arXiv subjects

Jian Zhang

Publications and source records attributed to Jian Zhang.

At least 253 records · Page 14Linked to original sources

arXiv2025

AssetDropper: Asset Extraction via Diffusion Models with Reward-Driven Optimization

Recent research on generative models has primarily focused on creating product-ready visual outputs; however, designers often favor access to standardized asset libraries, a domain that has yet to be significantly enhanced by generative capabilities. Although open-world scenes provide ample raw materials for designers, efficiently extracting high-quality, standardized assets remains a challenge. To address this, we introduce AssetDropper, the first framework designed to extract assets from reference images, providing artists with an open-world asset palette. Our model adeptly extracts a front view of selected subjects from input images, effectively handling complex scenarios such as perspective distortion and subject occlusion. We establish a synthetic dataset of more than 200,000 image-subject pairs and a real-world benchmark with thousands more for evaluation, facilitating the exploration of future research in downstream tasks. Furthermore, to ensure precise asset extraction that aligns well with the image prompts, we employ a pre-trained reward model to fulfill a closed-loop with feedback. We design the reward model to perform an inverse task that pastes the extracted assets back into the reference sources, which assists training with additional consistency and mitigates hallucination. Extensive experiments show that, with the aid of reward-driven optimization, AssetDropper achieves the state-of-the-art results in asset extraction. Project page: AssetDropper.github.io.

cs.CV↗

arXiv2025

Efficient Universal Goal Hijacking with Semantics-guided Prompt Organization

Universal goal hijacking is a kind of prompt injection attack that forces LLMs to return a target malicious response for arbitrary normal user prompts. The previous methods achieve high attack performance while being too cumbersome and time-consuming. Also, they have concentrated solely on optimization algorithms, overlooking the crucial role of the prompt. To this end, we propose a method called POUGH that incorporates an efficient optimization algorithm and two semantics-guided prompt organization strategies. Specifically, our method starts with a sampling strategy to select representative prompts from a candidate pool, followed by a ranking strategy that prioritizes them. Given the sequentially ranked prompts, our method employs an iterative optimization algorithm to generate a fixed suffix that can concatenate to arbitrary user prompts for universal goal hijacking. Experiments conducted on four popular LLMs and ten types of target responses verified the effectiveness.

cs.CL↗

arXiv2025

Unleashing the Power of Intermediate Domains for Mixed Domain Semi-Supervised Medical Image Segmentation

Both limited annotation and domain shift are prevalent challenges in medical image segmentation. Traditional semi-supervised segmentation and unsupervised domain adaptation methods address one of these issues separately. However, the coexistence of limited annotation and domain shift is quite common, which motivates us to introduce a novel and challenging scenario: Mixed Domain Semi-supervised medical image Segmentation (MiDSS), where limited labeled data from a single domain and a large amount of unlabeled data from multiple domains. To tackle this issue, we propose the UST-RUN framework, which fully leverages intermediate domain information to facilitate knowledge transfer. We employ Unified Copy-paste (UCP) to construct intermediate domains, and propose a Symmetric GuiDance training strategy (SymGD) to supervise unlabeled data by merging pseudo-labels from intermediate samples. Subsequently, we introduce a Training Process aware Random Amplitude MixUp (TP-RAM) to progressively incorporate style-transition components into intermediate samples. To generate more diverse intermediate samples, we further select reliable samples with high-quality pseudo-labels, which are then mixed with other unlabeled data. Additionally, we generate sophisticated intermediate samples with high-quality pseudo-labels for unreliable samples, ensuring effective knowledge transfer for them. Extensive experiments on four public datasets demonstrate the superiority of UST-RUN. Notably, UST-RUN achieves a 12.94% improvement in Dice score on the Prostate dataset. Our code is available at https://github.com/MQinghe/UST-RUN

cs.CV↗

arXiv2025

MIND-Edit: MLLM Insight-Driven Editing via Language-Vision Projection

Recent advances in AI-generated content (AIGC) have significantly accelerated image editing techniques, driving increasing demand for diverse and fine-grained edits. Despite these advances, existing image editing methods still face challenges in achieving high precision and semantic accuracy in complex scenarios. Recent studies address this issue by incorporating multimodal large language models (MLLMs) into image editing pipelines. However, current MLLM-based methods mainly rely on interpreting textual instructions, leaving the intrinsic visual understanding of large models largely unexplored, thus resulting in insufficient alignment between textual semantics and visual outcomes. To overcome these limitations, we propose MIND-Edit, an end-to-end image-editing framework integrating pretrained diffusion model with MLLM. MIND-Edit introduces two complementary strategies: (1) a text instruction optimization strategy that clarifies ambiguous user instructions based on semantic reasoning from the MLLM, and (2) an MLLM insight-driven editing strategy that explicitly leverages the intrinsic visual understanding capability of the MLLM to infer editing intent and guide the diffusion process via generated visual embeddings. Furthermore, we propose a joint training approach to effectively integrate both strategies, allowing them to reinforce each other for more accurate instruction interpretation and visually coherent edits aligned with user intent. Extensive experiments demonstrate that MIND-Edit outperforms state-of-the-art image editing methods in both quantitative metrics and visual quality, particularly under complex and challenging scenarios.

cs.CV↗

arXiv2025

Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement Learning

Graphical User Interface (GUI) agents have made substantial strides in understanding and executing user instructions across diverse platforms. Yet, grounding these instructions to precise interface elements remains challenging, especially in complex, high-resolution, professional environments. Traditional supervised finetuning (SFT) methods often require large volumes of diverse data and exhibit weak generalization. To overcome these limitations, we introduce a reinforcement learning (RL) based framework that incorporates three core strategies: (1) seed data curation to ensure high quality training samples, (2) a dense policy gradient that provides continuous feedback based on prediction accuracy, and (3) a self evolutionary reinforcement finetuning mechanism that iteratively refines the model using attention maps. With only 3k training samples, our 7B-parameter model achieves state-of-the-art results among similarly sized models on three grounding benchmarks. Notably, it attains 47.3\% accuracy on the ScreenSpot-Pro dataset, outperforming much larger models, such as UI-TARS-72B, by a margin of 24.2\%. These findings underscore the effectiveness of RL-based approaches in enhancing GUI agent performance, particularly in high-resolution, complex environments.

cs.AI↗

arXiv2025

D3C2-Net: Dual-Domain Deep Convolutional Coding Network for Compressive Sensing

By mapping iterative optimization algorithms into neural networks (NNs), deep unfolding networks (DUNs) exhibit well-defined and interpretable structures and achieve remarkable success in the field of compressive sensing (CS). However, most existing DUNs solely rely on the image-domain unfolding, which restricts the information transmission capacity and reconstruction flexibility, leading to their loss of image details and unsatisfactory performance. To overcome these limitations, this paper develops a dual-domain optimization framework that combines the priors of (1) image- and (2) convolutional-coding-domains and offers generality to CS and other inverse imaging tasks. By converting this optimization framework into deep NN structures, we present a Dual-Domain Deep Convolutional Coding Network (D3C2-Net), which enjoys the ability to efficiently transmit high-capacity self-adaptive convolutional features across all its unfolded stages. Our theoretical analyses and experiments on simulated and real captured data, covering 2D and 3D natural, medical, and scientific signals, demonstrate the effectiveness, practicality, superior performance, and generalization ability of our method over other competing approaches and its significant potential in achieving a balance among accuracy, complexity, and interpretability. Code is available at https://github.com/lwq20020127/D3C2-Net.

cs.CV↗

arXiv2025

Q-Insight: Understanding Image Quality via Visual Reinforcement Learning

Image quality assessment (IQA) focuses on the perceptual visual quality of images, playing a crucial role in downstream tasks such as image reconstruction, compression, and generation. The rapid advancement of multi-modal large language models (MLLMs) has significantly broadened the scope of IQA, moving toward comprehensive image quality understanding that incorporates content analysis, degradation perception, and comparison reasoning beyond mere numerical scoring. Previous MLLM-based methods typically either generate numerical scores lacking interpretability or heavily rely on supervised fine-tuning (SFT) using large-scale annotated datasets to provide descriptive assessments, limiting their flexibility and applicability. In this paper, we propose Q-Insight, a reinforcement learning-based model built upon group relative policy optimization (GRPO), which demonstrates strong visual reasoning capability for image quality understanding while requiring only a limited amount of rating scores and degradation labels. By jointly optimizing score regression and degradation perception tasks with carefully designed reward functions, our approach effectively exploits their mutual benefits for enhanced performance. Extensive experiments demonstrate that Q-Insight substantially outperforms existing state-of-the-art methods in both score regression and degradation perception tasks, while exhibiting impressive zero-shot generalization to comparison reasoning tasks. Code will be available at https://github.com/lwq20020127/Q-Insight.

cs.CV↗

arXiv2025

Teach2Eval: An Indirect Evaluation Method for LLM by Judging How It Teaches

Recent progress in large language models (LLMs) has outpaced the development of effective evaluation methods. Traditional benchmarks rely on task-specific metrics and static datasets, which often suffer from fairness issues, limited scalability, and contamination risks. In this paper, we introduce Teach2Eval, an indirect evaluation framework inspired by the Feynman Technique. Instead of directly testing LLMs on predefined tasks, our method evaluates a model's multiple abilities to teach weaker student models to perform tasks effectively. By converting open-ended tasks into standardized multiple-choice questions (MCQs) through teacher-generated feedback, Teach2Eval enables scalable, automated, and multi-dimensional assessment. Our approach not only avoids data leakage and memorization but also captures a broad range of cognitive abilities that are orthogonal to current benchmarks. Experimental results across 26 leading LLMs show strong alignment with existing human and model-based dynamic rankings, while offering additional interpretability for training guidance.

cs.CL↗

arXiv2025

An Empirical Study: MEMS as a Static Performance Metric

Static performance estimation is essential during compile-time analysis, yet traditional runtime-based methods are costly and platform-dependent. We investigate mems, the number of memory accesses, as a static and architecture-independent performance metric. We develop a Clang-based automated instrumentation tool that rewrites source code to insert path tracing and \textit{mems} counting logic. This allows us to evaluate mems-based performance estimation across ten classical algorithm programs. Experimental results show that within the same program, execution paths with higher mems values consistently exhibit longer runtime. However, this correlation weakens between different programs, suggesting that mems is best suited for comparing performance of different execution paths in a program.

cs.SE↗

arXiv2025

Exploring Gen-AI applications in building research and industry: A review

This paper investigates the transformative potential of Generative AI (Gen-AI) technologies, particularly large language models, within the building industry. By leveraging these advanced AI tools, the study explores their application across key areas such as automated compliance checking and building design assistance. The research highlights how Gen-AI can automate labor-intensive processes, significantly improving efficiency and reducing costs in building practices. The paper first discusses the two widely applied fundamental models-Transformer and Diffusion model-and summarizes current pathways for accessing Gen-AI models and the most common techniques for customizing them. It then explores applications for text generation, such as compliance checking, control support, data mining, and building simulation input file editing. Additionally, it examines image generation, including direct generation through diffusion models and indirect generation through language model-supported template creation based on existing Computer-Aided Design or other design tools with rendering. The paper concludes with a comprehensive analysis of the current capabilities of Gen-AI in the building industry, outlining future directions for research and development, with the goal of paving the way for smarter, more effective, and responsive design, construction, and operational practices.

cs.AI↗

arXiv2025

JustinANN: Realistic Test Generation for Java Programs Driven by Annotations

Automated test case generation is important. However, the automatically generated test input does not always make sense, and the automated assertion is difficult to validate against the program under test. In this paper, we propose JustinANN, a flexible and scalable tool to generate test cases for Java programs, providing realistic test inputs and assertions. We have observed that, in practice, Java programs contain a large number of annotations from programs, which can be considered as part of the user specification. We design a systematic annotation set with 7 kinds of annotations and 4 combination rules based on them to modify complex Java objects. Annotations that modify the fields or return variables of methods can be used to generate assertions that represent the true intent of the program, and the ones that modify the input parameters can be used to generate test inputs that match the real business requirement. We have conducted experiments to evaluate the approach on open source Java programs. The results show that the annotations and their combinations designed in this paper are compatible with existing annotations; our approach is easier to generate test data in, on and outside the boundaries of the requirement domain; and it also helps to find program defects.

cs.SE↗

arXiv2025

OSMamba: Omnidirectional Spectral Mamba with Dual-Domain Prior Generator for Exposure Correction

Exposure correction is a fundamental problem in computer vision and image processing. Recently, frequency domain-based methods have achieved impressive improvement, yet they still struggle with complex real-world scenarios under extreme exposure conditions. This is due to the local convolutional receptive fields failing to model long-range dependencies in the spectrum, and the non-generative learning paradigm being inadequate for retrieving lost details from severely degraded regions. In this paper, we propose Omnidirectional Spectral Mamba (OSMamba), a novel exposure correction network that incorporates the advantages of state space models and generative diffusion models to address these limitations. Specifically, OSMamba introduces an omnidirectional spectral scanning mechanism that adapts Mamba to the frequency domain to capture comprehensive long-range dependencies in both the amplitude and phase spectra of deep image features, hence enhancing illumination correction and structure recovery. Furthermore, we develop a dual-domain prior generator that learns from well-exposed images to generate a degradation-free diffusion prior containing correct information about severely under- and over-exposed regions for better detail restoration. Extensive experiments on multiple-exposure and mixed-exposure datasets demonstrate that the proposed OSMamba achieves state-of-the-art performance both quantitatively and qualitatively.

eess.IV↗

arXiv2025

All-fiber highly efficient delivery of 2 kW laser over 2.45 km hollow-core fiber

Anti-resonant hollow-core fibers (AR-HCFs) have emerged as an important medium for high-power laser delivery due to their low optical nonlinearity and high damage threshold. However, current delivery systems of high-power laser based on AR-HCFs mainly rely on free-space optical components, which limits long-term stability in dynamic environments. Here, we report an all-fiber delivery of 2 kW laser with 85.3% transmission efficiency over 2.45 km, using a self-fabricated AR-HCF with a record low transmission loss of 0.175 dB/km at 1080 nm. This represents a nearly 500-fold improvement in the power-distance product compared to reported all-fiber AR-HCF-based laser transmission systems, achieving a record transmission distance for high-power laser delivery. Notably, we observed the phenomenon of stimulated Raman scattering amplified within the silica nested tubes in AR-HCF for the first time. By effectively suppressing the Raman noise from the laser source, we achieve an all-fiber laser delivery without stimulated Raman scattering of silica glass. This work marks a significant breakthrough in multi-kilometer and multi-kilowatt power delivery that is potentially useful for industrial manufacturing, nuclear decommissioning, laser drilling of oil, particle acceleration and so on.

physics.optics↗

arXiv2025

Quantum Littlewood correspondences

In the 1940s Littlewood formulated three fundamental correspondences for the immanants and Schur symmetric functions on the general linear group, which establish deep connections between representation theory of the symmetric group and the general linear group parallel to the Schur-Weyl duality. In this paper, we introduce the notion of quantum immanants in the quantum coordinate algebra using primitive idempotents of the Hecke algebra. By employing $R$-matrix techniques, we establish the quantum analog of Littlewood correspondences between quantum immanants and Schur functions for the quantum coordinate algebra. In the setting of the Schur-Weyl-Jimbo duality, we construct an exact correspondence between the Gelfand-Tsetlin bases of the irreducible representations of the quantum enveloping algebra $U_q(\mathfrak{gl}(n))$ and Young's orthonormal basis of an irreducible representation of the Hecke algebra $\mathcal H_m$. This isomorphism leads to our trace formula for the quantum immanants, which settled the generalization problem of $q$-analog of Kostant's formular for $λ$-immanants. As applications, we also derive general $q$-Littlewood-Merris-Watkins identities and $q$-Goulden-Jackson identities as special cases of the quantum Littlewood correspondence III.

math.RT↗

arXiv2025

Mamba-Sea: A Mamba-based Framework with Global-to-Local Sequence Augmentation for Generalizable Medical Image Segmentation

To segment medical images with distribution shifts, domain generalization (DG) has emerged as a promising setting to train models on source domains that can generalize to unseen target domains. Existing DG methods are mainly based on CNN or ViT architectures. Recently, advanced state space models, represented by Mamba, have shown promising results in various supervised medical image segmentation. The success of Mamba is primarily owing to its ability to capture long-range dependencies while keeping linear complexity with input sequence length, making it a promising alternative to CNNs and ViTs. Inspired by the success, in the paper, we explore the potential of the Mamba architecture to address distribution shifts in DG for medical image segmentation. Specifically, we propose a novel Mamba-based framework, Mamba-Sea, incorporating global-to-local sequence augmentation to improve the model's generalizability under domain shift issues. Our Mamba-Sea introduces a global augmentation mechanism designed to simulate potential variations in appearance across different sites, aiming to suppress the model's learning of domain-specific information. At the local level, we propose a sequence-wise augmentation along input sequences, which perturbs the style of tokens within random continuous sub-sequences by modeling and resampling style statistics associated with domain shifts. To our best knowledge, Mamba-Sea is the first work to explore the generalization of Mamba for medical image segmentation, providing an advanced and promising Mamba-based architecture with strong robustness to domain shifts. Remarkably, our proposed method is the first to surpass a Dice coefficient of 90% on the Prostate dataset, which exceeds previous SOTA of 88.61%. The code is available at https://github.com/orange-czh/Mamba-Sea.

cs.CV↗

arXiv2025

Deciphering the unique dynamic activation pathway in a G protein-coupled receptor enables unveiling biased signaling and identifying cryptic allosteric sites in conformational intermediates

Neurotensin receptor 1 (NTSR1), a member of the Class A G protein-coupled receptor superfamily, plays an important role in modulating dopaminergic neuronal activity and eliciting opioid-independent analgesia. Recent studies suggest that promoting \{beta}-arrestin-biased signaling in NTSR1 may diminish drugs of abuse, such as psychostimulants, thereby offering a potential avenue for treating human addiction-related disorders. In this study, we utilized a novel computational and experimental approach that combined nudged elastic band-based molecular dynamics simulations, Markov state models, temporal communication network analysis, site-directed mutagenesis, and conformational biosensors, to explore the intricate mechanisms underlying NTSR1 activation and biased signaling. Our study reveals a dynamic stepwise transition mechanism and activated transmission network associated with NTSR1 activation. It also yields valuable insights into the complex interplay between the unique polar network, non-conserved ion locks, and aromatic clusters in NTSR1 signaling. Moreover, we identified a cryptic allosteric site located in the intracellular region of the receptor that exists in an intermediate state within the activation pathway. Collectively, these findings contribute to a more profound understanding of NTSR1 activation and biased signaling at the atomic level, thereby providing a potential strategy for the development of NTSR1 allosteric modulators in the realm of G protein-coupled receptor biology, biophysics, and medicine.

q-bio.BM↗

arXiv2025

EIoU-EMC: A Novel Loss for Domain-specific Nested Entity Recognition

In recent years, research has mainly focused on the general NER task. There still have some challenges with nested NER task in the specific domains. Specifically, the scenarios of low resource and class imbalance impede the wide application for biomedical and industrial domains. In this study, we design a novel loss EIoU-EMC, by enhancing the implement of Intersection over Union loss and Multiclass loss. Our proposed method specially leverages the information of entity boundary and entity classification, thereby enhancing the model's capacity to learn from a limited number of data samples. To validate the performance of this innovative method in enhancing NER task, we conducted experiments on three distinct biomedical NER datasets and one dataset constructed by ourselves from industrial complex equipment maintenance documents. Comparing to strong baselines, our method demonstrates the competitive performance across all datasets. During the experimental analysis, our proposed method exhibits significant advancements in entity boundary recognition and entity classification. Our code are available here.

cs.CL↗

arXiv2025

InstanceGaussian: Appearance-Semantic Joint Gaussian Representation for 3D Instance-Level Perception

3D scene understanding has become an essential area of research with applications in autonomous driving, robotics, and augmented reality. Recently, 3D Gaussian Splatting (3DGS) has emerged as a powerful approach, combining explicit modeling with neural adaptability to provide efficient and detailed scene representations. However, three major challenges remain in leveraging 3DGS for scene understanding: 1) an imbalance between appearance and semantics, where dense Gaussian usage for fine-grained texture modeling does not align with the minimal requirements for semantic attributes; 2) inconsistencies between appearance and semantics, as purely appearance-based Gaussians often misrepresent object boundaries; and 3) reliance on top-down instance segmentation methods, which struggle with uneven category distributions, leading to over- or under-segmentation. In this work, we propose InstanceGaussian, a method that jointly learns appearance and semantic features while adaptively aggregating instances. Our contributions include: i) a novel Semantic-Scaffold-GS representation balancing appearance and semantics to improve feature representations and boundary delineation; ii) a progressive appearance-semantic joint training strategy to enhance stability and segmentation accuracy; and iii) a bottom-up, category-agnostic instance aggregation approach that addresses segmentation challenges through farthest point sampling and connected component analysis. Our approach achieves state-of-the-art performance in category-agnostic, open-vocabulary 3D point-level segmentation, highlighting the effectiveness of the proposed representation and training strategies. Project page: https://lhj-git.github.io/InstanceGaussian/

cs.CV↗