7209 papers
This paper proposes a novel adaptive vision-based control scheme with null-space interaction for redundant robots that ensures stable, safe, and effective human-robot collaboration in unknown environments by decoupling primary task execution from interactive adjustments, as validated through augmented reality experiments and Lyapunov stability analysis.
This paper introduces DSH-Bench, a comprehensive benchmark featuring a hierarchical subject taxonomy, granular difficulty and scenario classification, and a novel Subject Identity Consistency Score (SICS) metric to systematically evaluate and diagnose subject-driven text-to-image generation models.
TrianguLang is a feed-forward, pose-free framework for 3D object localization that leverages Geometry-Aware Semantic Attention to achieve state-of-the-art accuracy and geometric consistency across multiple views without requiring camera calibration or per-scene optimization.
This paper introduces PathBench, a unified benchmark for pathological speech intelligibility assessment that establishes systematic baselines across six public datasets and three evaluation protocols, while proposing the Dual-ASR Articulatory Precision (DArtP) method as a top-performing reference-free approach.
This paper proposes Adaptive MLP Pruning (AMP), a method that utilizes a label-free information entropy criterion for accurate neuron importance evaluation and a binary search algorithm for adaptive pruning, achieving roughly 40% parameter and FLOPs reduction in large vision transformers like CLIP and DINOv2 with near-lossless performance.
This paper investigates how users perceive fragility in Shape-Changing Interfaces (SCIs) through two studies that identify key influencing factors, formalize them into a framework, and demonstrate how manipulating these factors affects user interaction and perceived robustness.
This paper introduces permutation match puzzles on grids, characterizing their solvability via an acyclic constraint graph condition, providing a hook length formula for counting solutions, offering an algorithm for minimal repairs in the basic case, and proving that generalizing the problem to arbitrary permutations renders minimal repair NP-complete.
This paper introduces DeReCo, a novel multi-agent reinforcement learning framework that decouples representation and coordination learning through a three-stage training strategy to overcome bidirectional interference, thereby enabling sample-efficient and robust decentralized cooperative transport across objects with diverse shapes and physical properties.
The paper proposes SAMoE-VLA, a novel Vision-Language-Action framework for autonomous driving that replaces unstable token-level Mixture-of-Experts with a scene-adaptive mechanism driven by bird's-eye-view features and a conditional cross-modal causal attention module, achieving state-of-the-art performance with fewer parameters on both open-loop and closed-loop benchmarks.
This paper identifies the critical limitation of current LLM-based agents in accessing unindexed information, introduces the first dedicated UIS-QA benchmark to quantify this challenge, and proposes UIS-Digger, a multi-agent framework that significantly outperforms state-of-the-art models by effectively combining dual-mode browsing and file parsing to retrieve vital unindexed data.
This paper proposes an integrated framework combining RL-augmented teleoperation via the IMCopilot assistant and a Mixture-of-Dexterous-Experts VLA (MoDE-VLA) architecture to overcome data and learning bottlenecks, enabling robust human-like, contact-rich bimanual in-hand manipulation with significantly improved success rates.
UniGround introduces a novel, training-free framework for universal 3D visual grounding that leverages global candidate filtering and local precision reasoning to achieve state-of-the-art zero-shot performance in localizing arbitrary objects within complex 3D environments without relying on pre-trained models or 3D supervision.
FLED-GS is a fast framework for novel view synthesis in 3D dark scenes that addresses compound low-light, noise, and motion blur degradations by reformulating restoration as an alternating cycle of 2D deblurring and noise-aware 3D Gaussian Splatting reconstruction, achieving superior performance with significantly faster training and rendering speeds compared to state-of-the-art methods.
This paper resolves the fundamental mismatch between the combinatorial structure and observable behavior of Higher-Dimensional Automata by developing an order-independent semantics based on interval ipomsets, which unifies various categorical presentations and bisimulation concepts while eliminating artificial event ordering artifacts.
This paper introduces VesselFusion, a diffusion model-based approach that utilizes coarse-to-fine representation and voting-based aggregation to achieve more accurate and natural vessel centerline extraction from 3D CT images compared to conventional deterministic methods.
This study challenges the assumption that physical robot interaction universally enhances user experience by demonstrating that while tangible delivery does not inherently improve engagement, it significantly reduces narrative immersion for individuals with high negative attitudes toward robots, who instead benefit from digitally mediated interfaces as a social buffer.
This position paper argues that as wearable Augmented Reality evolves into Mediated Reality capable of altering visual scenes in safety-critical mobile contexts, it is essential to develop governance mechanisms that allow users to configure, inspect, and understand these perceptual modifications without compromising safety and trust.
This paper presents a model-based control framework for humanoid robots that utilizes trained tactile force estimators to dynamically redistribute forces across the torso, arm, wrist, and fingers, thereby maintaining stable contact with objects of varying mass or unstable configurations by minimizing the distance between the Center of Pressure and the contact polygon centroid.
This paper introduces MV-Fashion, a large-scale multi-view video dataset featuring 3,273 sequences with pixel-level annotations, ground-truth material properties, and paired flat/worn garment images, designed to bridge the realism and annotation gaps in existing datasets for virtual try-on and size estimation tasks.
Edged USLAM is a hybrid visual-inertial SLAM system that integrates an edge-aware front-end and a lightweight depth module to achieve robust, drift-minimized localization on UAVs, particularly excelling in slow or structured trajectories under challenging illumination where purely event-based or learning-based methods may struggle.