arXiv subjects

Zeyu Zhang

Publications and source records attributed to Zeyu Zhang.

At least 199 records · Page 11Linked to original sources

arXiv2025

Deep Learning and Explainable AI: New Pathways to Genetic Insights

Deep learning-based AI models have been extensively applied in genomics, achieving remarkable success across diverse applications. As these models gain prominence, there exists an urgent need for interpretability methods to establish trustworthiness in model-driven decisions. For genetic researchers, interpretable insights derived from these models hold significant value in providing novel perspectives for understanding biological processes. Current interpretability analyses in genomics predominantly rely on intuition and experience rather than rigorous theoretical foundations. In this review, we systematically categorize interpretability methods into input-based and model-based approaches, while critically evaluating their limitations through concrete biological application scenarios. Furthermore, we establish theoretical underpinnings to elucidate the origins of these constraints through formal mathematical demonstrations, aiming to assist genetic researchers in better understanding and designing models in the future. Finally, we provide feasible suggestions for future research on interpretability in the field of genetics.

q-bio.GN↗

arXiv2025

DeepPlantCRE: A Transformer-CNN Hybrid Framework for Plant Gene Expression Modeling and Cross-Species Generalization

The investigation of plant transcriptional regulation constitutes a fundamental basis for crop breeding, where cis-regulatory elements (CREs), as the key factor determining gene expression, have become the focus of crop genetic improvement research. Deep learning techniques, leveraging their exceptional capacity for high-dimensional feature extraction and nonlinear regulatory relationship modeling, have been extensively employed in this field. However, current methodologies present notable limitations: single CNN-based architectures struggle to capture long-range regulatory interactions, while existing CNN-Transformer hybrid models demonstrate proneness to overfitting and inadequate generalization in cross-species prediction contexts. To address these challenges, this study proposes DeepPlantCRE, a deep-learning framework for plant gene expression prediction and CRE Extraction. The model employs a Transformer-CNN hybrid architecture that achieves enhanced Accuracy, AUC-ROC, and F1-score metrics over existing baselines (DeepCRE and PhytoExpr), with improved generalization performance and overfitting inhibiting. Cross-species validation experiments conducted on gene expression datasets from \textit{Gossypium}, \textit{Arabidopsis thaliana}, \textit{Solanum lycopersicum}, \textit{Sorghum bicolor}, and \textit{Arabidopsis thaliana} reveal that the model achieves peak prediction accuracy of 92.3\%, particularly excelling in complex genomic data analysis. Furthermore, interpretability investigations using DeepLIFT and Transcription Factor Motif Discovery from the importance scores algorithm (TF-MoDISco) demonstrate that the derived motifs from our model exhibit high concordance with known transcription factor binding sites (TFBSs) such as MYR2, TSO1 in JASPAR plant database, substantiating the potential of biological interpretability and practical agricultural application of DeepPlantCRE.

q-bio.GN↗

arXiv2025

CCL: Collaborative Curriculum Learning for Sparse-Reward Multi-Agent Reinforcement Learning via Co-evolutionary Task Evolution

Sparse reward environments pose significant challenges in reinforcement learning, especially within multi-agent systems (MAS) where feedback is delayed and shared across agents, leading to suboptimal learning. We propose Collaborative Multi-dimensional Course Learning (CCL), a novel curriculum learning framework that addresses this by (1) refining intermediate tasks for individual agents, (2) using a variational evolutionary algorithm to generate informative subtasks, and (3) co-evolving agents with their environment to enhance training stability. Experiments on five cooperative tasks in the MPE and Hide-and-Seek environments show that CCL outperforms existing methods in sparse reward settings.

cs.AI↗

arXiv2025

MemEngine: A Unified and Modular Library for Developing Advanced Memory of LLM-based Agents

Recently, large language model based (LLM-based) agents have been widely applied across various fields. As a critical part, their memory capabilities have captured significant interest from both industrial and academic communities. Despite the proposal of many advanced memory models in recent research, however, there remains a lack of unified implementations under a general framework. To address this issue, we develop a unified and modular library for developing advanced memory models of LLM-based agents, called MemEngine. Based on our framework, we implement abundant memory models from recent research works. Additionally, our library facilitates convenient and extensible memory development, and offers user-friendly and pluggable memory usage. For benefiting our community, we have made our project publicly available at https://github.com/nuster1128/MemEngine.

cs.AI↗

arXiv2025

Dual-channel Heterophilic Message Passing for Graph Fraud Detection

Fraudulent activities have significantly increased across various domains, such as e-commerce, online review platforms, and social networks, making fraud detection a critical task. Spatial Graph Neural Networks (GNNs) have been successfully applied to fraud detection tasks due to their strong inductive learning capabilities. However, existing spatial GNN-based methods often enhance the graph structure by excluding heterophilic neighbors during message passing to align with the homophilic bias of GNNs. Unfortunately, this approach can disrupt the original graph topology and increase uncertainty in predictions. To address these limitations, this paper proposes a novel framework, Dual-channel Heterophilic Message Passing (DHMP), for fraud detection. DHMP leverages a heterophily separation module to divide the graph into homophilic and heterophilic subgraphs, mitigating the low-pass inductive bias of traditional GNNs. It then applies shared weights to capture signals at different frequencies independently and incorporates a customized sampling strategy for training. This allows nodes to adaptively balance the contributions of various signals based on their labels. Extensive experiments on three real-world datasets demonstrate that DHMP outperforms existing methods, highlighting the importance of separating signals with different frequencies for improved fraud detection. The code is available at https://github.com/shaieesss/DHMP.

cs.LG↗

arXiv2025

MediAug: Exploring Visual Augmentation in Medical Imaging

Data augmentation is essential in medical imaging for improving classification accuracy, lesion detection, and organ segmentation under limited data conditions. However, two significant challenges remain. First, a pronounced domain gap between natural photographs and medical images can distort critical disease features. Second, augmentation studies in medical imaging are fragmented and limited to single tasks or architectures, leaving the benefits of advanced mix-based strategies unclear. To address these challenges, we propose a unified evaluation framework with six mix-based augmentation methods integrated with both convolutional and transformer backbones on brain tumour MRI and eye disease fundus datasets. Our contributions are threefold. (1) We introduce MediAug, a comprehensive and reproducible benchmark for advanced data augmentation in medical imaging. (2) We systematically evaluate MixUp, YOCO, CropMix, CutMix, AugMix, and SnapMix with ResNet-50 and ViT-B backbones. (3) We demonstrate through extensive experiments that MixUp yields the greatest improvement on the brain tumor classification task for ResNet-50 with 79.19% accuracy and SnapMix yields the greatest improvement for ViT-B with 99.44% accuracy, and that YOCO yields the greatest improvement on the eye disease classification task for ResNet-50 with 91.60% accuracy and CutMix yields the greatest improvement for ViT-B with 97.94% accuracy. Code will be available at https://github.com/AIGeeksGroup/MediAug.

cs.CV↗

arXiv2025

Generative Meta-Learning for Zero-Shot Relation Triplet Extraction

Zero-shot Relation Triplet Extraction (ZeroRTE) aims to extract relation triplets from texts containing unseen relation types. This capability benefits various downstream information retrieval (IR) tasks. The primary challenge lies in enabling models to generalize effectively to unseen relation categories. Existing approaches typically leverage the knowledge embedded in pre-trained language models to accomplish the generalization process. However, these methods focus solely on fitting the training data during training, without specifically improving the model's generalization performance, resulting in limited generalization capability. For this reason, we explore the integration of bi-level optimization (BLO) with pre-trained language models for learning generalized knowledge directly from the training data, and propose a generative meta-learning framework which exploits the `learning-to-learn' ability of meta-learning to boost the generalization capability of generative models. Specifically, we introduce a BLO approach that simultaneously addresses data fitting and generalization. This is achieved by constructing an upper-level loss to focus on generalization and a lower-level loss to ensure accurate data fitting. Building on this, we subsequently develop three generative meta-learning methods, each tailored to a distinct category of meta-learning. Extensive experimental results demonstrate that our framework performs well on the ZeroRTE task. Our code is available at https://github.com/leeworry/TGM-MetaLearning.

cs.CL↗

arXiv2025

TrustMap: Mapping Truthfulness Stance of Social Media Posts on Factual Claims for Geographical Analysis

Factual claims and misinformation circulate widely on social media and affect how people form opinions and make decisions. This paper presents a truthfulness stance map (TrustMap), an application that identifies and maps public stances toward factual claims across U.S. regions. Each social media post is classified as positive, negative, or neutral/no stance, based on whether it believes a factual claim is true or false, expresses uncertainty about the truthfulness, or does not explicitly take a position on the claim's truthfulness. The tool uses a retrieval-augmented model with fine-tuned language models for automatic stance classification. The stance classification results and social media posts are grouped by location to show how stance patterns vary geographically. TrustMap allows users to explore these patterns by claim and region and connects stance detection with geographical analysis to better understand public engagement with factual claims.

cs.SI↗

arXiv2025

MMCLIP: Cross-modal Attention Masked Modelling for Medical Language-Image Pre-Training

Vision-and-language pretraining (VLP) in the medical field utilizes contrastive learning on image-text pairs to achieve effective transfer across tasks. Yet, current VLP approaches with the masked modeling strategy face two challenges when applied to the medical domain. First, current models struggle to accurately reconstruct key pathological features due to the scarcity of medical data. Second, most methods only adopt either paired image-text or image-only data, failing to exploit the combination of both paired and unpaired data. To this end, this paper proposes the MMCLIP (Masked Medical Contrastive Language-Image Pre-Training) framework to enhance pathological learning and feature learning via unpaired data. First, we introduce the attention-masked image modeling (AttMIM) and entity-driven masked language modeling module (EntMLM), which learns to reconstruct pathological visual and textual tokens via multi-modal feature interaction, thus improving medical-enhanced features. The AttMIM module masks a portion of the image features that are highly responsive to textual features. This allows MMCLIP to improve the reconstruction of highly similar image data in medicine efficiency. Second, our MMCLIP capitalizes unpaired data to enhance multimodal learning by introducing disease-kind prompts. The experimental results show that MMCLIP achieves SOTA for zero-shot and fine-tuning classification performance on five datasets. Our code will be available at https://github.com/AIGeeksGroup/MMCLIP.

cs.CV↗

arXiv2025

KMM: Key Frame Mask Mamba for Extended Motion Generation

Human motion generation is a cut-edge area of research in generative computer vision, with promising applications in video creation, game development, and robotic manipulation. The recent Mamba architecture shows promising results in efficiently modeling long and complex sequences, yet two significant challenges remain: Firstly, directly applying Mamba to extended motion generation is ineffective, as the limited capacity of the implicit memory leads to memory decay. Secondly, Mamba struggles with multimodal fusion compared to Transformers, and lack alignment with textual queries, often confusing directions (left or right) or omitting parts of longer text queries. To address these challenges, our paper presents three key contributions: Firstly, we introduce KMM, a novel architecture featuring Key frame Masking Modeling, designed to enhance Mamba's focus on key actions in motion segments. This approach addresses the memory decay problem and represents a pioneering method in customizing strategic frame-level masking in SSMs. Additionally, we designed a contrastive learning paradigm for addressing the multimodal fusion problem in Mamba and improving the motion-text alignment. Finally, we conducted extensive experiments on the go-to dataset, BABEL, achieving state-of-the-art performance with a reduction of more than 57% in FID and 70% parameters compared to previous state-of-the-art methods. See project website: https://steve-zeyu-zhang.github.io/KMM

cs.CV↗

arXiv2025

Can GPT tell us why these images are synthesized? Empowering Multimodal Large Language Models for Forensics

The rapid development of generative AI facilitates content creation and makes image manipulation easier and more difficult to detect. While multimodal Large Language Models (LLMs) have encoded rich world knowledge, they are not inherently tailored for combating AI-generated Content (AIGC) and struggle to comprehend local forgery details. In this work, we investigate the application of multimodal LLMs in forgery detection. We propose a framework capable of evaluating image authenticity, localizing tampered regions, providing evidence, and tracing generation methods based on semantic tampering clues. Our method demonstrates that the potential of LLMs in forgery analysis can be effectively unlocked through meticulous prompt engineering and the application of few-shot learning techniques. We conduct qualitative and quantitative experiments and show that GPT4V can achieve an accuracy of 92.1% in Autosplice and 86.3% in LaMa, which is competitive with state-of-the-art AIGC detection methods. We further discuss the limitations of multimodal LLMs in such tasks and propose potential improvements.

cs.CV↗

arXiv2025

PuzzleBench: A Fully Dynamic Evaluation Framework for Large Multimodal Models on Puzzle Solving

Large Multimodal Models (LMMs) have demonstrated impressive capabilities across a wide range of multimodal tasks, achieving ever-increasing performance on various evaluation benchmarks. However, existing benchmarks are typically static and often overlap with pre-training datasets, leading to fixed complexity constraints and substantial data contamination issues. Meanwhile, manually annotated datasets are labor-intensive, time-consuming, and subject to human bias and inconsistency, leading to reliability and reproducibility issues. To address these problems, we propose a fully dynamic multimodal evaluation framework, named Open-ended Visual Puzzle Generation (OVPG), which aims to generate fresh, diverse, and verifiable evaluation data automatically in puzzle-solving tasks. Specifically, the OVPG pipeline consists of a raw material sampling module, a visual content generation module, and a puzzle rule design module, which ensures that each evaluation instance is primitive, highly randomized, and uniquely solvable, enabling continual adaptation to the evolving capabilities of LMMs. Built upon OVPG, we construct PuzzleBench, a dynamic and scalable benchmark comprising 11,840 VQA samples. It features six carefully designed puzzle tasks targeting three core LMM competencies, visual recognition, logical reasoning, and context understanding. PuzzleBench differs from static benchmarks that quickly become outdated. It enables ongoing dataset refreshing through OVPG and a rich set of open-ended puzzle designs, allowing seamless adaptation to the evolving capabilities of LMMs.

cs.CV↗

arXiv2025

TMCIR: Token Merge Benefits Composed Image Retrieval

Composed Image Retrieval (CIR) retrieves target images using a multi-modal query that combines a reference image with text describing desired modifications. The primary challenge is effectively fusing this visual and textual information. Current cross-modal feature fusion approaches for CIR exhibit an inherent bias in intention interpretation. These methods tend to disproportionately emphasize either the reference image features (visual-dominant fusion) or the textual modification intent (text-dominant fusion through image-to-text conversion). Such an imbalanced representation often fails to accurately capture and reflect the actual search intent of the user in the retrieval results. To address this challenge, we propose TMCIR, a novel framework that advances composed image retrieval through two key innovations: 1) Intent-Aware Cross-Modal Alignment. We first fine-tune CLIP encoders contrastively using intent-reflecting pseudo-target images, synthesized from reference images and textual descriptions via a diffusion model. This step enhances the encoder ability of text to capture nuanced intents in textual descriptions. 2) Adaptive Token Fusion. We further fine-tune all encoders contrastively by comparing adaptive token-fusion features with the target image. This mechanism dynamically balances visual and textual representations within the contrastive learning pipeline, optimizing the composed feature for retrieval. Extensive experiments on Fashion-IQ and CIRR datasets demonstrate that TMCIR significantly outperforms state-of-the-art methods, particularly in capturing nuanced user intent.

cs.CV↗

arXiv2025

Cumulative-Time Signal Temporal Logic

Signal Temporal Logic (STL) is a widely adopted specification language in cyber-physical systems for expressing critical temporal requirements, such as safety conditions and response time. However, STL's expressivity is not sufficient to capture the cumulative duration during which a property holds within an interval of time. To overcome this limitation, we introduce Cumulative-Time Signal Temporal Logic (CT-STL) that operates over discrete-time signals and extends STL with a new cumulative-time operator. This operator compares the sum of all time steps for which its nested formula is true with a threshold. We present both a qualitative and a quantitative (robustness) semantics for CT-STL and prove both their soundness and completeness properties. We provide an efficient online monitoring algorithm for both semantics. Finally, we show the applicability of CT-STL in two case studies: specifying and monitoring cumulative temporal requirements for a microgrid and an artificial pancreas.

cs.LO↗

arXiv2025

DiffuMural: Restoring Dunhuang Murals with Multi-scale Diffusion

Large-scale pre-trained diffusion models have produced excellent results in the field of conditional image generation. However, restoration of ancient murals, as an important downstream task in this field, poses significant challenges to diffusion model-based restoration methods due to its large defective area and scarce training samples. Conditional restoration tasks are more concerned with whether the restored part meets the aesthetic standards of mural restoration in terms of overall style and seam detail, and such metrics for evaluating heuristic image complements are lacking in current research. We therefore propose DiffuMural, a combined Multi-scale convergence and Collaborative Diffusion mechanism with ControlNet and cyclic consistency loss to optimise the matching between the generated images and the conditional control. DiffuMural demonstrates outstanding capabilities in mural restoration, leveraging training data from 23 large-scale Dunhuang murals that exhibit consistent visual aesthetics. The model excels in restoring intricate details, achieving a coherent overall appearance, and addressing the unique challenges posed by incomplete murals lacking factual grounding. Our evaluation framework incorporates four key metrics to quantitatively assess incomplete murals: factual accuracy, textural detail, contextual semantics, and holistic visual coherence. Furthermore, we integrate humanistic value assessments to ensure the restored murals retain their cultural and artistic significance. Extensive experiments validate that our method outperforms state-of-the-art (SOTA) approaches in both qualitative and quantitative metrics.

cs.CV↗

arXiv2025

3D CoCa: Contrastive Learners are 3D Captioners

3D captioning, which aims to describe the content of 3D scenes in natural language, remains highly challenging due to the inherent sparsity of point clouds and weak cross-modal alignment in existing methods. To address these challenges, we propose 3D CoCa, a novel unified framework that seamlessly combines contrastive vision-language learning with 3D caption generation in a single architecture. Our approach leverages a frozen CLIP vision-language backbone to provide rich semantic priors, a spatially-aware 3D scene encoder to capture geometric context, and a multi-modal decoder to generate descriptive captions. Unlike prior two-stage methods that rely on explicit object proposals, 3D CoCa jointly optimizes contrastive and captioning objectives in a shared feature space, eliminating the need for external detectors or handcrafted proposals. This joint training paradigm yields stronger spatial reasoning and richer semantic grounding by aligning 3D and textual representations. Extensive experiments on the ScanRefer and Nr3D benchmarks demonstrate that 3D CoCa significantly outperforms current state-of-the-arts by 10.2% and 5.76% in CIDEr at 0.5IoU, respectively. Code will be available at https://github.com/AIGeeksGroup/3DCoCa.

cs.CV↗

arXiv2025

Towards Explainable Partial-AIGC Image Quality Assessment

The rapid advancement of AI-driven visual generation technologies has catalyzed significant breakthroughs in image manipulation, particularly in achieving photorealistic localized editing effects on natural scene images (NSIs). Despite extensive research on image quality assessment (IQA) for AI-generated images (AGIs), most studies focus on fully AI-generated outputs (e.g., text-to-image generation), leaving the quality assessment of partial-AIGC images (PAIs)-images with localized AI-driven edits an almost unprecedented field. Motivated by this gap, we construct the first large-scale PAI dataset towards explainable partial-AIGC image quality assessment (EPAIQA), the EPAIQA-15K, which includes 15K images with localized AI manipulation in different regions and over 300K multi-dimensional human ratings. Based on this, we leverage large multi-modal models (LMMs) and propose a three-stage model training paradigm. This paradigm progressively trains the LMM for editing region grounding, quantitative quality scoring, and quality explanation. Finally, we develop the EPAIQA series models, which possess explainable quality feedback capabilities. Our work represents a pioneering effort in the perceptual IQA field for comprehensive PAI quality assessment.

cs.CV↗

arXiv2025

MedConv: Convolutions Beat Transformers on Long-Tailed Bone Density Prediction

Bone density prediction via CT scans to estimate T-scores is crucial, providing a more precise assessment of bone health compared to traditional methods like X-ray bone density tests, which lack spatial resolution and the ability to detect localized changes. However, CT-based prediction faces two major challenges: the high computational complexity of transformer-based architectures, which limits their deployment in portable and clinical settings, and the imbalanced, long-tailed distribution of real-world hospital data that skews predictions. To address these issues, we introduce MedConv, a convolutional model for bone density prediction that outperforms transformer models with lower computational demands. We also adapt Bal-CE loss and post-hoc logit adjustment to improve class balance. Extensive experiments on our AustinSpine dataset shows that our approach achieves up to 21% improvement in accuracy and 20% in ROC AUC over previous state-of-the-art methods.

cs.CV↗