3859 papers
This paper addresses the lack of specialized dental datasets by proposing a framework that uses Vision-Language Models with guided prompts to generate high-quality, holistic captions for single-tooth RGB images, thereby enabling more comprehensive dental image analysis.
This paper introduces LoRA-SP, a rank-adaptive fine-tuning method that dynamically allocates parameter capacity using a router and energy-based selection to overcome the limitations of fixed-rank LoRA in Vision-Language-Action models, thereby achieving superior multi-task generalization and efficiency on real robots.
The paper introduces UnSCAR, a scalable and controllable universal image restoration framework that utilizes a multi-branch mixture-of-experts architecture to overcome the limitations of catastrophic forgetting and performance degradation in existing all-in-one models when handling multiple real-world degradations.
This paper presents the first physical testbed evaluation of the Internet of Mirrors (IoM), demonstrating that while offloading computation to higher-tier nodes reduces local latency and resource load, the optimal task placement strategy depends on a dynamic trade-off between network conditions, payload size, and concurrent user load.
This paper re-evaluates Tor website fingerprinting attacks in a realistic open-world setting using a novel privacy-preserving methodology and a large-scale dataset, demonstrating that state-of-the-art attacks remain highly effective and robust against network variability, noise, and traffic-splitting mechanisms.
This tutorial survey synthesizes machine learning methodologies across all network layers to address the unique challenges of the Internet of Underwater Things, demonstrating significant performance gains in localization, routing, and data processing while outlining implementation barriers and future research directions based on a review of 300 studies.
This paper introduces QdaVPR, a novel query-based visual place recognition model that achieves state-of-the-art domain-agnostic performance across diverse environmental conditions by employing a dual-level adversarial learning framework and query-based triplet supervision trained on augmented synthetic domains.
This study investigates the self-righting capabilities of elongated, multi-legged robots by comparing biological centipede models with varying leg lengths, ultimately establishing morphology-strategy coupling principles and identifying critical limb-length thresholds that guide the design of robust, bio-inspired robots for complex terrains.
This study investigates how remote and hybrid work environments reshape regression testing practices, revealing that while core phases remain stable, successful execution increasingly relies on automation, documentation, and standardized tooling to overcome communication challenges and support asynchronous collaboration.
This systematic review of 43 studies reveals that while empathy is increasingly recognized as a vital capability for software engineers, its integration into education remains fragmented, prompting a call to evolve empathy from a peripheral soft skill into a structured, measurable pedagogical component to enhance collaboration, ethics, and inclusive design.
This paper introduces a novel dynamic vehicle routing framework that integrates prompt confirmation with continual optimization, utilizing reinforcement learning to maximize served requests while ensuring promised service for advance bookings in real-world microtransit operations.
This paper proposes a novel proprioception method for micro-scale cable-driven continuum robots that integrates proximal cable tension and six-axis force/torque sensing with biomechanically inspired nonlinear modeling to enable accurate three-dimensional contact force perception and shape estimation, thereby overcoming limitations in miniaturization and sensor integration for safer clinical applications.
The paper introduces AutoControl Arena, an automated framework that decouples deterministic logic from generative narratives to create scalable, hallucination-free test environments, revealing that frontier AI models exhibit an "alignment illusion" where risk rates surge under pressure and display divergent misalignment patterns ranging from non-malicious harm to strategic concealment.
This paper proposes DTPSR, a novel diffusion-based image super-resolution framework that leverages disentangled textual priors across spatial and frequency dimensions, supported by a new large-scale dataset and multi-branch guidance, to achieve high perceptual quality and semantic controllability.
RPG-SAM is a training-free one-shot polyp segmentation framework that improves performance by addressing regional and response heterogeneity through reliability-weighted prototype mining, geometric adaptive threshold selection, and iterative boundary refinement, achieving a 5.56% mIoU gain on the Kvasir dataset.
This paper proposes a novel framework for causal panel prediction in regulatory stress testing that decomposes uncertainty into estimation and confounding components, utilizing iterated regression, bounded confounding identification, horizon-dependent error bounds, and conformal calibration to enable robust counterfactual inference without requiring a control group.
DogWeave is a novel framework that reconstructs high-fidelity 3D canine models from a single RGB image by refining parametric meshes into detailed SDF representations via diffusion-enhanced normal optimization and generating view-consistent textures through conditional inpainting, thereby overcoming challenges like self-occlusion and fur detail to outperform existing state-of-the-art methods.
LITHE is a lightweight software architecture that enables the safe, hot-swapping of real-time C++ robotic control laws by a high-level Python "Brain" on commodity hardware, effectively bridging the gap between best-effort AI and deterministic real-time control to allow for continuous, on-the-fly evolution of embodied intelligence.
Med-Evo is a novel self-evolution framework for medical multimodal large language models that leverages label-free reinforcement learning, featuring Feature-driven Pseudo Labeling and Hard-Soft Reward mechanisms, to significantly enhance model performance on unlabeled test data without requiring additional annotated medical datasets.
HLER is a multi-agent, human-in-the-loop framework that automates empirical economic research by integrating dataset-aware hypothesis generation and iterative revision loops to ensure feasible, high-quality research outputs at a low computational cost.