arXiv subjects

Fan Zhang

Publications and source records attributed to Fan Zhang.

At least 397 records · Page 22Linked to original sources

arXiv2025

Large Language Model Agent: A Survey on Methodology, Applications and Challenges

The era of intelligent agents is upon us, driven by revolutionary advancements in large language models. Large Language Model (LLM) agents, with goal-driven behaviors and dynamic adaptation capabilities, potentially represent a critical pathway toward artificial general intelligence. This survey systematically deconstructs LLM agent systems through a methodology-centered taxonomy, linking architectural foundations, collaboration mechanisms, and evolutionary pathways. We unify fragmented research threads by revealing fundamental connections between agent design principles and their emergent behaviors in complex environments. Our work provides a unified architectural perspective, examining how agents are constructed, how they collaborate, and how they evolve over time, while also addressing evaluation methodologies, tool applications, practical challenges, and diverse application domains. By surveying the latest developments in this rapidly evolving field, we offer researchers a structured taxonomy for understanding LLM agents and identify promising directions for future research. The collection is available at https://github.com/luo-junyu/Awesome-Agent-Papers.

cs.CL↗

arXiv2025

Superior electrochemical performance of zinc-ion batteries with fine-grained and textured zinc anode produced by high-pressure torsion

Zinc-ion batteries are promising alternatives to lithium-ion batteries, offering advantages in safety, cost, and environmental impact. However, their performance is often limited by the functioning of the zinc anode. This study employs severe plastic deformation via the high-pressure torsion (HPT) method to enhance the electrochemical performance of zinc anodes. HPT reduced the grain size from >1000 μm to 20 μm and introduced a (002) basal texture. The battery assembled with HPT-processed zinc demonstrated improved cycling stability, rate performance, and specific discharge capacity (>500 mAh/g at 0.5 A/g after 50 cycles), particularly at high current densities. This performance enhancement was attributed to grain-boundary and texture effects on improved ion transfer (confirmed by electrochemical impedance spectroscopy), fast redox reaction kinetics (confirmed by cyclic voltammetry), and reduced corrosion (confirmed by microscopy and potentiodynamic polarization test). This study highlights the potential of severely deformed materials with textured fine grains for advanced rechargeable battery technologies.

cond-mat.mtrl-sci↗

arXiv2025

Exploration of Multi-Element Collaborative Research and Application for Modern Power System Based on Generative Large Models

The transition to intelligent, low-carbon power systems necessitates advanced optimization strategies for managing renewable energy integration, energy storage, and carbon emissions. Generative Large Models (GLMs) provide a data-driven approach to enhancing forecasting, scheduling, and market operations by processing multi-source data and capturing complex system dynamics. This paper explores the role of GLMs in optimizing load-side management, energy storage utilization, and electricity carbon, with a focus on Smart Wide-area Hybrid Energy Systems with Storage and Carbon (SGLSC). By leveraging spatiotemporal modeling and reinforcement learning, GLMs enable dynamic energy scheduling, improve grid stability, enhance carbon trading strategies, and strengthen resilience against extreme weather events. The proposed framework highlights the transformative potential of GLMs in achieving efficient, adaptive, and low-carbon power system operations.

eess.SY↗

arXiv2025

GIViC: Generative Implicit Video Compression

While video compression based on implicit neural representations (INRs) has recently demonstrated great potential, existing INR-based video codecs still cannot achieve state-of-the-art (SOTA) performance compared to their conventional or autoencoder-based counterparts given the same coding configuration. In this context, we propose a Generative Implicit Video Compression framework, GIViC, aiming at advancing the performance limits of this type of coding methods. GIViC is inspired by the characteristics that INRs share with large language and diffusion models in exploiting long-term dependencies. Through the newly designed implicit diffusion process, GIViC performs diffusive sampling across coarse-to-fine spatiotemporal decompositions, gradually progressing from coarser-grained full-sequence diffusion to finer-grained per-token diffusion. A novel Hierarchical Gated Linear Attention-based transformer (HGLA), is also integrated into the framework, which dual-factorizes global dependency modeling along scale and sequential axes. The proposed GIViC model has been benchmarked against SOTA conventional and neural codecs using a Random Access (RA) configuration (YUV 4:2:0, GOPSize=32), and yields BD-rate savings of 15.94%, 22.46% and 8.52% over VVC VTM, DCVC-FM and NVRC, respectively. As far as we are aware, GIViC is the first INR-based video codec that outperforms VTM based on the RA coding configuration. The source code will be made available.

eess.IV↗

arXiv2025

"Becoming My Own Audience": How Dancers React to Avatars Unlike Themselves in Motion Capture-Supported Live Improvisational Performance

The use of motion capture in live dance performances has created an emerging discipline enabling dancers to play different avatars on the digital stage. Unlike classical workflows, avatars enable performers to act as different characters in customized narratives, but research has yet to address how movement, improvisation, and perception change when dancers act as avatars. We created five avatars representing differing genders, shapes, and body limitations, and invited 15 dancers to improvise with each in practice and performance settings. Results show that dancers used avatars to distance themselves from their own habitual movements, exploring new ways of moving through differing physical constraints. Dancers explored using gender-stereotyped movements like powerful or feminine actions, experimenting with gender identity. However, focusing on avatars can coincide with a lack of continuity in improvisation. This work shows how emerging practices with performance technology enable dancers to improvise with new constraints, stepping outside the classical stage.

cs.HC↗

arXiv2025

PMANet: Malicious URL detection via post-trained language model guided multi-level feature attention network

The proliferation of malicious URLs has made their detection crucial for enhancing network security. While pre-trained language models offer promise, existing methods struggle with domain-specific adaptability, character-level information, and local-global encoding integration. To address these challenges, we propose PMANet, a pre-trained Language Model-Guided multi-level feature attention network. PMANet employs a post-training process with three self-supervised objectives: masked language modeling, noisy language modeling, and domain discrimination, effectively capturing subword and character-level information. It also includes a hierarchical representation module and a dynamic layer-wise attention mechanism for extracting features from low to high levels. Additionally, spatial pyramid pooling integrates local and global features. Experiments on diverse scenarios, including small-scale data, class imbalance, and adversarial attacks, demonstrate PMANet's superiority over state-of-the-art models, achieving a 0.9941 AUC and correctly detecting all 20 malicious URLs in a case study. Code and data are available at https://github.com/Alixyvtte/Malicious-URL-Detection-PMANet.

cs.CR↗

arXiv2025

TransURL: Improving malicious URL detection with multi-layer Transformer encoding and multi-scale pyramid features

Machine learning progress is advancing the detection of malicious URLs. However, advanced Transformers applied to URLs face difficulties in extracting local information, character-level details, and structural relationships. To address these challenges, we propose a novel approach for malicious URL detection, named TransURL. This method is implemented by co-training the character-aware Transformer with three feature modules: Multi-Layer Encoding, Multi-Scale Feature Learning, and Spatial Pyramid Attention. This specialized Transformer enables TransURL to extract embeddings with character-level information from URL token sequences, with the three modules aiding the fusion of multi-layer Transformer encodings and the capture of multi-scale local details and structural relationships. The proposed method is evaluated across several challenging scenarios, including class imbalance learning, multi-classification, cross-dataset testing, and adversarial sample attacks. Experimental results demonstrate a significant improvement compared to previous methods. For instance, it achieved a peak F1-score improvement of 40% in class-imbalanced scenarios and surpassed the best baseline by 14.13% in accuracy for adversarial attack scenarios. Additionally, a case study demonstrated that our method accurately identified all 30 active malicious web pages, whereas two previous state-of-the-art methods missed 4 and 7 malicious web pages, respectively. The codes and data are available at: https://github.com/Vul-det/TransURL/.

cs.CR↗

arXiv2025

Vul-LMGNNs: Fusing language models and online-distilled graph neural networks for code vulnerability detection

Code Language Models (codeLMs) and Graph Neural Networks (GNNs) are widely used in code vulnerability detection. However, GNNs often rely on aggregating information from adjacent nodes, limiting structural information propagation across layers. While codeLMs can supplement GNNs with semantic information, existing integration methods underexplore their collaborative potential. To address these challenges, we propose Vul-LMGNNs, integrating pre-trained codeLMs with GNNs to enable cross-layer propagation of semantic and structural information. Vul-LMGNNs leverage Code Property Graphs (CPGs) to incorporate syntax, control flow, and data dependencies, using gated GNNs for structural extraction. An online knowledge distillation (KD) mechanism allows a student GNN to capture structural information from a trained counterpart via alternating training. Additionally, an "implicit-explicit" joint training framework leverages codeLMs to initialize embeddings and propagate code semantics. In the explicit phase, it performs late fusion via linear interpolation. Evaluations on real-world vulnerability datasets show Vul-LMGNNs outperform 17 state-of-the-art approaches. Source code is available at: https://github.com/Vul-LMGNN/vul-LMGNN.

cs.CR↗

arXiv2025

Isoperimetric Inequalities in Quantum Geometry

We reveal strong and weak inequalities relating two fundamental macroscopic quantum geometric quantities, the quantum distance and Berry phase, for closed paths in the Hilbert space of wavefunctions. We recount the role of quantum geometry in various quantum problems and show that our findings place new bounds on important physical quantities.

quant-ph↗

arXiv2025

Code-Driven Inductive Synthesis: Enhancing Reasoning Abilities of Large Language Models with Sequences

Large language models make remarkable progress in reasoning capabilities. Existing works focus mainly on deductive reasoning tasks (e.g., code and math), while another type of reasoning mode that better aligns with human learning, inductive reasoning, is not well studied. We attribute the reason to the fact that obtaining high-quality process supervision data is challenging for inductive reasoning. Towards this end, we novelly employ number sequences as the source of inductive reasoning data. We package sequences into algorithmic problems to find the general term of each sequence through a code solution. In this way, we can verify whether the code solution holds for any term in the current sequence, and inject case-based supervision signals by using code unit tests. We build a sequence synthetic data pipeline and form a training dataset CodeSeq. Experimental results show that the models tuned with CodeSeq improve on both code and comprehensive reasoning benchmarks.

cs.CL↗

arXiv2025

C2D-ISR: Optimizing Attention-based Image Super-resolution from Continuous to Discrete Scales

In recent years, attention mechanisms have been exploited in single image super-resolution (SISR), achieving impressive reconstruction results. However, these advancements are still limited by the reliance on simple training strategies and network architectures designed for discrete up-sampling scales, which hinder the model's ability to effectively capture information across multiple scales. To address these limitations, we propose a novel framework, \textbf{C2D-ISR}, for optimizing attention-based image super-resolution models from both performance and complexity perspectives. Our approach is based on a two-stage training methodology and a hierarchical encoding mechanism. The new training methodology involves continuous-scale training for discrete scale models, enabling the learning of inter-scale correlations and multi-scale feature representation. In addition, we generalize the hierarchical encoding mechanism with existing attention-based network structures, which can achieve improved spatial feature fusion, cross-scale information aggregation, and more importantly, much faster inference. We have evaluated the C2D-ISR framework based on three efficient attention-based backbones, SwinIR-L, SRFormer-L and MambaIRv2-L, and demonstrated significant improvements over the other existing optimization framework, HiT, in terms of super-resolution performance (up to 0.2dB) and computational complexity reduction (up to 11%). The source code will be made publicly available at www.github.com.

cs.CV↗

arXiv2025

EndoChat: Grounded Multimodal Large Language Model for Endoscopic Surgery

Recently, Multimodal Large Language Models (MLLMs) have demonstrated their immense potential in computer-aided diagnosis and decision-making. In the context of robotic-assisted surgery, MLLMs can serve as effective tools for surgical training and guidance. However, there is still a lack of MLLMs specialized for surgical scene understanding in clinical applications. In this work, we introduce EndoChat to address various dialogue paradigms and subtasks in surgical scene understanding that surgeons encounter. To train our EndoChat, we construct the Surg-396K dataset through a novel pipeline that systematically extracts surgical information and generates structured annotations based on collected large-scale endoscopic surgery datasets. Furthermore, we introduce a multi-scale visual token interaction mechanism and a visual contrast-based reasoning mechanism to enhance the model's representation learning and reasoning capabilities. Our model achieves state-of-the-art performance across five dialogue paradigms and eight surgical scene understanding tasks. Additionally, we conduct evaluations with professional surgeons, most of whom provide positive feedback on collaborating with EndoChat. Overall, these results demonstrate that our EndoChat has great potential to significantly advance training and automation in robotic-assisted surgery.

cs.CV↗

arXiv2025

GeoPix: Multi-Modal Large Language Model for Pixel-level Image Understanding in Remote Sensing

Multi-modal large language models (MLLMs) have achieved remarkable success in image- and region-level remote sensing (RS) image understanding tasks, such as image captioning, visual question answering, and visual grounding. However, existing RS MLLMs lack the pixel-level dialogue capability, which involves responding to user instructions with segmentation masks for specific instances. In this paper, we propose GeoPix, a RS MLLM that extends image understanding capabilities to the pixel level. This is achieved by equipping the MLLM with a mask predictor, which transforms visual features from the vision encoder into masks conditioned on the LLM's segmentation token embeddings. To facilitate the segmentation of multi-scale objects in RS imagery, a class-wise learnable memory module is integrated into the mask predictor to capture and store class-wise geo-context at the instance level across the entire dataset. In addition, to address the absence of large-scale datasets for training pixel-level RS MLLMs, we construct the GeoPixInstruct dataset, comprising 65,463 images and 140,412 instances, with each instance annotated with text descriptions, bounding boxes, and masks. Furthermore, we develop a two-stage training strategy to balance the distinct requirements of text generation and masks prediction in multi-modal multi-task optimization. Extensive experiments verify the effectiveness and superiority of GeoPix in pixel-level segmentation tasks, while also maintaining competitive performance in image- and region-level benchmarks.

cs.CV↗

arXiv2025

Dialogue Injection Attack: Jailbreaking LLMs through Context Manipulation

Large language models (LLMs) have demonstrated significant utility in a wide range of applications; however, their deployment is plagued by security vulnerabilities, notably jailbreak attacks. These attacks manipulate LLMs to generate harmful or unethical content by crafting adversarial prompts. While much of the current research on jailbreak attacks has focused on single-turn interactions, it has largely overlooked the impact of historical dialogues on model behavior. In this paper, we introduce a novel jailbreak paradigm, Dialogue Injection Attack (DIA), which leverages the dialogue history to enhance the success rates of such attacks. DIA operates in a black-box setting, requiring only access to the chat API or knowledge of the LLM's chat template. We propose two methods for constructing adversarial historical dialogues: one adapts gray-box prefilling attacks, and the other exploits deferred responses. Our experiments show that DIA achieves state-of-the-art attack success rates on recent LLMs, including Llama-3.1 and GPT-4o. Additionally, we demonstrate that DIA can bypass 5 different defense mechanisms, highlighting its robustness and effectiveness.

cs.CL↗

arXiv2025

$Prooφ$: A ZKP Market Mechanism

Zero-knowledge proofs (ZKPs) are computationally demanding to generate. Their importance for applications like ZK-Rollups has prompted some to outsource ZKP generation to a market of specialized provers. However, existing market designs either do not fit the ZKP setting or lack formal description and analysis. In this work, we propose a formal ZKP market model that captures the interactions between users submitting ZKP tasks and provers competing to generate proofs. Building on this model, we introduce $Prooφ$, an auction-based ZKP market mechanism. We prove that $Prooφ$ is incentive compatible for users and provers, and budget balanced. We augment $Prooφ$ with system-level designs to address the practical challenges of our setting, such as Sybil attacks, misreporting of prover capacity, and collusion. We analyze our system-level designs and show how they can mitigate the various security concerns.

cs.GT↗

arXiv2025

MultiCo3D: Multi-Label Voxel Contrast for One-Shot Incremental Segmentation of 3D Neuroimages

3D neuroimages provide a comprehensive view of brain structure and function, aiding in precise localization and functional connectivity analysis. Segmentation of white matter (WM) tracts using 3D neuroimages is vital for understanding the brain's structural connectivity in both healthy and diseased states. One-shot Class Incremental Semantic Segmentation (OCIS) refers to effectively segmenting new (novel) classes using only a single sample while retaining knowledge of old (base) classes without forgetting. Voxel-contrastive OCIS methods adjust the feature space to alleviate the feature overlap problem between the base and novel classes. However, since WM tract segmentation is a multi-label segmentation task, existing single-label voxel contrastive-based methods may cause inherent contradictions. To address this, we propose a new multi-label voxel contrast framework called MultiCo3D for one-shot class incremental tract segmentation. Our method utilizes uncertainty distillation to preserve base tract segmentation knowledge while adjusting the feature space with multi-label voxel contrast to alleviate feature overlap when learning novel tracts and dynamically weighting multi losses to balance overall loss. We compare our method against several state-of-the-art (SOTA) approaches. The experimental results show that our method significantly enhances one-shot class incremental tract segmentation accuracy across five different experimental setups on HCP and Preto datasets.

cs.CV↗

arXiv2025

TractCloud-FOV: Deep Learning-based Robust Tractography Parcellation in Diffusion MRI with Incomplete Field of View

Tractography parcellation classifies streamlines reconstructed from diffusion MRI into anatomically defined fiber tracts for clinical and research applications. However, clinical scans often have incomplete fields of view (FOV) where brain regions are partially imaged, leading to partial or truncated fiber tracts. To address this challenge, we introduce TractCloud-FOV, a deep learning framework that robustly parcellates tractography under conditions of incomplete FOV. We propose a novel training strategy, FOV-Cut Augmentation (FOV-CA), in which we synthetically cut tractograms to simulate a spectrum of real-world inferior FOV cutoff scenarios. This data augmentation approach enriches the training set with realistic truncated streamlines, enabling the model to achieve superior generalization. We evaluate the proposed TractCloud-FOV on both synthetically cut tractography and two real-life datasets with incomplete FOV. TractCloud-FOV significantly outperforms several state-of-the-art methods on all testing datasets in terms of streamline classification accuracy, generalization ability, tract anatomical depiction, and computational efficiency. Overall, TractCloud-FOV achieves efficient and consistent tractography parcellation in diffusion MRI with incomplete FOV.

cs.CV↗

arXiv2025

DDCSR: A Novel End-to-End Deep Learning Framework for Cortical Surface Reconstruction from Diffusion MRI

Diffusion MRI (dMRI) plays a crucial role in studying brain white matter connectivity. Cortical surface reconstruction (CSR), including the inner whiter matter (WM) and outer pial surfaces, is one of the key tasks in dMRI analyses such as fiber tractography and multimodal MRI analysis. Existing CSR methods rely on anatomical T1-weighted data and map them into the dMRI space through inter-modality registration. However, due to the low resolution and image distortions of dMRI data, inter-modality registration faces significant challenges. This work proposes a novel end-to-end learning framework, DDCSR, which for the first time enables CSR directly from dMRI data. DDCSR consists of two major components, including: (1) an implicit learning module to predict a voxel-wise intermediate surface representation, and (2) an explicit learning module to predict the 3D mesh surfaces. Compared to several baseline and advanced CSR methods, we show that the proposed DDCSR can largely increase both accuracy and efficiency. Furthermore, we demonstrate a high generalization ability of DDCSR to data from different sources, despite the differences in dMRI acquisitions and populations.

q-bio.TO↗