Lei Liu’s research while affiliated with University of Science and Technology of China and other places

Tropical cyclone (TC) intensity forecasting is crucial for early disaster warning and emergency decision-making. Numerous researchers have explored deep-learning methods to address computational and post-processing issues in operational forecasting. Regrettably, they exhibit subpar long-term forecasting capabilities. We use two strategies to enhance long-term forecasting. (1) By enhancing the matching between TC intensity and spatial information, we can improve long-term forecasting performance. (2) Incorporating physical knowledge and physical constraints can help mitigate the accumulation of forecasting errors. To achieve the above strategies, we propose the VQLTI framework. VQLTI transfers the TC intensity information to a discrete latent space while retaining the spatial information differences, using large-scale spatial meteorological data as conditions. Furthermore, we leverage the forecast from the weather prediction model FengWu to provide additional physical knowledge for VQLTI. Additionally, we calculate the potential intensity (PI) to impose physical constraints on the latent variables. In the global long-term TC intensity forecasting, VQLTI achieves state-of-the-art results for the 24h to 120h, with the MSW (Maximum Sustained Wind) forecast error reduced by 35.65%-42.51% compared to ECMWF-IFS.

Purpose The main objective of this study was to analyze the fractal dimensions (D(f)) of retinal vasculature in premature infants with retinopathy of prematurity (ROP) and determine their correlation with ROP severity. Methods We conducted a single-center retrospective case-control study involving 641 premature patients with ROP (641 eyes) and 684 normal preterm infants (684 eyes) matched for corrected gestational age (CGA). Computer-assisted techniques were used to quantify peripapillary retinal vascular D(f), vessel tortuosity (VT), and vessel width (VW). Results Compared to the normal preterm groups, patients with ROP exhibited a significant increase in retinal vascular D(f) by 0.0061 (P = 0.0002). Subgroup analyses revealed a significant association between increasing ROP severity and increased retinal vascular D(f) (P < 0.05). Multivariable-adjusted ordered logistic regression models demonstrated that retinal vascular D(f) (aOR: 3.307, P < 0.0001) was significantly independent and associated with ROP severity. For every 0.1 increase in D(f), the probability of ROP requiring intervention increased by 33.07%. Multiple linear regression models indicated a significant positive correlation between D(f) and VT, as well as VW around the optic disc (P < 0.0001). For every 1 (10⁴ cm⁻³) increase in VT, D(f) increased by 0.0010. Similarly, for every 1 (μm) increase in VW, D(f) increased by 0.0025. Conclusions Our findings suggest that increased D(f) in retinal vessels is a pathological characteristic of ROP. This increase may be attributed to the curvature and width of the retinal vasculature in infants with ROP. Quantitative measurement of retinal vascular D(f) could serve as a valuable vascular indicator for assessing the severity of ROP.

Multimodal autoregressive (AR) models, based on next-token prediction and transformer architecture, have demonstrated remarkable capabilities in various multimodal tasks including text-to-image (T2I) generation. Despite their strong performance in general T2I tasks, our research reveals that these models initially struggle with subject-driven image generation compared to dominant diffusion models. To address this limitation, we introduce Proxy-Tuning, leveraging diffusion models to enhance AR models' capabilities in subject-specific image generation. Our method reveals a striking weak-to-strong phenomenon: fine-tuned AR models consistently outperform their diffusion model supervisors in both subject fidelity and prompt adherence. We analyze this performance shift and identify scenarios where AR models excel, particularly in multi-subject compositions and contextual understanding. This work not only demonstrates impressive results in subject-driven AR image generation, but also unveils the potential of weak-to-strong generalization in the image generation domain, contributing to a deeper understanding of different architectures' strengths and limitations.

Tropical cyclone (TC) intensity forecasting is crucial for early disaster warning and emergency decision-making. Numerous researchers have explored deep-learning methods to address computational and post-processing issues in operational forecasting. Regrettably, they exhibit subpar long-term forecasting capabilities. We use two strategies to enhance long-term forecasting. (1) By enhancing the matching between TC intensity and spatial information, we can improve long-term forecasting performance. (2) Incorporating physical knowledge and physical constraints can help mitigate the accumulation of forecasting errors. To achieve the above strategies, we propose the VQLTI framework. VQLTI transfers the TC intensity information to a discrete latent space while retaining the spatial information differences, using large-scale spatial meteorological data as conditions. Furthermore, we leverage the forecast from the weather prediction model FengWu to provide additional physical knowledge for VQLTI. Additionally, we calculate the potential intensity (PI) to impose physical constraints on the latent variables. In the global long-term TC intensity forecasting, VQLTI achieves state-of-the-art results for the 24h to 120h, with the MSW (Maximum Sustained Wind) forecast error reduced by 35.65%-42.51% compared to ECMWF-IFS.

Multi-view hashing is a crucial technology for multimedia retrieval because it transforms heterogeneous data from many viewpoints into binary hash codes. However, the existing approaches focus mostly on the complementarity among multiple views while being without confidence fusion. Furthermore, redundant noise is present in the single-view data in real-world application contexts. We present an innovative Adaptive Confidence Multi-View Learning (ACMVL) method to perform confidence fusion and remove extraneous noise. Initially, a confidence network is constructed to eliminate noise data and extract useful information from various single-view features. Moreover, an adaptive confidence multi-view network is utilized to quantify the confidence of each view and further fuse multiple view features using a weighted summation. Here, we propose an Automatic View Confidence Metric (AVCM) as a score for evaluating the confidence of views. Finally, to improve the semantic representation of the fused feature, a dilation network is created. Based on ACMVL, we introduce a novel Adaptive Confidence Multi-View Hashing (ACMVH) method. To our knowledge, we are the pioneers in using confidence learning for multimedia retrieval. Comprehensive experiments on three publicly available datasets demonstrate that our ACMVH outperforms the state-of-the-art methods (maximum improvement of $3.24\%$ on mAP). The original code is available at https://github.com/HackerHyper/ACMVH .