Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks24 from public data
- MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment864
Multi-dimension Attention Network for no-reference Image Quality Assessment (MANIQA) is proposed to improve the performance on GAN-based distortion images and outperforms state-of-the-art methods on four standard datasets by a large margin.
- Attentions Help CNNs See Better: Attention-based Hybrid Image Quality Assessment Network137
An Attention-based Hybrid Image Quality Assessment Network (AHIQ) is proposed to deal with the challenge and get better performance on the GAN-based IQA task and outperforms the state-of-the-art methods on four standard IQA datasets.
- NTIRE 2022 Challenge on Perceptual Image Quality Assessment84
This paper reports on the NTIRE 2022 challenge on perceptual image quality assessment (IQA), held in conjunction with the New Trends in Image Restoration and Enhancement workshop (NTIRE) workshop at CVPR 2022 to address the emerging challenge of IQA by perceptual image processing algorithms.
- Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumption57
A generalized FR-IQA model, namely Adaptive Fidelity-Naturalness Evaluator (A-FINE), to accurately assess and adaptively combine the fidelity and naturalness of a test image and surpasses standard FR-IQA models on well-established IQA datasets and the authors' newly created DiffIQA.
- 38
- Qwen-Image-2.0 Technical Report34
Qwen-Image-2.0 is presented, an omni-capable image generation foundation model that unifies high-fidelity generation and precise image editing within a single framework and substantially outperforms previous Qwen-Image models in both generation and editing.
- 23
- Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis21
Diversity-preserved DMD is described, a role-separated distillation method inspired by the complementary roles of early and late denoising steps that preserves sample diversity while maintaining competitive visual quality under few-step sampling, providing a simple and stable alternative to other DMD variants.
- Qwen-Image-Bench: From Generation to Creation in Text-to-Image Evaluation19
Qwen-Image-Bench reliably distinguishes leading T2I models, achieving the greatest separation on the two application-driven dimensions of Real-world Fidelity and Creative Generation where existing benchmarks provide little insight, while also providing a trustworthy optimization signal for production-level T2I development.
- Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation13
This work proposes Qwen-Image-Agent, a unified agentic framework that integrates plan, reason, search, memory and feedback in a context-centric manner and shows that Qwen-Image-Agent outperforms strong baselines and achieves state-of-the-art performance.
- Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation12
Qwen-RobotWorld is introduced, a language-conditioned video world model for embodied intelligence that predicts physically grounded future visual trajectories from current observations across robotic manipulation, autonomous driving, indoor navigation, and human-to-robot transfer.
- A subtype specific probe for targeted magnetic resonance imaging of M2 tumor-associated macrophages in brain tumors10
An M2-targeted magnetic resonance imaging probe based on sub-5 nm ultrafine iron oxide nanoparticles (uIONP), featuring an anti-biofouling coating to prevent non-specific macrophage uptake and an M2-specific peptide ligand (M2pep) for active targeting of M2 TAMs is reported.
- 10
- Label-Free Chemically and Molecularly Selective Magnetic Resonance Imaging9
The chemical and biological bases of several label-free chemically and molecularly selective MRI and MRS methods that have been applied in imaging biomarker discovery, preclinical investigation, and image-guided clinical management are outlined.
- Qwen-Image-2.0-RL Technical Report7
A scalable GRPO-based RL training framework is developed, incorporating a hybrid classifier-free guidance (CFG) strategy to preserve pre-trained knowledge, prompt curation via intra-group reward range filtering, and per-category reward weight calibration.
- Long-Horizon Streaming Video Generation via Hybrid Attention with Decoupled Distillation7
This work introduces lightweight linear temporal attention to preserve long-range dependencies beyond the sliding window, and incorporates block-sparse attention into the local sliding window to reduce redundant computation within short-range modeling, reallocating computational capacity toward more critical dependencies.
- Hemodynamic property incorporated brain tumor segmentation by deep learning and density-based analysis of dynamic susceptibility contrast-enhanced magnetic resonance imaging (MRI)5
It is demonstrated that including hemodynamic properties of tissues from DSC MRI can improve existing structural or morphological feature-based tumor segmentation techniques with additional information on tumor biology and physiology.
- 4
- Qwen-Image-VAE-2.0 Technical Report2
This work presents Qwen-Image-VAE-2.0, a suite of high-compression Variational Autoencoders (VAEs) that achieve significant advances in both reconstruction fidelity and diffusability and proposes OmniDoc-TokenBench, a new benchmark comprising a diverse collection of real-world documents coupled with specialized OCR-based evaluation metrics.
- Small Intestine-Targeted Long-Acting Oral Insulin Formulation Based on Engineered Milk Protein Nanoparticles2
Oral casNP/insulin/C10 exhibited a blood sugar-lowering efficacy comparable to subcutaneously injected Insulin Aspart while extending the duration of action by approximately 6 h and preventing hypoglycemia in fasted mice, demonstrating that casNP/insulin/C10 is a promising oral insulin formulation for managing diabetes.
- Tool-IQA: Augmenting Image Quality Assessment with Simple Tools1
The proposed Tool-IQA equip VLMs with simple yet effective view tools: a Magnifier to inspect local details, and a Gamma Corrector to uncover visibility and hidden artifacts, and introduces a batch-aware training strategy to reward tool interactions that can yield positive contributions rather than simply encouraging usage.
- –
- An interpretable survival benefit analytics framework for optimizing cancer treatment decision-making–
By enabling survival benefit–supervised optimization and interpretable model construction, reported SurvS offers a powerful tool for personalized cancer treatment planning with the potential to improve treatment efficacy and reduce overtreatment.
- Investigating Prognostic Value of Dynamic Susceptibility Contrast Perfusion MRI-Derived Features for Glioblastoma Survival by Deep Learning–
Investigating hemodynamic information in dynamic susceptibility contrast perfusion-weighted imaging (DSC-PWI) reveals key features that can enhance GBM prognosis, supporting the importance of including hemodynamic and physiological imaging data in future GBM research.
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-15. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.