5673 papers
This paper introduces gRef-CW, the first benchmark dataset for generalised visual grounding in agriculture that includes negative expressions, and proposes Weed-VG, a modular framework designed to overcome the domain gap and effectively localise crop and weed instances under challenging field conditions.
This paper introduces the SIQA framework, which redefines scientific image quality assessment by distinguishing between perceptual alignment and scientific correctness, and demonstrates through a new benchmark that current multimodal models often achieve high scoring consistency with experts while lacking genuine scientific understanding.
This paper introduces the Fifth Graph Normal Form (5GNF), a trait-based framework that normalizes property graph metadata by extracting recurring attributes into shared Trait Nodes, thereby reducing redundancy and improving semantic clarity while maintaining competitive query performance.
This paper proposes a novel approach to mining data-aware temporal specifications from execution traces by combining Syntax Guided Synthesis with a finite-prefix interpretation of Temporal Stream Logic (TSL), enabling the robust and sample-efficient synthesis of reactive programs that capture both data transformations and temporal behaviors.
This paper presents a pivot-based, 3D-printed "kiri-spoon" that functions as both a hand-held and robot-assisted utensil, utilizing a plier-like mechanism to securely grasp food and significantly reduce spills for users with tremors and mobility limitations.
This paper proposes a hierarchical planning approach that integrates supplemental geostationary satellite data to extend lookahead horizons for Dynamic Targeting missions, demonstrating up to a 41% performance improvement over traditional onboard-only planners, particularly in scenarios with sparsely distributed targets.
This paper introduces Universal Watermark Presence Detection (UWPD), a novel task for identifying invisible watermarks without prior algorithm knowledge, supported by the UniFreq-100K dataset and the Frequency Shield Network (FSNet) model that achieves superior zero-shot detection by dynamically amplifying high-frequency watermark signals while suppressing semantic content.
This paper introduces the Open-Vocabulary Temporal Sentence Grounding (OV-TSGV) task with new benchmarks (Charades-OV and ActivityNet-OV) and proposes HERO, a hierarchical embedding-refinement framework that achieves state-of-the-art performance by effectively generalizing to novel linguistic expressions through multi-level semantic modeling and cross-modal refinement.
This paper proposes a vessel-aware deep learning framework for detecting age-related macular degeneration (AMD) in OCTA images by integrating external multiplicative attention with clinically meaningful vascular biomarkers, specifically tortuosity and dropout maps, to guide the model toward physiologically relevant regions and improve interpretability.
This paper presents "Agent Hunt," a decentralized autoformalization system for algebraic topology that utilizes a simulated bounty-based marketplace to coordinate multiple LLM agents in dynamically proposing, competing to prove, and iteratively refining formal statements within an Interactive Theorem Proving environment.
The paper introduces ResearchEnvBench, a new benchmark designed to evaluate autonomous agents' ability to synthesize complex execution environments for research code, revealing significant current limitations in dependency resolution and version management.
The paper introduces ViroGym, a comprehensive benchmark comprising extensive deep mutational scanning data and real-world tasks to evaluate protein language models for predicting viral variant effects and guiding rational antigen selection for vaccine development.
ButterflyViT introduces a geometric parameterization method that treats Mixture of Experts as rotations of a shared quantized substrate, achieving a 354 memory reduction for Vision Transformers on edge devices while maintaining accuracy through spatial smoothness regularization.
This paper surveys the landscape of robotic foundation models, identifies eleven key industrial implications to establish a 149-criteria assessment framework, and evaluates 324 models to reveal that current industrial readiness is limited and uneven, necessitating a shift from isolated benchmark successes to systematic integration of safety, real-time performance, and robust system deployment.
This paper introduces XMACNet, an explainable, lightweight CNN that combines self-attention mechanisms with multi-modal fusion of RGB images and vegetation indices to achieve high-accuracy chili disease classification suitable for edge deployment.
This paper introduces EarthBridge, a high-fidelity cross-modal translation framework combining Diffusion Bridge Implicit Models and Contrastive Unpaired Translation to achieve second place in the 4th Multi-modal Aerial View Image Challenge by effectively translating between SAR, EO, and IR aerial imagery.
This paper introduces a general-purpose, gradient-based nested co-design framework that jointly optimizes the aerodynamic shape and motion planner of winged robots using neural surrogate models for complex flow conditions, demonstrating superior performance and efficiency over evolutionary baselines in tasks like perching and short landing.
The paper proposes HiDE, a hierarchical dictionary-based entropy modeling framework for learned image compression that enhances coding efficiency by decomposing external priors into global and local dictionaries with cascaded retrieval and employing a context-aware parameter estimator to achieve significant BD-rate savings over state-of-the-art methods.
This paper presents a highly efficient method for 3D point cloud neighbourhood searching that combines Space-Filling Curves with a linear Octree structure and specialized algorithms, achieving up to 10 faster performance and significant cache miss reductions compared to existing solutions while demonstrating strong parallel scalability.
This paper proposes a novel black-box simulation method that combines RRT-style search, sampling-based MPC, and a stability-guided sampling scheme to efficiently discover diverse, long-horizon robot manipulation strategies without relying on labor-intensive human demonstrations or task-specific guidance.