arXiv subjects

Tiantian Yang

Publications and source records attributed to Tiantian Yang.

10 recordsLinked to original sources

arXiv2026

VARPose: Flexible 2D Pose Densification via Visual Autoregressive Modeling for Enhanced 3D Lifting

Visual AutoRegressive Modeling (VAR) has excelled in natural image generation via next-scale prediction, but its use on topology-structured data like human skeletons is still unexplored. VARPose is proposed to adaptively densify 2D sparse poses, thereby enriching the anatomical information available for 3D lifting models. Our core contributions are twofold. First, we introduce a Granularity-agnostic Pose Tokenizer (GPT), which employs a single hybrid codebook and a residual quantization strategy to encode poses of varying densities into a unified, multi-scale discrete representation. Our results demonstrate the strong generalizability of this representation. By decoupling the representation from the projection, we can successfully decode novel pose granularities using a frozen codebook with a retrained decoder. Second, we propose UniSkelar, a unified autoregressive model that treats "joint density" as "scale". UniSkelar learns to predict the token sequence for the next density level in a coarse-to-fine manner, conditioned on the sparsest pose. VARPose not only outperforms state-of-the-art methods and generalizes to unseen granularities, but also confers tangible performance gains on downstream tasks, such as 3D Pose Estimation and Human Mesh Recovery, through 2D pose densification. Our code and model are available at https://github.com/BRL-SYSU/VARPose.git.

cs.CV↗

arXiv2026

Prediction of Radiotherapy-Induced Hematologic Toxicity in Cervical Cancer with Cohort-Aware Framework

Hematologic toxicity (HT) is a major dose-limiting complication of pelvic radiotherapy for cervical cancer. Although radiomic and dosiomic features improve HT prediction beyond dosimetric metrics, their performance is highly sensitive to contour variability, limiting generalizability. We developed a cohort-aware representation-learning framework to address this challenge. We retrospectively analyzed 152 cervical cancer patients treated with pelvic radiotherapy without concurrent chemotherapy. Patients were divided into two cohorts based on the operators performing pelvic bone segmentation. HT prediction models were developed using cohort-specific training, pooled training, statistical harmonization, and a cohort-aware neural network (CANN) that learns shared and cohort-specific representations with contrastive regularization. Performance was evaluated using cross-validation and an independent test set. Cohort-specific models achieved test AUCs of 0.77 and 0.71, outperforming a dosimetry-only model (AUC=0.58). Directly pooling cohorts reduced performance (test AUC=0.64). Statistical harmonization provided limited benefit, while adversarial and correlation-based alignment further degraded performance. CANN achieved the best balance between robustness and generalizability (test AUC=0.72), with ablation studies confirming the importance of cohort-specific representations and contrastive alignment. These results demonstrate that cohort-aware representation learning effectively mitigates contour variability and improves the generalizability of radiomic and dosiomic models for HT prediction.

physics.med-ph↗

arXiv2026

AXON: An Automated Netlist Optimization Framework for High-Speed Adders

Adders are fundamental building blocks in modern digital systems, and their performance, power, and area (PPA) directly impact system efficiency. Contemporary adders typically use parallel-prefix architectures with established PPA trade-offs, but these often fail to deliver globally optimal PPA for specific design goals. Prior work lacks netlist-/cell-level awareness, and general synthesis heuristics are not adder-specific, resulting in suboptimal PPA. To address this, we propose AXON, an automated netlist optimization framework for adders. It performs design space exploration from architectural to netlist level, integrating prefix topology search with standard-cell-aware mapping via a hierarchical approach to quickly converge to near-optimal PPA solutions. We also introduce a hybrid ultra-high-speed adder combining parallel-prefix and Ling architectures to shorten the critical path. Experiments on TSMC 28nm library show AXON improves delay, area-delay product, and energy-delay product by up to 10.3%, 12.6%, and 32.1% respectively, compared to commercial synthesis tools.

cs.AR↗

arXiv2026

engGNN: A Dual-Graph Neural Network for Omics-Based Disease Classification and Feature Selection

Omics data, such as transcriptomics, proteomics, and metabolomics, provide critical insights into disease mechanisms and clinical outcomes. However, their high dimensionality, small sample sizes, and intricate biological networks pose major challenges for reliable prediction and meaningful interpretation. Graph Neural Networks (GNNs) offer a promising way to integrate prior knowledge by encoding feature relationships as graphs. Yet, existing methods typically rely solely on either an externally curated feature graph or a data-driven generated one, which limits their ability to capture complementary information. To address this, we propose the external and generated Graph Neural Network (engGNN), a dual-graph framework that jointly leverages both external known biological networks and data-driven generated graphs. Specifically, engGNN constructs a biologically informed undirected feature graph from established network databases and complements it with a directed feature graph derived from tree-ensemble models. This dual-graph design produces more comprehensive embeddings, thereby improving predictive performance and interpretability. Through extensive simulations and real-world applications to gene expression data, engGNN consistently outperforms state-of-the-art baselines. Beyond classification, engGNN provides interpretable feature importance scores that facilitate biologically meaningful discoveries, such as pathway enrichment analysis. Taken together, these results highlight engGNN as a robust, flexible, and interpretable framework for disease classification and biomarker discovery in high-dimensional omics contexts.

cs.LG↗

arXiv2025

Structure-Function Coherent Coarsening for Cross-Resolution Ecohydrological Modeling

Ecohydrological models are increasingly applied across multiple scenarios, yet their application remains constrained by high computational costs of fine-resolution simulations and structural inconsistencies in cross-scale modeling. This study develops a Structure-Function Coherent Coarsening (SFCC) framework that preserves both hydrological connectivity and functional heterogeneity during model input coarsening. We apply the VELMA model to 24 subbasins in the Salish Sea Basin, U.S. and examine three types of inputs: (i) DEM coarsened with a Hydro-aware approach that preserves drainage topology; (ii) land-use and soil-type datasets coarsened with function-preserving methods (Auto-weight and Auto-reassign) that retain small but process-dominant classes; and (iii) initial conditions coarsened with hydrology-, land-cover-, and soil-aware strategies to enhance temporal stability. Results show that the Hydro-aware method effectively preserves watershed morphology and yields more consistent runoff and nitrate predictions than mean-based coarsening across scales. For categorical inputs, the function-preserving methods alleviate the dominant-class bias of majority aggregation, particularly in basins where small high-impact patches drive nitrogen export. Long-term simulations further show that although hydrological variables equilibrate rapidly and biogeochemical processes adjust more gradually, deviations in both decrease over time and converge toward a steady state. These demonstrate that structural consistency and functional preservation together maintain dynamic stability through spatiotemporal feedback. Compared with existing work, the proposed SFCC framework operates directly at the data-input level, enabling more coherent integration of multi-source datasets and maximizing the retention of high-resolution information.

physics.geo-ph↗

arXiv2025

Interactions Between Multiple Environmental Markets: Addressing Contamination Bias in Overlapping Policies

To address the dual environmental challenges of pollution and climate change, China has established multiple environmental markets, including pollution emissions trading, carbon emissions trading, energy-use rights trading, and green electricity trading. Previous empirical studies suffer from known biases arising from time-varying treatment and multiple treatments. To address these limitations, this study adopts a dynamic control group design and combines Difference-in-Difference (DiD) and Artificial Counterfactual (ArCo) empirical strategies. Using panel data on A-share listed companies from 2000 to 2024, this study investigates the marginal effects and interactive impacts of multiple environmental markets implemented in staggered and overlapping phases. Existing pollution emissions trading mitigates the negative effects of carbon emission trading. Carbon trading suppresses (improves) financial performance (if implemented alongside energy-use rights trading). The addition of energy-use rights or green electricity trading in regions already covered by carbon or pollution markets has no significant effects.

econ.GN↗

arXiv2025

TF-DWGNet: A Directed Weighted Graph Neural Network with Tensor Fusion for Multi-Omics Cancer Subtype Classification

Integration and analysis of multi-omics data provide valuable insights for improving cancer subtype classification. However, such data are inherently heterogeneous, high-dimensional, and exhibit complex intra- and inter-modality dependencies. Graph neural networks (GNNs) offer a principled framework for modeling these structures, but existing approaches often rely on prior knowledge or predefined similarity networks that produce undirected or unweighted graphs and fail to capture task-specific directionality and interaction strength. Interpretability at both the modality and feature levels also remains limited. To address these challenges, we propose TF-DWGNet, a novel Graph Neural Network framework that combines tree-based Directed Weighted graph construction with Tensor Fusion for multiclass cancer subtype classification. TF-DWGNet introduces two key innovations: (i) a supervised tree-based strategy that constructs directed, weighted graphs tailored to each omics modality, and (ii) a tensor fusion mechanism that captures unimodal, bimodal, and trimodal interactions using low-rank decomposition for computational efficiency. Experiments on three real-world cancer datasets demonstrate that TF-DWGNet consistently outperforms state-of-the-art baselines across multiple metrics and statistical tests. In addition, the model provides biologically meaningful insights through modality-level contribution scores and ranked feature importance. These results highlight that TF-DWGNet is an effective and interpretable solution for multi-omics integration in cancer research.

q-bio.QM↗

arXiv2025

MOTGNN: Interpretable Graph Neural Networks for Multi-Omics Disease Classification

Integrating multi-omics data, such as DNA methylation, mRNA expression, and microRNA (miRNA) expression, offers a comprehensive view of the biological mechanisms underlying disease. However, the high dimensionality of multi-omics data, the heterogeneity across modalities, and the lack of reliable biological interaction networks make meaningful integration challenging. In addition, many existing models rely on handcrafted similarity graphs, are vulnerable to class imbalance, and often lack built-in interpretability, limiting their usefulness in biomedical applications. We propose Multi-Omics integration with Tree-generated Graph Neural Network (MOTGNN), a novel and interpretable framework for binary disease classification. MOTGNN employs eXtreme Gradient Boosting (XGBoost) for omics-specific supervised graph construction, followed by modality-specific Graph Neural Networks (GNNs) for hierarchical representation learning, and a deep feedforward network for cross-omics integration. Across three real-world disease datasets, MOTGNN outperforms state-of-the-art baselines by 5-10% in accuracy, ROC-AUC, and F1-score, and remains robust to severe class imbalance. The model maintains computational efficiency through the use of sparse graphs and provides built-in interpretability, revealing both top-ranked biomarkers and the relative contributions of each omics modality. These results highlight the potential of MOTGNN to improve both predictive accuracy and interpretability in multi-omics disease modeling.

cs.LG↗

arXiv2025

Beta-Generalized Lindley Distribution: A Novel Probability Model for Wind Speed

Wind speed distribution has many applications, such as the assessment of wind energy and building design. Applying an appropriate statistical distribution to fit the wind speed data, especially on its heavy right tail, is of great interest. In this study, we introduce a novel four-parameter class of generalized Lindley distribution, called the beta-generalized Lindley (BGL) distribution, to fit the wind speed data, which are derived from the annual and long-term measurements of the Flatirons M2 meteorological tower from the years 2010 to 2020 at heights of 10, 20, 50, and 80 meters. In terms of the density fit and various goodness-of-fit metrics, the BGL model outperforms its submodels (beta-Lindley, generalized Lindley, and Lindley) and other reference distributions, such as gamma, beta-Weibull, Weibull, beta-exponential, and Log-Normal. Furthermore, the BGL distribution is more accurate at modeling the long right tail of wind speed, including the $95^{th}$ and $99^{th}$ percentiles and Anderson-Darling statistics at different heights. Therefore, we conclude that the BGL distribution is a strong alternative model for the wind speed distribution.

stat.AP↗

arXiv2025

A Deep State Space Model for Rainfall-Runoff Simulations

The classical way of studying the rainfall-runoff processes in the water cycle relies on conceptual or physically-based hydrologic models. Deep learning (DL) has recently emerged as an alternative and blossomed in hydrology community for rainfall-runoff simulations. However, the decades-old Long Short-Term Memory (LSTM) network remains the benchmark for this task, outperforming newer architectures like Transformers. In this work, we propose a State Space Model (SSM), specifically the Frequency Tuned Diagonal State Space Sequence (S4D-FT) model, for rainfall-runoff simulations. The proposed S4D-FT is benchmarked against the established LSTM and a physically-based Sacramento Soil Moisture Accounting model across 531 watersheds in the contiguous United States (CONUS). Results show that S4D-FT is able to outperform the LSTM model across diverse regions. Our pioneering introduction of the S4D-FT for rainfall-runoff simulations challenges the dominance of LSTM in the hydrology community and expands the arsenal of DL tools available for hydrological modeling.

cs.LG↗