arXiv subjects

Zhenyu Zhang

Publications and source records attributed to Zhenyu Zhang.

At least 145 records · Page 8Linked to original sources

arXiv2025

Debiasing Multimodal Large Language Models via Noise-Aware Preference Optimization

Multimodal Large Language Models excel in various tasks, yet often struggle with modality bias, where the model tends to rely heavily on a single modality and overlook critical information in other modalities, which leads to incorrect focus and generating irrelevant responses. In this paper, we propose using the paradigm of preference optimization to solve the modality bias problem, including RLAIFVBias, a debiased preference optimization dataset, and a Noise Aware Preference Optimization algorithm. Specifically, we first construct the dataset by introducing perturbations to reduce the informational content of certain modalities, compelling the model to rely on a specific modality when generating negative responses. To address the inevitable noise in automatically constructed data, we combine the noise robust Mean Absolute Error with the Binary Cross Entropy in Direct Preference Optimization by a negative Box Cox transformation, and dynamically adjust the algorithm noise robustness based on the evaluated noise levels in the data. Extensive experiments validate our approach, demonstrating not only its effectiveness in mitigating modality bias but also its significant role in minimizing hallucinations.

cs.CV↗

arXiv2025

Time-EAPCR-T: A Universal Deep Learning Approach for Anomaly Detection in Industrial Equipment

With the advancement of Industry 4.0, intelligent manufacturing extensively employs sensors for real-time multidimensional data collection, playing a crucial role in equipment monitoring, process optimisation, and efficiency enhancement. Industrial data exhibit characteristics such as multi-source heterogeneity, nonlinearity, strong coupling, and temporal interactions, while also being affected by noise interference. These complexities make it challenging for traditional anomaly detection methods to extract key features, impacting detection accuracy and stability. Traditional machine learning approaches often struggle with such complex data due to limitations in processing capacity and generalisation ability, making them inadequate for practical applications. While deep learning feature extraction modules have demonstrated remarkable performance in image and text processing, they remain ineffective when applied to multi-source heterogeneous industrial data lacking explicit correlations. Moreover, existing multi-source heterogeneous data processing techniques still rely on dimensionality reduction and feature selection, which can lead to information loss and difficulty in capturing high-order interactions. To address these challenges, this study applies the EAPCR and Time-EAPCR models proposed in previous research and introduces a new model, Time-EAPCR-T, where Transformer replaces the LSTM module in the time-series processing component of Time-EAPCR. This modification effectively addresses multi-source data heterogeneity, facilitates efficient multi-source feature fusion, and enhances the temporal feature extraction capabilities of multi-source industrial data.Experimental results demonstrate that the proposed method outperforms existing approaches across four industrial datasets, highlighting its broad application potential.

cs.LG↗

arXiv2025

Antiferroelectric Altermagnets: Antiferroelectricity Alters Magnets

Magnetoelectric coupling is crucial for uncovering fundamental phenomena and advancing technologies in high-density data storage and energy-efficient devices. The emergence of altermagnets, which unify the advantages of ferromagnets and antiferromagnets, offers unprecedented opportunities for magnetoelectric coupling. However, electrically tuning altermagnets remains an outstanding challenge. Here, we demonstrate how this challenge can be overcome by using antiferroelectricity and ferroelectricity to modulate the spin splitting in altermagnets, employing a universal, symmetry-based design principle supported by an effective model. We introduce an unexplored class of multiferroics: antiferroelectric altermagnets (AFEAM), where antiferroelectricity and altermagnetism coexist in a single material. From first-principles calculations, we validate the feasibility of AFEAM in well-established van der Waals metal thio(seleno)phosphates and perovskite oxides. We reveal the design of AFEAM ranging from two-dimensional monolayers to three-dimensional bulk structures. Remarkably, even a weak electric field can effectively toggle spin polarization in the AFEAM by switching between antiferroelectric and ferroelectric states. Our findings not only enrich the understanding of magnetoelectric coupling but also pave the way for electrically controlled spintronic and multiferroic devices.

cond-mat.mtrl-sci↗

arXiv2025

Time-EAPCR: A Deep Learning-Based Novel Approach for Anomaly Detection Applied to the Environmental Field

As human activities intensify, environmental systems such as aquatic ecosystems and water treatment systems face increasingly complex pressures, impacting ecological balance, public health, and sustainable development, making intelligent anomaly monitoring essential. However, traditional monitoring methods suffer from delayed responses, insufficient data processing capabilities, and weak generalisation, making them unsuitable for complex environmental monitoring needs.In recent years, machine learning has been widely applied to anomaly detection, but the multi-dimensional features and spatiotemporal dynamics of environmental ecological data, especially the long-term dependencies and strong variability in the time dimension, limit the effectiveness of traditional methods.Deep learning, with its ability to automatically learn features, captures complex nonlinear relationships, improving detection performance. However, its application in environmental monitoring is still in its early stages and requires further exploration.This paper introduces a new deep learning method, Time-EAPCR (Time-Embedding-Attention-Permutated CNN-Residual), and applies it to environmental science. The method uncovers feature correlations, captures temporal evolution patterns, and enables precise anomaly detection in environmental systems.We validated Time-EAPCR's high accuracy and robustness across four publicly available environmental datasets. Experimental results show that the method efficiently handles multi-source data, improves detection accuracy, and excels across various scenarios with strong adaptability and generalisation. Additionally, a real-world river monitoring dataset confirmed the feasibility of its deployment, providing reliable technical support for environmental monitoring.

cs.LG↗

arXiv2025

Inorganic Catalyst Efficiency Prediction Based on EAPCR Model: A Deep Learning Solution for Multi-Source Heterogeneous Data

The design of inorganic catalysts and the prediction of their catalytic efficiency are fundamental challenges in chemistry and materials science. Traditional catalyst evaluation methods primarily rely on machine learning techniques; however, these methods often struggle to process multi-source heterogeneous data, limiting both predictive accuracy and generalization. To address these limitations, this study introduces the Embedding-Attention-Permutated CNN-Residual (EAPCR) deep learning model. EAPCR constructs a feature association matrix using embedding and attention mechanisms and enhances predictive performance through permutated CNN architectures and residual connections. This approach enables the model to accurately capture complex feature interactions across various catalytic conditions, leading to precise efficiency predictions. EAPCR serves as a powerful tool for computational researchers while also assisting domain experts in optimizing catalyst design, effectively bridging the gap between data-driven modeling and experimental applications. We evaluate EAPCR on datasets from TiO2 photocatalysis, thermal catalysis, and electrocatalysis, demonstrating its superiority over traditional machine learning methods (e.g., linear regression, random forest) as well as conventional deep learning models (e.g., ANN, NNs). Across multiple evaluation metrics (MAE, MSE, R2, and RMSE), EAPCR consistently outperforms existing approaches. These findings highlight the strong potential of EAPCR in inorganic catalytic efficiency prediction. As a versatile deep learning framework, EAPCR not only improves predictive accuracy but also establishes a solid foundation for future large-scale model development in inorganic catalysis.

cs.LG↗

arXiv2025

Unsupervised Waste Classification By Dual-Encoder Contrastive Learning and Multi-Clustering Voting (DECMCV)

Waste classification is crucial for improving processing efficiency and reducing environmental pollution. Supervised deep learning methods are commonly used for automated waste classification, but they rely heavily on large labeled datasets, which are costly and inefficient to obtain. Real-world waste data often exhibit category and style biases, such as variations in camera angles, lighting conditions, and types of waste, which can impact the model's performance and generalization ability. Therefore, constructing a bias-free dataset is essential. Manual labeling is not only costly but also inefficient. While self-supervised learning helps address data scarcity, it still depends on some labeled data and generally results in lower accuracy compared to supervised methods. Unsupervised methods show potential in certain cases but typically do not perform as well as supervised models, highlighting the need for an efficient and cost-effective unsupervised approach. This study presents a novel unsupervised method, Dual-Encoder Contrastive Learning with Multi-Clustering Voting (DECMCV). The approach involves using a pre-trained ConvNeXt model for image encoding, leveraging VisionTransformer to generate positive samples, and applying a multi-clustering voting mechanism to address data labeling and domain shift issues. Experimental results demonstrate that DECMCV achieves classification accuracies of 93.78% and 98.29% on the TrashNet and Huawei Cloud datasets, respectively, outperforming or matching supervised models. On a real-world dataset of 4,169 waste images, only 50 labeled samples were needed to accurately label thousands, improving classification accuracy by 29.85% compared to supervised models. This method effectively addresses style differences, enhances model generalization, and contributes to the advancement of automated waste classification.

cs.CV↗

arXiv2025

Form factors in semileptonic decay of D mesons

We study the vector, scalar and tensor form factors for the semileptonic process $D\rightarrow K$ by using lattice Quantum Chromodynamcs (QCD). Chiral lattice fermions are used in our study: overlap fermion for the valence quark and domain-wall fermion for the sea. The 2+1-flavor configurations are from the RBC-UKQCD Collaborations with an inverse lattice spacing $1/a=2.383(9)$ GeV. A modified $z$-expansion taking into account valence quark mass dependence is used to fit our numerical results of the form factors at a fixed pion mass $\sim360$ MeV in the sea. At the physical valence quark mass point we give the preliminary results $f_+(0)=f_0(0)=0.760(39)$ and $f_T(0)=0.733(50)$ with only statistical uncertainties. For $f_T$ the number is given in the $\overline{\rm MS}$ scheme at a scale of 2 GeV.

hep-lat↗

arXiv2025

Anywhere: A Multi-Agent Framework for User-Guided, Reliable, and Diverse Foreground-Conditioned Image Generation

Recent advancements in image-conditioned image generation have demonstrated substantial progress. However, foreground-conditioned image generation remains underexplored, encountering challenges such as compromised object integrity, foreground-background inconsistencies, limited diversity, and reduced control flexibility. These challenges arise from current end-to-end inpainting models, which suffer from inaccurate training masks, limited foreground semantic understanding, data distribution biases, and inherent interference between visual and textual prompts. To overcome these limitations, we present Anywhere, a multi-agent framework that departs from the traditional end-to-end approach. In this framework, each agent is specialized in a distinct aspect, such as foreground understanding, diversity enhancement, object integrity protection, and textual prompt consistency. Our framework is further enhanced with the ability to incorporate optional user textual inputs, perform automated quality assessments, and initiate re-generation as needed. Comprehensive experiments demonstrate that this modular design effectively overcomes the limitations of existing end-to-end models, resulting in higher fidelity, quality, diversity and controllability in foreground-conditioned image generation. Additionally, the Anywhere framework is extensible, allowing it to benefit from future advancements in each individual agent.

cs.CV↗

arXiv2025

Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking

Large language models (LLMs) face inherent performance bottlenecks under parameter constraints, particularly in processing critical tokens that demand complex reasoning. Empirical analysis reveals challenging tokens induce abrupt gradient spikes across layers, exposing architectural stress points in standard Transformers. Building on this insight, we propose Inner Thinking Transformer (ITT), which reimagines layer computations as implicit thinking steps. ITT dynamically allocates computation through Adaptive Token Routing, iteratively refines representations via Residual Thinking Connections, and distinguishes reasoning phases using Thinking Step Encoding. ITT enables deeper processing of critical tokens without parameter expansion. Evaluations across 162M-466M parameter models show ITT achieves 96.5\% performance of a 466M Transformer using only 162M parameters, reduces training data by 43.2\%, and outperforms Transformer/Loop variants in 11 benchmarks. By enabling elastic computation allocation during inference, ITT balances performance and efficiency through architecture-aware optimization of implicit thinking pathways.

cs.CL↗

arXiv2025

Perfect spin-triplet pairing in two-dimensional Ising superconductors purified by indirect excitons

Much research effort has been devoted to interfacial or two-dimensional (2D) superconductors, but the underlying pairing mechanisms and pairing symmetries are highly controversial in most cases. Here we propose an innovative approach to probe the pairing symmetry of 2D superconductors, based on a van der Waals heterostructure consisting of a prototypical 2D Ising superconductor coupled with a 2D hole gas through an insulating spacer. We first show that, by tuning the Coulomb attraction between the superconducting and hole layers, the gap of the corresponding indirect exciton insulators is tuned as well, resulting in contrasting manifestations of the distinct superconducting channels with spin-singlet (s-, extended s-, and d-wave) and spin-triplet (p- and f-wave) pairings. Strikingly, we find that the application of in-plane magnetic fields can suppress all other channels while selecting the spin-triplet p-wave channel to be the pure superconducting state, thus providing an ideal and practical platform for realizing highly desirable topological superconductivity. Such an approach can also be readily extended to other types of superconducting systems, offering unprecedented opportunities to probe the microscopic mechanisms of unconventional superconductivity.

cond-mat.supr-con↗

arXiv2025

Variable Radiance Field for Real-World Category-Specific Reconstruction from Single Image

Reconstructing category-specific objects using Neural Radiance Field (NeRF) from a single image is a promising yet challenging task. Existing approaches predominantly rely on projection-based feature retrieval to associate 3D points in the radiance field with local image features from the reference image. However, this process is computationally expensive, dependent on known camera intrinsics, and susceptible to occlusions. To address these limitations, we propose Variable Radiance Field (VRF), a novel framework capable of efficiently reconstructing category-specific objects without requiring known camera intrinsics and demonstrating robustness against occlusions. First, we replace the local feature retrieval with global latent representations, generated through a single feed-forward pass, which improves efficiency and eliminates reliance on camera intrinsics. Second, to tackle coordinate inconsistencies inherent in real-world dataset, we define a canonical space by introducing a learnable, category-specific shape template and explicitly aligning each training object to this template using a learnable 3D transformation. This approach also reduces the complexity of geometry prediction to modeling deformations from the template to individual instances. Finally, we employ a hyper-network-based method for efficient NeRF creation and enhance the reconstruction performance through a contrastive learning-based pretraining strategy. Evaluations on the CO3D dataset demonstrate that VRF achieves state-of-the-art performance in both reconstruction quality and computational efficiency.

cs.CV↗

arXiv2025

APOLLO: SGD-like Memory, AdamW-level Performance

Large language models (LLMs) are notoriously memory-intensive during training, particularly with the popular AdamW optimizer. This memory burden necessitates using more or higher-end GPUs or reducing batch sizes, limiting training scalability and throughput. To address this, various memory-efficient optimizers have been proposed to reduce optimizer memory usage. However, they face critical challenges: (i) reliance on costly SVD operations; (ii) significant performance trade-offs compared to AdamW; and (iii) still substantial optimizer memory overhead to maintain competitive performance. In this work, we identify that AdamW's learning rate adaptation rule can be effectively coarsened as a structured learning rate update. Based on this insight, we propose Approximated Gradient Scaling for Memory-Efficient LLM Optimization (APOLLO), which approximates learning rate scaling using an auxiliary low-rank optimizer state based on pure random projection. This structured learning rate update rule makes APOLLO highly tolerant to further memory reductions while delivering comparable pre-training performance. Even its rank-1 variant, APOLLO-Mini, achieves superior pre-training performance compared to AdamW with SGD-level memory costs. Extensive experiments demonstrate that the APOLLO series performs on-par with or better than AdamW, while achieving greater memory savings by nearly eliminating the optimization states of AdamW. These savings provide significant system-level benefits: (1) Enhanced Throughput: 3x throughput on an 8xA100-80GB setup compared to AdamW by supporting 4x larger batch sizes. (2) Improved Model Scalability: Pre-training LLaMA-13B with naive DDP on A100-80GB GPUs without system-level optimizations. (3) Low-End GPU Friendly Pre-training: Pre-training LLaMA-7B on a single GPU using less than 12 GB of memory with weight quantization.

cs.LG↗

arXiv2025

Multi-Branch Collaborative Learning Network for Video Quality Assessment in Industrial Video Search

Video Quality Assessment (VQA) is vital for large-scale video retrieval systems, aimed at identifying quality issues to prioritize high-quality videos. In industrial systems, low-quality video characteristics fall into four categories: visual-related issues like mosaics and black boxes, textual issues from video titles and OCR content, and semantic issues like frame incoherence and frame-text mismatch from AI-generated videos. Despite their prevalence in industrial settings, these low-quality videos have been largely overlooked in academic research, posing a challenge for accurate identification. To address this, we introduce the Multi-Branch Collaborative Network (MBCN) tailored for industrial video retrieval systems. MBCN features four branches, each designed to tackle one of the aforementioned quality issues. After each branch independently scores videos, we aggregate these scores using a weighted approach and a squeeze-and-excitation mechanism to dynamically address quality issues across different scenarios. We implement point-wise and pair-wise optimization objectives to ensure score stability and reasonableness. Extensive offline and online experiments on a world-level video search engine demonstrate MBCN's effectiveness in identifying video quality issues, significantly enhancing the retrieval system's ranking performance. Detailed experimental analyses confirm the positive contribution of all four evaluation branches. Furthermore, MBCN significantly improves recognition accuracy for low-quality AI-generated videos compared to the baseline.

cs.CV↗

arXiv2025

Invertible Diffusion Models for Compressed Sensing

While deep neural networks (NN) significantly advance image compressed sensing (CS) by improving reconstruction quality, the necessity of training current CS NNs from scratch constrains their effectiveness and hampers rapid deployment. Although recent methods utilize pre-trained diffusion models for image reconstruction, they struggle with slow inference and restricted adaptability to CS. To tackle these challenges, this paper proposes Invertible Diffusion Models (IDM), a novel efficient, end-to-end diffusion-based CS method. IDM repurposes a large-scale diffusion sampling process as a reconstruction model, and fine-tunes it end-to-end to recover original images directly from CS measurements, moving beyond the traditional paradigm of one-step noise estimation learning. To enable such memory-intensive end-to-end fine-tuning, we propose a novel two-level invertible design to transform both (1) multi-step sampling process and (2) noise estimation U-Net in each step into invertible networks. As a result, most intermediate features are cleared during training to reduce up to 93.8% GPU memory. In addition, we develop a set of lightweight modules to inject measurements into noise estimator to further facilitate reconstruction. Experiments demonstrate that IDM outperforms existing state-of-the-art CS networks by up to 2.64dB in PSNR. Compared to the recent diffusion-based approach DDNM, our IDM achieves up to 10.09dB PSNR gain and 14.54 times faster inference. Code is available at https://github.com/Guaishou74851/IDM.

cs.CV↗

arXiv2025

Binding of the three-hadron $DD^{*}K$ system from the lattice effective field theory

We employ the nuclear lattice effective field theory (NLEFT), an efficient tool for nuclear ab initio calculations, to solve the asymmetric multihadron systems. We take the $DD^*K$ three-body system as an illustration to demonstrate the capability of the method. Here the two-body chiral interactions between $D$, $D^*$, and $K$ are regulated with a soft lattice regulator and calibrated with the binding energies of the $T_{cc}^+$, $D^{*}_{s0}(2317)$, and $D_{s1}(2460)$ molecular states. We then calculate the three-body binding energy using the NLEFT and analyze the systematic uncertainties due to the finite volume effects, the sliding cutoff, and the leading-order three-body forces. Even when the three-body interaction is repulsive (even as large as the infinite repulsive interaction), the three-body system has a bound state unambiguously with binding energy no larger than the $D_{s1}(2460)D$ threshold. To check the renormalization group invariance of our framework, we extract the first excited state. We find that when the ground state is fixed, the first excited states with various cutoffs coincide with each other when the cubic size goes larger. In addition, the standard angular momentum and parity projection technique is implemented for the quantum numbers of the ground and excited states. We find that both of them are $S$-wave states with quantum number $J^{P}=1^-$. Because the three-body state contains two charm quarks, it is easier to be detected in the Large Hadron Collider.

hep-ph↗

arXiv2025

EasySplat: View-Adaptive Learning makes 3D Gaussian Splatting Easy

3D Gaussian Splatting (3DGS) techniques have achieved satisfactory 3D scene representation. Despite their impressive performance, they confront challenges due to the limitation of structure-from-motion (SfM) methods on acquiring accurate scene initialization, or the inefficiency of densification strategy. In this paper, we introduce a novel framework EasySplat to achieve high-quality 3DGS modeling. Instead of using SfM for scene initialization, we employ a novel method to release the power of large-scale pointmap approaches. Specifically, we propose an efficient grouping strategy based on view similarity, and use robust pointmap priors to obtain high-quality point clouds and camera poses for 3D scene initialization. After obtaining a reliable scene structure, we propose a novel densification approach that adaptively splits Gaussian primitives based on the average shape of neighboring Gaussian ellipsoids, utilizing KNN scheme. In this way, the proposed method tackles the limitation on initialization and optimization, leading to an efficient and accurate 3DGS modeling. Extensive experiments demonstrate that EasySplat outperforms the current state-of-the-art (SOTA) in handling novel view synthesis.

cs.CV↗

arXiv2025

STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution

Image diffusion models have been adapted for real-world video super-resolution to tackle over-smoothing issues in GAN-based methods. However, these models struggle to maintain temporal consistency, as they are trained on static images, limiting their ability to capture temporal dynamics effectively. Integrating text-to-video (T2V) models into video super-resolution for improved temporal modeling is straightforward. However, two key challenges remain: artifacts introduced by complex degradations in real-world scenarios, and compromised fidelity due to the strong generative capacity of powerful T2V models (\textit{e.g.}, CogVideoX-5B). To enhance the spatio-temporal quality of restored videos, we introduce\textbf{~\name} (\textbf{S}patial-\textbf{T}emporal \textbf{A}ugmentation with T2V models for \textbf{R}eal-world video super-resolution), a novel approach that leverages T2V models for real-world video super-resolution, achieving realistic spatial details and robust temporal consistency. Specifically, we introduce a Local Information Enhancement Module (LIEM) before the global attention block to enrich local details and mitigate degradation artifacts. Moreover, we propose a Dynamic Frequency (DF) Loss to reinforce fidelity, guiding the model to focus on different frequency components across diffusion steps. Extensive experiments demonstrate\textbf{~\name}~outperforms state-of-the-art methods on both synthetic and real-world datasets.

cs.CV↗

arXiv2024

AddSR: Accelerating Diffusion-based Blind Super-Resolution with Adversarial Diffusion Distillation

Blind super-resolution methods based on stable diffusion showcase formidable generative capabilities in reconstructing clear high-resolution images with intricate details from low-resolution inputs. However, their practical applicability is often hampered by poor efficiency, stemming from the requirement of thousands or hundreds of sampling steps. Inspired by the efficient adversarial diffusion distillation (ADD), we design~\name~to address this issue by incorporating the ideas of both distillation and ControlNet. Specifically, we first propose a prediction-based self-refinement strategy to provide high-frequency information in the student model output with marginal additional time cost. Furthermore, we refine the training process by employing HR images, rather than LR images, to regulate the teacher model, providing a more robust constraint for distillation. Second, we introduce a timestep-adaptive ADD to address the perception-distortion imbalance problem introduced by original ADD. Extensive experiments demonstrate our~\name~generates better restoration results, while achieving faster speed than previous SD-based state-of-the-art models (e.g., $7$$\times$ faster than SeeSR).

cs.CV↗