8464 papers
PhaForce is a phase-scheduled visuomotor policy that enhances contact-rich manipulation by coordinating a slow, vision-dominant diffusion planner with a fast, force-driven corrector to enable high-frequency, phase-aware residual corrections, achieving an 86% success rate and superior adaptability compared to existing baselines.
The paper proposes SOT-GLP, a novel few-shot adaptation method for vision-language models that employs shared sparse optimal transport to partition visual regions among class-specific local prompts while maintaining global alignment, thereby achieving state-of-the-art performance in both classification accuracy and out-of-distribution detection by preserving the native feature geometry.
This paper addresses the scalability challenges of state-space analysis in large-scale renewable power systems by leveraging system symmetry to define distinct inner-group and group-grid eigenvalue patterns and introducing a novel group participation factor for stability analysis and targeted optimization.
This paper introduces VLA, a prior-guided framework that enhances robotic manipulation by modeling discrete world-knowledge variations relative to an explicit current state prior, rather than predicting absolute future states, thereby achieving state-of-the-art performance and efficiency through its novel components: the Prior-Guided World Knowledge Extractor, Latent World Variation Quantization, and Conditional Variation Attention.
This paper introduces UniDiffDA, a unified analytical framework that decomposes diffusion-based data augmentation into three core components to enable a systematic, fair benchmarking of diverse methods across low-data classification tasks, ultimately offering practical design insights and reproducible code.
The paper proposes M3-ACE, a multi-agentic context engineering framework that rectifies inaccurate visual perception in multimodal math reasoning by decoupling perception from reasoning and employing collaborative agents with specialized tools to dynamically refine visual evidence, thereby achieving state-of-the-art performance on benchmarks like MathVision.
This paper analyzes the technical implications of the Digital Markets Act (DMA) through qualitative methods to propose eight high-level design strategies and 15 specific tactics for building value-based platform architectures that ensure fairness, contestability, and user choice.
This paper introduces Adaptive Manifold Prototypes (AMP), a framework that leverages Stiefel manifold optimization to represent class prototypes as orthonormal bases, thereby preventing prototype collapse caused by Neural Collapse while achieving state-of-the-art accuracy and improved causal faithfulness in fine-grained recognition.
This paper presents the biased interaction game as a versatile modeling tool for social systems, demonstrating how boundedly rational interactions under scarcity and bias naturally generate emergent hierarchies, inequality, and non-linear stability patterns while offering a framework to evaluate competing wealth redistribution philosophies like social welfare and universal basic income.
This paper presents a communication-free multi-UAV coordination framework that leverages onboard anisotropic 3D LiDAR for simultaneous SLAM, obstacle detection, and neighbor tracking, enabling safe and scalable navigation in complex, GNSS-denied environments like dense forests.
This paper proposes a rank-order based neural network inspired by the STG-LIFG-PMC pathway that demonstrates how rank-order coding effectively bridges acoustic input to abstract structure, enabling robust sequence reconstruction, global novelty detection, and proto-syntactic generalization through context-sensitive sensorimotor representations.
MoMaStage is a structured vision-language framework that enables robust long-horizon indoor mobile manipulation by guiding task planning through a topology-aware Skill-State Graph and ensuring execution reliability via a closed-loop mechanism that triggers semantic replanning upon detecting physical deviations, all without requiring explicit scene mapping.
This study presents a rectified flow-based AI model that generates realistic post-treatment brain MRIs from pre-radiotherapy priors and dose maps for glioma patients, achieving high structural fidelity and significantly faster inference than diffusion models to support adaptive treatment planning.
This paper proposes DDHF, a novel real-time drone detection framework for event cameras that utilizes Non-uniform Discrete Fourier Transform (NDFT) to analyze per-pixel temporal frequency signatures, achieving superior accuracy and significantly lower latency compared to traditional deep learning methods like YOLO.
AULLM++ is a structural reasoning framework that leverages Large Language Models to enhance micro-expression Action Unit detection by fusing multi-granularity visual features with learned AU correlations through a three-stage evidence construction, structure modeling, and deduction-based prediction process, achieving state-of-the-art performance and superior cross-domain generalization.
This paper proposes the Hierarchical Error-Corrective Graph Framework (HECG) for autonomous agents, which integrates Multi-Dimensional Transferable Strategy (MDTS) for precise candidate selection, Error Matrix Classification (EMC) for structured failure attribution, and Causal-Context Graph Retrieval (CCGR) for enhanced contextual reasoning to improve execution reliability in complex, multi-step tasks.
The paper proposes StructBiHOI, a hierarchical framework that combines a jointVAE for long-term planning, a maniVAE for frame-level refinement, and a Mamba-based diffusion denoiser to achieve stable, physically plausible, and semantically aligned long-horizon bimanual hand-object interaction generation.
This paper presents a novel capability architecture and a corresponding Zephyr-based real-time operating system that achieves comprehensive security for embedded devices by fully disaggregating and isolating all software subsystems and peripherals, thereby eliminating the need for a run-time software Trusted Computing Base (TCB) without requiring hardware modifications.
SPIRAL is a closed-loop framework that enhances controllable long-horizon video generation by integrating a reflective planning process with iterative action world modeling, enabling self-improvement through explicit planning, object-centric decomposition, and feedback-driven refinement.
This paper presents and evaluates a scalable dynamic point cloud streaming system that leverages on-the-fly transcoding, demonstrating how caching and speculative transcoding significantly reduce server loads and improve user Quality of Experience to support a higher number of simultaneous clients.