Yuan Yan Tang
YOU?
Author Swipe
View article: AlphaOPT: Formulating Optimization Programs with Self-Improving LLM Experience Library
AlphaOPT: Formulating Optimization Programs with Self-Improving LLM Experience Library Open
Optimization modeling enables critical decisions across industries but remains difficult to automate: informal language must be mapped to precise mathematical formulations and executable solver code. Prior LLM approaches either rely on bri…
View article: Diabetes Lifestyle Medicine Treatment Assistance Using Reinforcement Learning
Diabetes Lifestyle Medicine Treatment Assistance Using Reinforcement Learning Open
Type 2 diabetes prevention and treatment can benefit from personalized lifestyle prescriptions. However, the delivery of personalized lifestyle medicine prescriptions is limited by the shortage of trained professionals and the variability …
View article: The association of serum GDF-15 level with the improvement of left ventricular ejection fraction in patients with heart failure and reduced ejection fraction
The association of serum GDF-15 level with the improvement of left ventricular ejection fraction in patients with heart failure and reduced ejection fraction Open
Background: Heart failure with improved ejection fraction (HFimpEF) is a distinct subtype of heart failure. Growth differentiation factor-15 (GDF-15), a biomarker linked to adverse cardiovascular outcomes, could help predict left ventricul…
View article: Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI
Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI Open
The rapid advancement of embodied intelligence and world models has intensified efforts to integrate physical laws into AI systems, yet physical perception and symbolic physics reasoning have developed along separate trajectories without a…
View article: Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets
Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets Open
Recent advances in 3D-native generative models have accelerated asset creation for games, film, and design. However, most methods still rely primarily on image or text conditioning and lack fine-grained, cross-modal controls, which limits …
View article: Prognostic Significance of Cardiac Output in Postcapillary Pulmonary Hypertension: Estimated Fick vs. Thermodilution
Prognostic Significance of Cardiac Output in Postcapillary Pulmonary Hypertension: Estimated Fick vs. Thermodilution Open
Background: The prognostic value of cardiac output measured by the estimated Fick method and thermodilution in patients with postcapillary pulmonary hypertension (pc-PH) is unclear. We aimed to compare the correlations and consistency of c…
View article: MPCG: Multi-Round Persona-Conditioned Generation for Modeling the Evolution of Misinformation with LLMs
MPCG: Multi-Round Persona-Conditioned Generation for Modeling the Evolution of Misinformation with LLMs Open
Misinformation evolves as it spreads, shifting in language, framing, and moral emphasis to adapt to new audiences. However, current misinformation detection approaches implicitly assume that misinformation is static. We introduce MPCG, a m…
View article: Revealing the Numeracy Gap: An Empirical Investigation of Text Embedding Models
Revealing the Numeracy Gap: An Empirical Investigation of Text Embedding Models Open
Text embedding models are widely used in natural language processing applications. However, their capability is often benchmarked on tasks that do not require understanding nuanced numerical information in text. As a result, it remains unc…
View article: Innovative No-Reference Image Quality Assessment for MRI-Guided Radiotherapy: Automated Distortion Detection
Innovative No-Reference Image Quality Assessment for MRI-Guided Radiotherapy: Automated Distortion Detection Open
View article: Efficient Diffusion-Based 3D Human Pose Estimation with Hierarchical Temporal Pruning
Efficient Diffusion-Based 3D Human Pose Estimation with Hierarchical Temporal Pruning Open
Diffusion models have demonstrated strong capabilities in generating high-fidelity 3D human poses, yet their iterative nature and multi-hypothesis requirements incur substantial computational cost. In this paper, we propose an Efficient Di…
View article: Genome-wide identification and characterization of the ubiquitin-specific protease (USP) gene family in cattle: primary analysis of muscle-specific USP genes and their influence on myogenesis
Genome-wide identification and characterization of the ubiquitin-specific protease (USP) gene family in cattle: primary analysis of muscle-specific USP genes and their influence on myogenesis Open
BACKGROUND: The ubiquitin-proteasome system(UPS) is a critical biological pathway that regulates protein function and plays a pivotal role in muscle formation. Nevertheless, the current comprehension of the ubiquitin-specific protease (USP…
View article: Reinforcement learning method for service life extension decision of corroded ship hull
Reinforcement learning method for service life extension decision of corroded ship hull Open
View article: Omics-Based Insights into Microbial Community Changes and Pathogen Identification in Strawberries Under Continuous Cropping
Omics-Based Insights into Microbial Community Changes and Pathogen Identification in Strawberries Under Continuous Cropping Open
Soilborne diseases resulting from continuous cropping obstacles of strawberries severely limit the development of the industry. In this study, samples of healthy and diseased strawberry plants were collected. Amplicon and metagenomic techn…
View article: Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material
Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material Open
3D AI-generated content (AIGC) is a passionate field that has significantly accelerated the creation of 3D models in gaming, film, and design. Despite the development of several groundbreaking models that have revolutionized 3D generation,…
View article: SASep: Saliency-Aware Structured Separation of Geometry and Feature for Open Set Learning on Point Clouds
SASep: Saliency-Aware Structured Separation of Geometry and Feature for Open Set Learning on Point Clouds Open
Recent advancements in deep learning have greatly enhanced 3D object recognition, but most models are limited to closed-set scenarios, unable to handle unknown samples in real-world applications. Open-set recognition (OSR) addresses this l…
View article: Designing transit routes based on vehicle routing behavior determined through location-based services data
Designing transit routes based on vehicle routing behavior determined through location-based services data Open
The disparity between transit agency travel predictions and the unpredictable nature of real-world travel behavior contributes to inefficiencies within the transit system. To address this challenge, we propose a bottom-up transit planning …
View article: Knowledge, attitudes and sexual behavior concerning AIDS among college students in Guangzhou, China: a cross-sectional questionnaire survey
Knowledge, attitudes and sexual behavior concerning AIDS among college students in Guangzhou, China: a cross-sectional questionnaire survey Open
Background Despite global efforts to control human immunodeficiency virus (HIV) among adolescents, the number of new infections among adolescents continues to increase. The increasingly widespread HIV epidemic among Chinese college student…
View article: Comparison of simultaneous integrated tumor bed boost and sequential boost during hypofractionated whole-breast irradiation after breast-conserving surgery
Comparison of simultaneous integrated tumor bed boost and sequential boost during hypofractionated whole-breast irradiation after breast-conserving surgery Open
SIB is a viable alternative to SeB, offering comparable toxicity profiles and survival outcomes while shortening treatment duration. Longer follow-up is warranted to assess long-term outcomes.
View article: Research on Hyperspectral Image Classification Based on Multi-task Generative Adversarial Networks
Research on Hyperspectral Image Classification Based on Multi-task Generative Adversarial Networks Open
As a prerequisite to realize many applications of hyperspectral images, hyperspectral image classification has been a hot and difficult research area in remote sensing. In recent years, various deep learning network models are in the ascen…
View article: Designing Transit Routes based on Vehicle Routing Behavior Determined through Location-Based Services Data
Designing Transit Routes based on Vehicle Routing Behavior Determined through Location-Based Services Data Open
The disparity between transit agency travel predictions and the unpredictable nature of real-world travel behavior contributes to inefficiencies within the transit system. To address this challenge, we propose a bottom-up transit planning …
View article: 4D-ACFNet: A 4D Attention Mechanism-Based Prognostic Framework for Colorectal Cancer Liver Metastasis Integrating Multimodal Spatiotemporal Features
4D-ACFNet: A 4D Attention Mechanism-Based Prognostic Framework for Colorectal Cancer Liver Metastasis Integrating Multimodal Spatiotemporal Features Open
Postoperative prognostic prediction for colorectal cancer liver metastasis (CRLM) remains challenging due to tumor heterogeneity, dynamic evolution of the hepatic microenvironment, and insufficient multimodal data fusion. To address these …
View article: FinMTEB: Finance Massive Text Embedding Benchmark
FinMTEB: Finance Massive Text Embedding Benchmark Open
Embedding models play a crucial role in representing and retrieving information across various NLP applications. Recent advances in large language models (LLMs) have further enhanced the performance of embedding models. While these models …
View article: Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation
Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation Open
We present Hunyuan3D 2.0, an advanced large-scale 3D synthesis system for generating high-resolution textured 3D assets. This system includes two foundation components: a large-scale shape generation model -- Hunyuan3D-DiT, and a large-sca…
View article: Genome-wide DNA methylation analysis of sorghum leaves following foreign GA3 exposure under salt stress
Genome-wide DNA methylation analysis of sorghum leaves following foreign GA3 exposure under salt stress Open
Sorghum is an increasingly popular topic of research in elucidating survival and adaptation approaches to augmented salinity. Nonetheless, little is known about the outcome and modulatory networks involved in the gibberellic acid (GA3)-ind…
View article: MPCG: Multi-Round Persona-Conditioned Generation for Modeling the Evolution of Misinformation with LLMs
MPCG: Multi-Round Persona-Conditioned Generation for Modeling the Evolution of Misinformation with LLMs Open
View article: Prism: A Secure Mobile Edge Computing Framework Via Hierarchical Structure and Blockchain Governance
Prism: A Secure Mobile Edge Computing Framework Via Hierarchical Structure and Blockchain Governance Open
View article: Characterization and Genetic Mapping of Dek1648 Mutant Reveals a Dead-Box Rna Helicase Involved in Maize Kernel Development
Characterization and Genetic Mapping of Dek1648 Mutant Reveals a Dead-Box Rna Helicase Involved in Maize Kernel Development Open
View article: FinMTEB: Finance Massive Text Embedding Benchmark
FinMTEB: Finance Massive Text Embedding Benchmark Open
View article: Evaluating and Aligning Human Economic Risk Preferences in LLMs
Evaluating and Aligning Human Economic Risk Preferences in LLMs Open
View article: Graphene-diyne-supported single transition metal atom catalysts for CO2 capture and CO2 hydrogenation conversion
Graphene-diyne-supported single transition metal atom catalysts for CO2 capture and CO2 hydrogenation conversion Open