Tag
This paper introduces a joint argument and entity detection method for political debates, using a generative framework with decoder-only LLMs to improve performance over sequential pipelines.
CoToGrasp is a generative framework that synthesizes diverse, stable grasps conditioned on specific contact topologies using a canonical workspace for zero-shot generalization, outperforming existing planners on the DexGraspNet dataset.
This paper introduces Predictive Set Theory, a formal generative framework for cognitive architecture that reconstructs cognition from set-theoretic operations and addresses limitations in predictive processing and Bayesian cognitive science.
This paper proposes a cross-modal generative framework that synthesizes fetal Doppler ultrasound waveforms from fetal-maternal electrocardiograms, using cross-modal attention and dilated convolutions, achieving improved synthesis quality and quantifying the influence of maternal-fetal coupling.
DiffoR proposes a novel continuous generative framework for ordinal regression using diffusion models, overcoming limitations of discrete methods. Extensive experiments on 12 benchmarks demonstrate state-of-the-art performance across four domains.
This paper proposes a generative framework for emotion intensity evaluation, shifting from discrete classification to continuous 0-100 scoring. It demonstrates superior performance and generalization in domains like finance.
ChangeFlow presents a generative framework for remote sensing change detection that synthesizes change masks in latent space using rectified flow, achieving improved accuracy and robustness through sampling-based prediction ensembling, with an average F1 of 80.4% across four benchmarks.