Tag
This paper proposes a geometry-aware multi-support heterogeneous graph neural network for fine-scale rainfall field reconstruction, which fuses observations from point gauges, path-integrated microwave links, and gridded radar/satellite data. The method reduces RMSE by 23.2% over classical interpolation on Singapore data and shows greatest gains when the field is undersampled relative to its spatial correlation length.
Proposes Geometry-aware R-Structured KAN (GRS-KAN), a hybrid neural architecture that integrates R-functions into KAN to encode geometric and logical constraints, achieving up to 67% RMSE reduction on regression benchmarks with discontinuities.
RaysUp is an ultra-lightweight, task-agnostic feature upsampling framework that uses geometry-aware ray domain techniques to reconstruct high-resolution features from low-resolution VFM outputs, achieving state-of-the-art performance with 84% fewer parameters than prior work and 7x faster inference.
Proposes REEF-GP, a post-hoc uncertainty quantification framework that fits a Gaussian process to the residuals of a frozen neural operator using its internal embeddings, enabling geometry-aware and calibrated uncertainties at low cost.
OmniLoc is a geometry-aware foundation model for anchor-free user equipment localization across diverse indoor environments, using a unified tokenization module, a geometry-aware Transformer, and geometric embeddings to significantly outperform existing methods.
GRASP introduces a geometry-aware, interaction-based method for scalable pretraining data attribution that models subset dynamics, outperforming existing additive approaches by over double the task-level rank correlation while reducing computation costs.
Introduces GARD, a diffusion-based framework that operates in the feature space of a feed-forward 3D reconstructor to jointly recover scene geometry and high-quality imagery from degraded inputs.
This paper introduces geometry-aware flow matching for natural images by treating them as points on a hypersphere, proposing SOT-CFM and SFM methods that improve generative modeling by leveraging the spherical structure of image data.
AnyMo is a geometry-aware framework for setup-agnostic human motion modeling using physics-grounded IMU simulation and graph encoding, achieving significant improvements in zero-shot activity recognition, cross-modal retrieval, and motion captioning across multiple datasets.
PanoWorld introduces spherical spatial cross-attention for panoramic reasoning, addressing limitations of MLLMs in 360-degree spatial understanding. It builds a large-scale pipeline for geometry-aware supervision and proposes a diagnostic benchmark, achieving state-of-the-art results on multiple benchmarks.
MC-RFM proposes a novel Riemannian flow-matching framework for few-shot adaptation that models feature displacement on a mixed-curvature manifold combining hyperbolic and Euclidean spaces, outperforming existing methods across multiple visual recognition benchmarks.
AnyRecon proposes a scalable framework for 3D reconstruction from arbitrary sparse inputs using a video diffusion model with persistent scene memory and geometry-aware conditioning.