5705 papers
This paper introduces PVBench, a benchmark demonstrating that over 40% of patches generated by automated vulnerability repair systems are falsely validated as correct because they fail to pass critical "PoC+" tests that encode developer intentions, root cause locations, and specific coding conventions.
This paper introduces ColonSplat, a dynamic Gaussian Splatting framework that achieves superior 3D reconstruction of peristaltic colon motion by preserving global geometric consistency, supported by a new synthetic benchmark dataset called DynamicColon and a critical analysis of existing methods' limitations.
This paper proposes a hardware-efficient trajectory prediction framework that integrates environmental priors with a Dual-Transformer-Cascaded (DTC) architecture to accurately predict the landing points of flying objects, such as tennis balls, by outperforming existing methods in complex real-world scenarios.
The paper introduces Robodimm, a physics-grounded software framework that automates actuator sizing for scalable modular robots by leveraging Pinocchio and Pink to solve constrained inverse dynamics via a Karush-Kuhn-Tucker formulation, thereby addressing the complexities of coupled joint torques and self-weight effects in closed kinematic chains.
The paper proposes CAR, a novel framework that leverages a Transformer encoder with Adaptive Layer Normalization to map diverse vehicle configurations into a shared latent space, enabling rapid and data-efficient kinodynamic adaptation for new autonomous off-road platforms with minimal training data.
The paper introduces Lookahead-Enhanced Atomic Decomposition (LEAD), a method that mitigates the "no-recovery bottleneck" caused by extreme decomposition in long-horizon reasoning by integrating short-horizon future validation and overlapping rollouts, thereby enabling models like o4-mini to solve complex algorithmic puzzles beyond the limits of previous approaches.
The paper introduces PICS, a self-supervised framework that improves pairwise image compositing by employing an Interaction Transformer with mask-guided Mixture-of-Experts and adaptive blending to explicitly model spatial interactions and preserve physical consistency between objects and backgrounds.
This study reveals that while the correctness of LLM-generated reasoning is the primary driver of user accuracy in critical thinking tasks, medium-length explanations uniquely enhance users' ability to detect errors when the AI's reasoning is incorrect, suggesting that response length plays a nuanced role in shaping human critical evaluation.
This paper proposes a framework for Material Driven HRI Design that leverages color, texture, and material choices as interaction signals to enhance robot explainability, clarify roles, and align user expectations with actual capabilities.
This paper introduces "notational animating," an interactive animation authoring paradigm that enables users to sketch high-level notations over static drawings, which are then interpreted by AI into formalized animation keyframes through a structured representation and a closed feedback loop for resolving ambiguity.
This paper proposes a Distributed Legal Infrastructure (DLI) framework comprising five interlocking layers—ranging from soulbound agent identities to decentralized adjudication—to establish interoperable protocols that ensure accountability, contestability, and rule-of-law principles within the emerging autonomous agentic web.
This paper introduces OPTED, an open-source preprocessed trachoma eye dataset derived from 2,832 images using a zero-shot SAM 3 pipeline to automatically extract and standardize regions of interest, thereby addressing the scarcity of high-quality data for automated trachoma classification in Sub-Saharan Africa.
The paper introduces VertiAdaptor, an online adaptation framework that integrates elevation and semantic data to enable rapid, accurate kinodynamic modeling and planning for autonomous vehicles navigating complex off-road terrains, demonstrating significant improvements in prediction accuracy and adaptation speed in both simulation and real-world tests.
This study demonstrates that a hybrid machine learning model combining Bi-LSTM and GRU algorithms, trained on diverse patient data, achieves a 97.07% accuracy in detecting Coronary Artery Disease, significantly outperforming traditional diagnostic methods.
This paper presents a comprehensive systematization of knowledge on Self-Sovereign Digital Identities (SSDI) by analyzing 80 sources to identify six major adoption challenges, evaluating 47 academic publications and 12 real-world applications to reveal that self-sovereignty is a spectrum, and outlining future research directions to accelerate the shift from centralized to self-sovereign identity systems.
This paper introduces CoPCS, a learning-based framework that utilizes a heterogeneous graph transformer and a synchronized transformer decoder to enable energy- and terrain-constrained UAV-UGV teams to perform coordinated, concurrent task planning and in-mission recharging, significantly improving overall team performance in complex real-world scenarios.
This paper introduces SELSM, a training-free framework that enhances locally deployable medical agents by distilling simulated clinical trajectories into entity-agnostic logical rules, thereby significantly improving zero-shot FHIR-based task performance and achieving a 100% completion rate on the MedAgentBench without compromising data privacy.
SysNav is a novel three-level system that integrates Vision-Language Models with hierarchical planning and embodiment-specific control to achieve robust, efficient, and state-of-the-art real-world object navigation across diverse robot platforms.
PaQ-DETR is a unified object detection framework that addresses query utilization imbalance by dynamically generating image-specific queries from shared latent patterns and employing a quality-aware one-to-many assignment strategy, resulting in consistent mAP improvements across various DETR backbones.
T2Nav is a zero-shot visual navigation system that leverages algebraic topology-aware temporal graph memory and loop detection to integrate heterogeneous data for robust obstacle avoidance, efficient path planning, and reliable navigation to visually similar yet spatially distinct targets in unknown environments.