6 papers
Poisson2Gaussian: Noise Gaussianization to Enhance Image Denoising
Xirou Zhou, Zijing Xu, Yibo Qu +3
The quantum nature of light determines the inherent Poisson stochasticity of photon detection, which is ubiquitous in photography, microscopy, and astronomy. However, our controlle…
TRACE: Timely Retrieval and Alignment for Cybersecurity Knowledge Graph Construction and Expansion
Zijing Xu, Ziwei Ning, Tiancheng Hu +4
The rapid evolution of cyber threats has highlighted significant gaps in security knowledge integration. Cybersecurity Knowledge Graphs (CKGs) relying on structured data inherently…
Contribution-Guided Asymmetric Learning for Robust Multimodal Fusion under Imbalance and Noise
Zijing Xu, Yunfeng Kou, Kunming Wu +1
Multimodal learning faces two major challenges: modality imbalance and data noise, which significantly affect the robustness and generalization ability of models. Existing methods…
LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence
Xingxuan Zhang, Gang Ren, Han Yu +35
We argue that progress toward general intelligence requires complementary foundation models grounded in language, the physical world, and structured data. This report presents Limi…
DemoSpeedup: Accelerating Visuomotor Policies via Entropy-Guided Demonstration Acceleration
Lingxiao Guo, Zhengrong Xue, Zijing Xu +1
Imitation learning has shown great promise in robotic manipulation, but the policy's execution is often unsatisfactorily slow due to commonly tardy demonstrations collected by huma…
Exploring the Low-Pass Filtering Behavior in Image Super-Resolution
Haoyu Deng, Zijing Xu, Yule Duan +3
Deep neural networks for image super-resolution (ISR) have shown significant advantages over traditional approaches like the interpolation. However, they are often criticized as 'b…