arXiv subjects

Lei Cai

Publications and source records attributed to Lei Cai.

At least 19 recordsLinked to original sources

arXiv2026

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility

World-action models (WAMs) predict the future to act better, but nearly all of them predict only RGB latents, trained purely for pixel reconstruction, with no explicit signal for the 3D geometry or object semantics manipulation needs. We find a surprising free lunch: the same frozen video-generation VAE that encodes RGB also encodes 3D pointmaps almost losslessly, with no pointmap-specific training at all. This lets us supervise Flex-$\pi$, a 6B-parameter WAM, on 3D geometry and object-centric DINO semantics alongside RGB, at no cost in new sensors, new pre-training, or inference latency. Every visual signal is projected into this shared latent space and denoised jointly with actions inside a Mixture-of-Transformers backbone; per-stream dropout with cross-modality forcing then lets a single trained checkpoint run on any subset of these streams, from a fast action-only mode to full joint generation. The result is a policy that is exceptionally demonstration-efficient and generalizes well, beating the strongest baselines by up to 2-7$\times$ on dexterous, precise, real-world bimanual manipulation tasks both in and out of distribution, all while running faster than $\pi_{0.5}$. Our project website: https://flex-pi.github.io/

cs.RO↗

arXiv2025

Investigating Students' Preferences for AI Roles in Mathematical Modelling: Evidence from a Randomized Controlled Trial

Mathematical modelling (MM) is a key competency for solving complex real-world problems, yet many students struggle with abstraction, representation, and iterative reasoning. Artificial intelligence (AI) has been proposed as a support for higher-order thinking, but its role in MM education is still underexplored. This study examines the relationships among students' design thinking (DT), computational thinking (CT), and mathematical modelling self-efficacy (MMSE), and investigates their preferences for different AI roles during the modelling process. Using a randomized controlled trial, we identify significant connections among DT, CT, and MMSE, and reveal distinct patterns in students' preferred AI roles, including AI as a tutor (providing explanations and feedback), AI as a tool (assisting with calculations and representations), AI as a collaborator (suggesting strategies and co-creating models), and AI as a peer (offering encouragement and fostering reflection). Differences across learner profiles highlight how students' dispositions shape their expectations for AI. These findings advance understanding of AI-supported MM and provide design implications for adaptive, learner-centered systems.

cs.HC↗

arXiv2025

Quantized resonant tunneling effect in Josephson junctions with ferromagnetic bilayers

We study the Josephson effect in one-dimensional SF$_1$F$_2$S junctions, which consist of conventional s-wave superconductors (S) connected by two ferromagnetic layers (F$_1$ and F$_2$). At low temperatures, the potential barrier at the F$_1$/F$_2$ interface can induce a quantized resonant tunneling effect. This effect not only modifies the amplitude of the critical current but also affects the phase of the Josephson current. As the exchange fields ($h_1$, $h_2$) and thicknesses ($d_1$, $d_2$) of the F$_1$ and F$_2$ layers vary, the critical current displays periodic resonance peaks. These peaks occur under the quantization conditions $Q_{1(2)} d_{1(2)} = \left(n_{1(2)} + 1/2\right) π$, where $Q_{1(2)} = 2h_{1(2)}/(\hbar v_F)$ is the center-of-mass momentum carried by Cooper pairs, with $v_F$ being the Fermi velocity, and $n_{1(2)} = 0, 1, 2, \cdots$. It can be inferred that the potential barrier suppresses the transport of spin-singlet pairs while allowing spin-triplet pairs with zero spin projection along the magnetization axis to pass through. As these spin-triplet pairs traverse the F$_1$ and F$_2$ layers, the total phase they acquire determines the ground state of the Josephson junction. At the resonance peaks, the Josephson current primarily arises from the first harmonic in both the parallel and antiparallel magnetization configurations. However, in perpendicular configurations, the second harmonic becomes more significant. In scenarios where both ferromagnetic layers have identical exchange fields and thicknesses, the potential barrier selectively suppresses the current in the 0-state while allowing it to persist in the $π$-state for parallel configurations. Conversely, in antiparallel configurations, the current in the 0-state is consistently preserved.

cond-mat.supr-con↗

arXiv2025

Hybrid Type-II and Type-III seesaw model for the muon $g-2$ anomaly

In this work we investigate the muon anomalous magnetic dipole moment $a_μ$ in a model that extends the Standard Model with a scalar triplet and a lepton triplet. Different from previous studies, we find that there is still viable parameter space in this model to explain the discrepancy $Δa_μ=a_μ(\mathrm{Exp})-a_μ(\mathrm{SM})$. While being consistent with the current data of neutrino mass, electroweak precision measurements and the perturbativity of couplings, our model can provide new physics contribution $a_μ^\textrm{NP}$ to cover the central region of $Δa_μ$ with new scalar and lepton mass as low as around TeV. This mass scale is allowed by the current collider searches for doubly charged scalars and the lepton triplet, and they can be tested at future high energy and/or high luminosity colliders.

hep-ph↗

arXiv2025

Strong quasi-MV* algebras and their logics

In this paper, we introduce the subvariety of quasi-MV* algebras in order to characterize the logic which is related to complex fuzzy logic. First, we give the definitions of strong quasi-MV* algebra and strong quasi-Wajsberg* algebra and show that they are term equivalence. Second, we present the representation theorem and the standard completeness of strong quasi-MV* algebras. Moreover, we discuss the properties of terms in the language of Wajsberg* algebras and strong quasi-Wajsberg* algebras. Finally, we establish the logical system associated with strong quasi-Wajsberg* algebra and prove that the logical system is sound and complete.

math.LO↗

arXiv2025

The logic of quasi MV star algebras

Quasi-MV* algebras were introduced as generalizations of MV*-algebras and quasi-MV algebras. The recent investigation into quasi-MV* algebras shows that they are closely related to quantum computational logic and complex fuzzy logic. In this paper, we aim to study the logical system associated with quasi-MV* algebras in detail. First, we introduce quasi-Wajsberg* algebras as the term equivalence of quasi-MV* algebras and investigate the related properties of quasi-Wajsberg* algebras. Then we establish the logical system associated with quasi-Wajsberg* algebras using fewer deduction rules. Finally, we discuss the soundness of this logical system.

math.LO↗

arXiv2024

SemiDDM-Weather: A Semi-supervised Learning Framework for All-in-one Adverse Weather Removal

Adverse weather removal aims to restore clear vision under adverse weather conditions. Existing methods are mostly tailored for specific weather types and rely heavily on extensive labeled data. In dealing with these two limitations, this paper presents a pioneering semi-supervised all-in-one adverse weather removal framework built on the teacher-student network with a Denoising Diffusion Model (DDM) as the backbone, termed SemiDDM-Weather. As for the design of DDM backbone in our SemiDDM-Weather, we adopt the SOTA Wavelet Diffusion Model-Wavediff with customized inputs and loss functions, devoted to facilitating the learning of many-to-one mapping distributions for efficient all-in-one adverse weather removal with limited label data. To mitigate the risk of misleading model training due to potentially inaccurate pseudo-labels generated by the teacher network in semi-supervised learning, we introduce quality assessment and content consistency constraints to screen the "optimal" outputs from the teacher network as the pseudo-labels, thus more effectively guiding the student network training with unlabeled data. Experimental results show that on both synthetic and real-world datasets, our SemiDDM-Weather consistently delivers high visual quality and superior adverse weather removal, even when compared to fully supervised competitors. Our code and pre-trained model are available at this repository.

cs.CV↗

arXiv2024

Image Re-Identification: Where Self-supervision Meets Vision-Language Learning

Recently, large-scale vision-language pre-trained models like CLIP have shown impressive performance in image re-identification (ReID). In this work, we explore whether self-supervision can aid in the use of CLIP for image ReID tasks. Specifically, we propose SVLL-ReID, the first attempt to integrate self-supervision and pre-trained CLIP via two training stages to facilitate the image ReID. We observe that: 1) incorporating language self-supervision in the first training stage can make the learnable text prompts more distinguishable, and 2) incorporating vision self-supervision in the second training stage can make the image features learned by the image encoder more discriminative. These observations imply that: 1) the text prompt learning in the first stage can benefit from the language self-supervision, and 2) the image feature learning in the second stage can benefit from the vision self-supervision. These benefits jointly facilitate the performance gain of the proposed SVLL-ReID. By conducting experiments on six image ReID benchmark datasets without any concrete text labels, we find that the proposed SVLL-ReID achieves the overall best performances compared with state-of-the-arts. Codes will be publicly available at https://github.com/BinWangGzhu/SVLL-ReID.

cs.CV↗

arXiv2024

The Devil is in the Details: Boosting Guided Depth Super-Resolution via Rethinking Cross-Modal Alignment and Aggregation

Guided depth super-resolution (GDSR) involves restoring missing depth details using the high-resolution RGB image of the same scene. Previous approaches have struggled with the heterogeneity and complementarity of the multi-modal inputs, and neglected the issues of modal misalignment, geometrical misalignment, and feature selection. In this study, we rethink some essential components in GDSR networks and propose a simple yet effective Dynamic Dual Alignment and Aggregation network (D2A2). D2A2 mainly consists of 1) a dynamic dual alignment module that adapts to alleviate the modal misalignment via a learnable domain alignment block and geometrically align cross-modal features by learning the offset; and 2) a mask-to-pixel feature aggregate module that uses the gated mechanism and pixel attention to filter out irrelevant texture noise from RGB features and combine the useful features with depth features. By combining the strengths of RGB and depth features while minimizing disturbance introduced by the RGB image, our method with simple reuse and redesign of basic components achieves state-of-the-art performance on multiple benchmark datasets. The code is available at https://github.com/JiangXinni/D2A2.

cs.CV↗

arXiv2023

MFMAN-YOLO: A Method for Detecting Pole-like Obstacles in Complex Environment

In real-world traffic, there are various uncertainties and complexities in road and weather conditions. To solve the problem that the feature information of pole-like obstacles in complex environments is easily lost, resulting in low detection accuracy and low real-time performance, a multi-scale hybrid attention mechanism detection algorithm is proposed in this paper. First, the optimal transport function Monge-Kantorovich (MK) is incorporated not only to solve the problem of overlapping multiple prediction frames with optimal matching but also the MK function can be regularized to prevent model over-fitting; then, the features at different scales are up-sampled separately according to the optimized efficient multi-scale feature pyramid. Finally, the extraction of multi-scale feature space channel information is enhanced in complex environments based on the hybrid attention mechanism, which suppresses the irrelevant complex environment background information and focuses the feature information of pole-like obstacles. Meanwhile, this paper conducts real road test experiments in a variety of complex environments. The experimental results show that the detection precision, recall, and average precision of the method are 94.7%, 93.1%, and 97.4%, respectively, and the detection frame rate is 400 f/s. This research method can detect pole-like obstacles in a complex road environment in real time and accurately, which further promotes innovation and progress in the field of automatic driving.

cs.CV↗

arXiv2023

Multi-scale Attentive Image De-raining Networks via Neural Architecture Search

Multi-scale architectures and attention modules have shown effectiveness in many deep learning-based image de-raining methods. However, manually designing and integrating these two components into a neural network requires a bulk of labor and extensive expertise. In this article, a high-performance multi-scale attentive neural architecture search (MANAS) framework is technically developed for image deraining. The proposed method formulates a new multi-scale attention search space with multiple flexible modules that are favorite to the image de-raining task. Under the search space, multi-scale attentive cells are built, which are further used to construct a powerful image de-raining network. The internal multiscale attentive architecture of the de-raining network is searched automatically through a gradient-based search algorithm, which avoids the daunting procedure of the manual design to some extent. Moreover, in order to obtain a robust image de-raining model, a practical and effective multi-to-one training strategy is also presented to allow the de-raining network to get sufficient background information from multiple rainy images with the same background scene, and meanwhile, multiple loss functions including external loss, internal loss, architecture regularization loss, and model complexity loss are jointly optimized to achieve robust de-raining performance and controllable model complexity. Extensive experimental results on both synthetic and realistic rainy images, as well as the down-stream vision applications (i.e., objection detection and segmentation) consistently demonstrate the superiority of our proposed method. The code is publicly available at https://github.com/lcai-gz/MANAS.

cs.CV↗

arXiv2021

Advanced Graph and Sequence Neural Networks for Molecular Property Prediction and Drug Discovery

Properties of molecules are indicative of their functions and thus are useful in many applications. With the advances of deep learning methods, computational approaches for predicting molecular properties are gaining increasing momentum. However, there lacks customized and advanced methods and comprehensive tools for this task currently. Here we develop a suite of comprehensive machine learning methods and tools spanning different computational models, molecular representations, and loss functions for molecular property prediction and drug discovery. Specifically, we represent molecules as both graphs and sequences. Built on these representations, we develop novel deep models for learning from molecular graphs and sequences. In order to learn effectively from highly imbalanced datasets, we develop advanced loss functions that optimize areas under precision-recall curves. Altogether, our work not only serves as a comprehensive tool, but also contributes towards developing novel and advanced graph and sequence learning methodologies. Results on both online and offline antibiotics discovery and molecular property prediction tasks show that our methods achieve consistent improvements over prior methods. In particular, our methods achieve #1 ranking in terms of both ROC-AUC and PRC-AUC on the AI Cures Open Challenge for drug discovery related to COVID-19. Our software is released as part of the MoleculeX library under AdvProp.

q-bio.QM↗

arXiv2020

Line Graph Neural Networks for Link Prediction

We consider the graph link prediction task, which is a classic graph analytical problem with many real-world applications. With the advances of deep learning, current link prediction methods commonly compute features from subgraphs centered at two neighboring nodes and use the features to predict the label of the link between these two nodes. In this formalism, a link prediction problem is converted to a graph classification task. In order to extract fixed-size features for classification, graph pooling layers are necessary in the deep learning model, thereby incurring information loss. To overcome this key limitation, we propose to seek a radically different and novel path by making use of the line graphs in graph theory. In particular, each node in a line graph corresponds to a unique edge in the original graph. Therefore, link prediction problems in the original graph can be equivalently solved as a node classification problem in its corresponding line graph, instead of a graph classification task. Experimental results on fourteen datasets from different applications demonstrate that our proposed method consistently outperforms the state-of-the-art methods, while it has fewer parameters and high training efficiency.

cs.LG↗

arXiv2020

Deep Low-Shot Learning for Biological Image Classification and Visualization from Limited Training Samples

Predictive modeling is useful but very challenging in biological image analysis due to the high cost of obtaining and labeling training data. For example, in the study of gene interaction and regulation in Drosophila embryogenesis, the analysis is most biologically meaningful when in situ hybridization (ISH) gene expression pattern images from the same developmental stage are compared. However, labeling training data with precise stages is very time-consuming even for evelopmental biologists. Thus, a critical challenge is how to build accurate computational models for precise developmental stage classification from limited training samples. In addition, identification and visualization of developmental landmarks are required to enable biologists to interpret prediction results and calibrate models. To address these challenges, we propose a deep two-step low-shot learning framework to accurately classify ISH images using limited training images. Specifically, to enable accurate model training on limited training samples, we formulate the task as a deep low-shot learning problem and develop a novel two-step learning approach, including data-level learning and feature-level learning. We use a deep residual network as our base model and achieve improved performance in the precise stage prediction task of ISH images. Furthermore, the deep model can be interpreted by computing saliency maps, which consist of pixel-wise contributions of an image to its prediction result. In our task, saliency maps are used to assist the identification and visualization of developmental landmarks. Our experimental results show that the proposed model can not only make accurate predictions, but also yield biologically meaningful interpretations. We anticipate our methods to be easily generalizable to other biological image classification tasks with small training datasets.

cs.LG↗

arXiv2020

Structural Plan of Indoor Scenes with Personalized Preferences

In this paper, we propose an assistive model that supports professional interior designers to produce industrial interior decoration solutions and to meet the personalized preferences of the property owners. The proposed model is able to automatically produce the layout of objects of a particular indoor scene according to property owners' preferences. In particular, the model consists of the extraction of abstract graph, conditional graph generation, and conditional scene instantiation. We provide an interior layout dataset that contains real-world 11000 designs from professional designers. Our numerical results on the dataset demonstrate the effectiveness of the proposed model compared with the state-of-art methods.

cs.CV↗

arXiv2020

Deep Learning of High-Order Interactions for Protein Interface Prediction

Protein interactions are important in a broad range of biological processes. Traditionally, computational methods have been developed to automatically predict protein interface from hand-crafted features. Recent approaches employ deep neural networks and predict the interaction of each amino acid pair independently. However, these methods do not incorporate the important sequential information from amino acid chains and the high-order pairwise interactions. Intuitively, the prediction of an amino acid pair should depend on both their features and the information of other amino acid pairs. In this work, we propose to formulate the protein interface prediction as a 2D dense prediction problem. In addition, we propose a novel deep model to incorporate the sequential information and high-order pairwise interactions to perform interface predictions. We represent proteins as graphs and employ graph neural networks to learn node features. Then we propose the sequential modeling method to incorporate the sequential information and reorder the feature matrix. Next, we incorporate high-order pairwise interactions to generate a 3D tensor containing different pairwise interactions. Finally, we employ convolutional neural networks to perform 2D dense predictions. Experimental results on multiple benchmarks demonstrate that our proposed method can consistently improve the protein interface prediction performance.

cs.LG↗

arXiv2020

Adversarial Model for Rotated Indoor Scenes Planning

In this paper, we propose an adversarial model for producing furniture layout for interior scene synthesis when the interior room is rotated. The proposed model combines a conditional adversarial network, a rotation module, a mode module, and a rotation discriminator module. As compared with the prior work on scene synthesis, our proposed three modules enhance the ability of auto-layout generation and reduce the mode collapse during the rotation of the interior room. We conduct our experiments on a proposed real-world interior layout dataset that contains 14400 designs from the professional designers. Our numerical results demonstrate that the proposed model yields higher-quality layouts for four types of rooms, including the bedroom, the bathroom, the study room, and the tatami room.

cs.CV↗

arXiv2020

Structural Temporal Graph Neural Networks for Anomaly Detection in Dynamic Graphs

Detecting anomalies in dynamic graphs is a vital task, with numerous practical applications in areas such as security, finance, and social media. Previous network embedding based methods have been mostly focusing on learning good node representations, whereas largely ignoring the subgraph structural changes related to the target nodes in dynamic graphs. In this paper, we propose StrGNN, an end-to-end structural temporal Graph Neural Network model for detecting anomalous edges in dynamic graphs. In particular, we first extract the $h$-hop enclosing subgraph centered on the target edge and propose the node labeling function to identify the role of each node in the subgraph. Then, we leverage graph convolution operation and Sortpooling layer to extract the fixed-size feature from each snapshot/timestamp. Based on the extracted features, we utilize Gated recurrent units (GRUs) to capture the temporal information for anomaly detection. Extensive experiments on six benchmark datasets and a real enterprise security system demonstrate the effectiveness of StrGNN.

cs.LG↗