6076 papers
The paper introduces OrdinalBench, a comprehensive benchmark dataset and evaluation framework designed to diagnose and expose the significant generalization limitations of Vision-Language Models in understanding ordinal numbers and performing sequential reasoning tasks involving large indices and complex paths.
The paper proposes Structured Gaussian Image (SGI), a framework that represents high-resolution images using multi-scale, seed-based structured 2D Gaussians generated by lightweight MLPs, achieving significant compression and faster convergence compared to existing unstructured 2D Gaussian methods while maintaining high image fidelity.
This paper introduces 4DRC-OCC, the first framework to fuse 4D radar and camera data for robust 3D semantic occupancy prediction, leveraging their complementary strengths to overcome adverse weather and lighting challenges while utilizing a newly created automatically labeled dataset to reduce annotation costs.
This paper presents a multi-legged robot equipped with biomimetic, gradient-compliant tactile antennae that enable robust navigation and recovery in confined, obstacle-rich environments by mapping antenna deformation to collision states for real-time steering without relying on global environmental information or vision.
This paper introduces Inverse Resistive Force Theory (I-RFT), a physics-informed machine learning framework that enables robots to accurately estimate granular terrain properties from proprioceptive contact forces under arbitrary gait trajectories, thereby facilitating data-efficient environmental characterization and adaptive locomotion strategies.
This paper introduces MWM, a mobile world model that enhances action-conditioned rollout consistency and inference efficiency for image-goal navigation through a novel two-stage training framework featuring Action-Conditioned Consistency post-training and Inference-Consistent State Distillation.
The paper introduces STEP, a preference-conditioned reinforcement learning framework that optimizes robotic 3D bin packing by explicitly balancing spatial efficiency against operational time, achieving a 44% reduction in execution time without compromising packing density.
This paper investigates the non-injectivity of the verbose persistent homology transform (VPHT) for graphs with collinear vertices, identifying necessary and sufficient conditions for their non-reconstructibility to advance a complete classification of such cases.
This paper proposes a temperature-aware, distributed optimization approach using the alternating direction method of multipliers to co-optimize energy, carbon, water, and latency costs for LLM inference across geo-distributed edge data centers in Australia, leveraging ambient temperature diversity to enhance sustainability and efficiency.
This paper examines the governance of AI-generated content across 40 social media platforms, finding that while most focus on moderation and disclosure, few address ownership and monetization, prompting a call for more comprehensive policies and user education.
HybridStitch is a novel Text-to-Image generation paradigm that accelerates diffusion models by treating generation as an editing process, dynamically splitting the image into easy and complex regions to leverage a small model for coarse sketching and a large model for targeted refinement, thereby achieving a 1.83× speedup on Stable Diffusion 3.
This study demonstrates that low-cost, animal-triggered camera traps combined with foundation vision models can effectively monitor fine-grained plant phenology and flora-faunal interactions in a Hawaiian cloud forest, revealing ecological trends that traditional sampling methods often miss.
This paper presents a curved monopole antenna design optimized for HF skywave radar that, through parametric analysis of curvature and straight-section length, achieves significantly enhanced gain and bandwidth compared to conventional monopoles, and demonstrates further performance improvements when scaled into a 12-element linear array.
This paper introduces the AWARE evaluation framework to systematically analyze screen reader-assisted authentication, revealing that current two-factor and passwordless methods contain significant accessibility flaws that expose blind and visually impaired users to various security vulnerabilities.
This paper proposes a dual-mode human-robot joint planning system that combines an LLM-assisted active elicitation mechanism with real-time intent inference to effectively mitigate task-relevant knowledge gaps and latent human intent, significantly reducing interaction costs and execution time in open-world environments.
This paper proposes a hierarchical quantum annealing-based model predictive control framework for large-scale household energy scheduling with hydrogen storage, demonstrating its superior scalability and effectiveness in solving complex optimization problems as the number of connected households increases compared to traditional methods.
This paper introduces MINT, a novel framework that enhances human-AI drone collaboration by using large language models to actively elicit minimal, targeted information from operators to resolve environmental uncertainties, thereby significantly improving task success rates while reducing the need for frequent human intervention.
This paper presents a unified control framework for aerial manipulators that integrates a physics-based blade-element model with a learning-based residual force estimator and online rotor-speed adaptation to achieve robust trajectory tracking and wall-contact operations in complex wind and near-wall environments.
This paper presents the implementation of a novel, rigorous time-domain phase-noise analysis module in the open-source QUCS simulator, featuring new closed-form expressions for amplitude and phase-amplitude correlations that surpass existing empirical models and commercial EDA capabilities in predicting the performance of noise-perturbed autonomous circuits.
This paper introduces VRGaze, the first large-scale off-axis gaze estimation dataset for VR, and GazeShift, an unsupervised, attention-guided framework that achieves real-time, label-efficient gaze tracking with high accuracy on both the new dataset and standard benchmarks.