3447 papers
This paper proposes a high-slip-ratio control framework for automated vehicles that actively excites peak tire-road friction during empty-haul operations to enable accurate, safe, and scalable estimation of the tire-road friction coefficient through constrained optimal control and robust statistical projection.
This paper presents a provably safe motion planning framework for robot manipulators in uncertain, non-convex environments by integrating a deep stochastic Koopman operator for state prediction with a hierarchical sum-of-squares verification filter within a Model Predictive Path Integral controller to generate certified, collision-free trajectories.
OmniEdit is a novel, training-free framework that achieves robust lip synchronization and audio-visual editing by reformulating the editing paradigm to replace the edit sequence with a target sequence, thereby eliminating the need for supervised fine-tuning and ensuring a smooth, stable generation process.
This paper proposes a framework for physically plausible video generation that models phenomena as causally connected event sequences by integrating physics-driven chain-of-thought reasoning with transition-aware cross-modal prompting to ensure dynamic continuity and physical consistency.
This paper evaluates the capability of state-of-the-art Large Language Models to automatically generate UML class diagrams from natural language requirements, demonstrating their effectiveness and reliability through a comprehensive dual-validation framework that combines LLM-as-a-Judge assessments with human expert evaluations.
MedKCO is a medical vision-language pretraining framework that overcomes the limitations of simultaneous concept learning by employing a two-level curriculum for data ordering and a self-paced asymmetric contrastive loss to dynamically adjust the learning objective, thereby significantly improving feature representations and downstream task performance.
This paper proposes a training-free, model-agnostic motion factorization framework that decomposes complex video generation into motionlessness, rigid, and non-rigid categories through a "planning before generation" paradigm to synthesize diverse instances with controlled appearance and motion.
This paper proposes PRLF, a Progressive Representation Learning Framework that addresses missing modalities in Multimodal Sentiment Analysis by dynamically estimating modality reliability and iteratively aligning incomplete features with a dominant modality to enhance robustness and performance.
Nezha is a distributed key-value store that resolves the I/O overhead caused by overlapping persistence operations in Raft-based systems by integrating key-value separation with an optimized persistence strategy and leveled garbage collection, thereby achieving significant throughput improvements while maintaining strong consistency.
This study audits Google's reverse image search and finds that it functions as an ineffective gatekeeper against visual misinformation, often prioritizing irrelevant content and repeated falsehoods over debunking information, particularly during the initial emergence of visual falsehoods.
This paper introduces AgenticCyOps, a security framework for enterprise multi-agent AI systems that mitigates emerging attack surfaces by formalizing tool orchestration and memory management as primary trust boundaries and applying five defensive principles aligned with global compliance standards to significantly reduce exploitable vulnerabilities in SOC workflows.
This paper introduces a novel, fully automated framework that utilizes a SegFormer transformer to segment multiple anatomical regions in HR-pQCT images and extract radiomic features, demonstrating that soft tissue analysis outperforms traditional bone-based metrics in detecting osteoporosis.
This paper introduces EQ-VMamba, the first rotation-equivariant visual Mamba architecture that incorporates a specialized cross-scan strategy and group Mamba blocks to achieve superior performance and robustness across various vision tasks while reducing parameter counts by approximately 50% compared to non-equivariant baselines.
This paper proposes an Agentic AI framework that serves as a control-plane intelligence layer for 6G networks, utilizing specialized agents to dynamically manage federated learning tasks by integrating network conditions with learning objectives to optimize client selection, resource allocation, and scheduling.
This paper presents a polynomial-time approximation scheme (PTAS) for the Weighted Triangle-Free 2-Matching problem, utilizing a local-search algorithm to achieve a -approximation ratio for any constant , thereby significantly improving upon the previous best-known $2/3$-approximation.
This paper presents a computationally lightweight, segment-based control architecture for multi-legged robots with six or more legs that effectively navigates rough terrain by bridging the gap between event-driven and CPG-based controllers through tightly coupled ground contact and fictive locomotion.
The paper proposes VNOIP, a novel method leveraging variational neural Ordinary Differential Equations with bidirectional jump ODEs and attention mechanisms to explicitly model continuous-time popularity trend dynamics, thereby significantly improving the accuracy and efficiency of information popularity prediction in online social networks compared to existing state-of-the-art approaches.
RTFDNet is a three-branch encoder-decoder network that unifies synergistic feature fusion with cross-modal and region decoupling regularization to achieve robust RGB-T semantic segmentation, enabling strong performance even when sensor signals are partially missing without requiring multi-stage training.
SPAN-Nav is an end-to-end foundation model that achieves state-of-the-art, robust generalization in versatile vision-language navigation by leveraging a massive 4.2-million-annotation dataset to learn universal 3D spatial priors, which are efficiently encoded into a single token to guide action reasoning across diverse indoor and outdoor environments.
This paper presents a new -differentially private algorithm for frequent substring mining that achieves near-optimal error guarantees while drastically reducing space and time complexity from to near-linear bounds through refined candidate generation and search space pruning.