Flexible Spectral-Normalized Neural Gaussian Process for Dynamic Aperture Prediction
本文提出了一种用于动态孔径预测的谱归一化神经高斯过程方法，通过集成超参数学习减少计算负担，解决大规模科学应用中的不确定性量化问题。
0 citationsRead paper
Selected work
Representative Papers
Learning to Forecast Crop Growth from Earth Observation Data
This study addresses trajectory distortion in national-scale crop growth prediction caused by sparse observations. We propose a lightweight unimodal shape-regularized Seq2Seq model that integrates Sentinel-2 remote sensing time series with meteorological drivers, embedding biological priors into a deep learning framework to effectively constrain curve morphology under sparse supervision. Experimental results demonstrate that the model predicts winter wheat LAI trajectories with an R² exceeding 0.8, significantly outperforming conventional methods. This approach achieves high-precision retrieval of growth dynamics consistent with agronomic principles, validating the effectiveness of multi-source data-driven sequence modeling for landscape-scale crop monitoring.
0 citationsRead paper
AI Wizards at EXIST 2026: Hierarchical Soft-Label Learning for Multimodal Sexism Identification in Memes
This work addresses the challenge of multimodal gender bias detection in internet memes by proposing a hierarchical soft-label learning framework that models three progressively difficult subtasks as conditional prediction problems, effectively capturing both inter-annotator semantic disagreements and task dependencies. Leveraging visual-language representations from Gemini Embedding 2, the approach introduces a lightweight gated MLP and employs an optimization strategy combining KL divergence with homoscedastic uncertainty weighting. Evaluated on the EXIST 2026 benchmark, the method achieves first place on Task 2.3 and fourth place on both Tasks 2.1 and 2.2 in the official Soft-Soft leaderboard, demonstrating its effectiveness and technical novelty.
0 citationsRead paper
Diffusion Active Learning: Towards Data-Driven Experimental Design in Computed Tomography
To address the ill-posed inverse problem of low-dose, few-view CT reconstruction, this paper proposes an active learning framework integrating generative diffusion models with data-driven sequential experimental design. Methodologically, it introduces an unconditional diffusion model as a structured prior within a closed-loop active learning pipeline; reconstruction uncertainty is quantified via diffusion posterior sampling, enabling adaptive selection of the most informative projection angles—thereby jointly optimizing measurement strategy and reconstruction quality. The framework comprises three stages: diffusion model pretraining, uncertainty-driven active query selection, and iterative co-updating of reconstruction and acquisition. Evaluated on multiple real-world CT datasets, the method achieves equivalent X-ray dose reductions of 30–50% while improving PSNR by 2.1–3.8 dB, significantly outperforming conventional sparse-angle reconstruction and state-of-the-art active learning approaches.
0 citationsRead paper
Recent publications
Latest Papers
Flexible Spectral-Normalized Neural Gaussian Process for Dynamic Aperture Prediction
本文提出了一种用于动态孔径预测的谱归一化神经高斯过程方法，通过集成超参数学习减少计算负担，解决大规模科学应用中的不确定性量化问题。
0 citationsRead paper
Learning to Forecast Crop Growth from Earth Observation Data
This study addresses trajectory distortion in national-scale crop growth prediction caused by sparse observations. We propose a lightweight unimodal shape-regularized Seq2Seq model that integrates Sentinel-2 remote sensing time series with meteorological drivers, embedding biological priors into a deep learning framework to effectively constrain curve morphology under sparse supervision. Experimental results demonstrate that the model predicts winter wheat LAI trajectories with an R² exceeding 0.8, significantly outperforming conventional methods. This approach achieves high-precision retrieval of growth dynamics consistent with agronomic principles, validating the effectiveness of multi-source data-driven sequence modeling for landscape-scale crop monitoring.
0 citationsRead paper
AI Wizards at EXIST 2026: Hierarchical Soft-Label Learning for Multimodal Sexism Identification in Memes
This work addresses the challenge of multimodal gender bias detection in internet memes by proposing a hierarchical soft-label learning framework that models three progressively difficult subtasks as conditional prediction problems, effectively capturing both inter-annotator semantic disagreements and task dependencies. Leveraging visual-language representations from Gemini Embedding 2, the approach introduces a lightweight gated MLP and employs an optimization strategy combining KL divergence with homoscedastic uncertainty weighting. Evaluated on the EXIST 2026 benchmark, the method achieves first place on Task 2.3 and fourth place on both Tasks 2.1 and 2.2 in the official Soft-Soft leaderboard, demonstrating its effectiveness and technical novelty.
0 citationsRead paper
Diffusion Active Learning: Towards Data-Driven Experimental Design in Computed Tomography
To address the ill-posed inverse problem of low-dose, few-view CT reconstruction, this paper proposes an active learning framework integrating generative diffusion models with data-driven sequential experimental design. Methodologically, it introduces an unconditional diffusion model as a structured prior within a closed-loop active learning pipeline; reconstruction uncertainty is quantified via diffusion posterior sampling, enabling adaptive selection of the most informative projection angles—thereby jointly optimizing measurement strategy and reconstruction quality. The framework comprises three stages: diffusion model pretraining, uncertainty-driven active query selection, and iterative co-updating of reconstruction and acquisition. Evaluated on multiple real-world CT datasets, the method achieves equivalent X-ray dose reductions of 30–50% while improving PSNR by 2.1–3.8 dB, significantly outperforming conventional sparse-angle reconstruction and state-of-the-art active learning approaches.
0 citationsRead paper