodal large language models suffer systematic performance drops and exhibit the "AI Dunning-Kruger Effect" of overconfidence under image quality degradations.
The paper introduces Apply2Isar, a tool that automatically converts procedural apply-style proofs in Isabelle/HOL into readable and robust declarative Isar proofs, demonstrating its effectiveness through evaluation on a large benchmark set from the Isabelle Archive of Formal Proofs.
This paper proposes the Geometric Knowledge-Guided Federated Dual Knowledge Distillation (GK-FedDKD) framework to address data heterogeneity in remote sensing satellite imagery by leveraging aggregated geometric knowledge from local covariance matrices and a dual distillation process to significantly outperform state-of-the-art methods.
This paper proposes a stability-aligned residual control architecture that enables robotic systems to rapidly recover from mid-episode dynamics shifts by keeping the nominal policy frozen while using a bounded, gated additive residual channel to adaptively compensate for unobserved disturbances, achieving up to an 87% reduction in recovery time across various robotic platforms.
This paper proposes a novel style transfer method that represents images in the brushstroke domain rather than the traditional pixel domain, offering a more natural and visually superior approach to mimicking artistic styles.
The paper introduces OrdinalBench, a comprehensive benchmark dataset and evaluation framework designed to diagnose and expose the significant generalization limitations of Vision-Language Models in understanding ordinal numbers and performing sequential reasoning tasks involving large indices and complex paths.
The paper proposes Structured Gaussian Image (SGI), a framework that represents high-resolution images using multi-scale, seed-based structured 2D Gaussians generated by lightweight MLPs, achieving significant compression and faster convergence compared to existing unstructured 2D Gaussian methods while maintaining high image fidelity.
This paper introduces 4DRC-OCC, the first framework to fuse 4D radar and camera data for robust 3D semantic occupancy prediction, leveraging their complementary strengths to overcome adverse weather and lighting challenges while utilizing a newly created automatically labeled dataset to reduce annotation costs.