arXiv subjects

Weidong Huang

Publications and source records attributed to Weidong Huang.

At least 19 recordsLinked to original sources

arXiv2026

Chart2SVG: Editable SVG Generation from Raster Chart Images

We present Chart2SVG, a multimodal large language model that converts static raster charts into structurally organized, semantically enriched SVGs that support programmatic editing. By incorporating chart-specific semantic tokens into a vision-language model, Chart2SVG captures both geometric primitives and their functional roles. To support robust structural recovery, we introduce Beagle+, a dataset of 33K canonicalized and structurally distilled chart samples. Our approach combines specialized training objectives with a rendering-aware post-training phase, producing SVGs that are both visually accurate and structurally consistent. To facilitate higher-level manipulations, we construct a Chart Structure Graph (CSG) that exposes visual dependencies, enabling tasks such as interactive exploration, chart repurposing, and layout reuse. Experiments show that Chart2SVG substantially outperforms baselines in reconstruction fidelity and downstream editing utility, advancing the development of intelligent and interactive visualization tools.

cs.LG↗

arXiv2026

SNAP-tFDP: Massively Scalable Graph Layouts via Sparse Negative Sampling

Force-Directed Placement (FDP) is a widely used approach for network visualization, yet scaling it to massive graphs while preserving clear community structures remains a major computational and visual challenge. Existing approximation methods often rely on auxiliary data structures (e.g., spatial trees), which introduce substantial memory overhead; furthermore, traditional power-function-based forces frequently fail to separate dense clusters effectively. In this paper, we present a negative sampling-based algorithm that achieves O(|E|) time complexity with a low memory footprint, without requiring complex multi-level representations. In a first step, we introduce a linearly normalized degree-weighting scheme, which, combined with short-range bounded $t$-distribution forces, effectively untangles dense structures and enhances visual cluster separation. To optimize for this formulation efficiently, we introduce an edge-centric negative sampling strategy that naturally reconstructs the global degree-weighted objective. Furthermore, we design a lock-free, bundle-based parallelization scheme that leverages the sparsity of stochastic updates to achieve significant speedups while mitigating access conflicts. Comprehensive evaluations on 12 large-scale graphs demonstrate that the proposed method outperforms state-of-the-art algorithms in neighborhood preservation and cluster separation. Compared to existing baselines, our method reduces memory consumption by 72% on average and leverages simple GPU parallelism to generate a high-quality layout for a graph with 4 million nodes and 34 million edges in below 10 seconds.

cs.GR↗

arXiv2026

Towards Bridging the Gap between Large-Scale Pretraining and Efficient Finetuning for Humanoid Control

Reinforcement learning (RL) is widely used for humanoid control, with on-policy methods such as Proximal Policy Optimization (PPO) enabling robust training via large-scale parallel simulation and, in some cases, zero-shot deployment to real robots. However, the low sample efficiency of on-policy algorithms limits safe adaptation to new environments. Although off-policy RL and model-based RL have shown improved sample efficiency, the gap between large-scale pretraining and efficient finetuning on humanoids still exists. In this paper, we find that off-policy Soft Actor-Critic (SAC), with large-batch update and a high Update-To-Data (UTD) ratio, reliably supports large-scale pretraining of humanoid locomotion policies, achieving zero-shot deployment on real robots. For adaptation, we demonstrate that these SAC-pretrained policies can be finetuned in new environments and out-of-distribution tasks using model-based methods. Data collection in the new environment executes a deterministic policy while stochastic exploration is instead confined to a physics-informed world model. This separation mitigates the risks of random exploration during adaptation while preserving exploratory coverage for improvement. Overall, the approach couples the wall-clock efficiency of large-scale simulation during pretraining with the sample efficiency of model-based learning during fine-tuning. For code and videos, see https://lift-humanoid.github.io

cs.RO↗

arXiv2026

ECO: Energy-Constrained Optimization with Reinforcement Learning for Humanoid Walking

Achieving stable and energy-efficient locomotion is essential for humanoid robots to operate continuously in real-world applications. Existing MPC and RL approaches often rely on energy-related metrics embedded within a multi-objective optimization framework, which require extensive hyperparameter tuning and often result in suboptimal policies. To address these challenges, we propose ECO (Energy-Constrained Optimization), a constrained RL framework that separates energy-related metrics from rewards, reformulating them as explicit inequality constraints. This method provides a clear and interpretable physical representation of energy costs, enabling more efficient and intuitive hyperparameter tuning for improved energy efficiency. ECO introduces dedicated constraints for energy consumption and reference motion, enforced by the Lagrangian method, to achieve stable, symmetric, and energy-efficient walking for humanoid robots. We evaluated ECO against MPC, standard RL with reward shaping, and four state-of-the-art constrained RL methods. Experiments, including sim-to-sim and sim-to-real transfers on the kid-sized humanoid robot BRUCE, demonstrate that ECO significantly reduces energy consumption compared to baselines while maintaining robust walking performance. These results highlight a substantial advancement in energy-efficient humanoid locomotion. All experimental demonstrations can be found on the project website: https://sites.google.com/view/eco-humanoid.

cs.RO↗

arXiv2026

Benchmarking Preprocessing and Integration Methods in Single-Cell Genomics

Single-cell data analysis has the potential to revolutionize personalized medicine by characterizing disease-associated molecular changes at the single-cell level. Advanced single-cell multimodal assays can now simultaneously measure various molecules (e.g., DNA, RNA, Protein) across hundreds of thousands of individual cells, providing a comprehensive molecular readout. A significant analytical challenge is integrating single-cell measurements across different modalities. Various methods have been developed to address this challenge, but there has been no systematic evaluation of these techniques with different preprocessing strategies. This study examines a general pipeline for single-cell data analysis, which includes normalization, data integration, and dimensionality reduction. The performance of different algorithm combinations often depends on the dataset sizes and characteristics. We evaluate six datasets across diverse modalities, tissues, and organisms using three metrics: Silhouette Coefficient Score, Adjusted Rand Index, and Calinski-Harabasz Index. Our experiments involve combinations of seven normalization methods, four dimensional reduction methods, and five integration methods. The results show that Seurat and Harmony excel in data integration, with Harmony being more time-efficient, especially for large datasets. UMAP is the most compatible dimensionality reduction method with the integration techniques, and the choice of normalization method varies depending on the integration method used.

q-bio.QM↗

arXiv2026

Towards Automated Differential Diagnosis of Skin Diseases Using Deep Learning and Imbalance-Aware Strategies

As dermatological conditions become increasingly common and the availability of dermatologists remains limited, there is a growing need for intelligent tools to support both patients and clinicians in the timely and accurate diagnosis of skin diseases. In this project, we developed a deep learning based model for the classification and diagnosis of skin conditions. By leveraging pretraining on publicly available skin disease image datasets, our model effectively extracted visual features and accurately classified various dermatological cases. Throughout the project, we refined the model architecture, optimized data preprocessing workflows, and applied targeted data augmentation techniques to improve overall performance. The final model, based on the Swin Transformer, achieved a prediction accuracy of 87.71 percent across eight skin lesion classes on the ISIC2019 dataset. These results demonstrate the model's potential as a diagnostic support tool for clinicians and a self assessment aid for patients.

cs.CV↗

arXiv2025

A Hybrid Computational Intelligence Framework for scRNA-seq Imputation: Integrating scRecover and Random Forests

Single-cell RNA sequencing (scRNA-seq) enables transcriptomic profiling at cellular resolution but suffers from pervasive dropout events that obscure biological signals. We present SCR-MF, a modular two-stage workflow that combines principled dropout detection using scRecover with robust non-parametric imputation via missForest. Across public and simulated datasets, SCR-MF achieves robust and interpretable performance comparable to or exceeding existing imputation methods in most cases, while preserving biological fidelity and transparency. Runtime analysis demonstrates that SCR-MF provides a competitive balance between accuracy and computational efficiency, making it suitable for mid-scale single-cell datasets.

cs.LG↗

arXiv2025

World Models Should Prioritize the Unification of Physical and Social Dynamics

World models, which explicitly learn environmental dynamics to lay the foundation for planning, reasoning, and decision-making, are rapidly advancing in predicting both physical dynamics and aspects of social behavior, yet predominantly in separate silos. This division results in a systemic failure to model the crucial interplay between physical environments and social constructs, rendering current models fundamentally incapable of adequately addressing the true complexity of real-world systems where physical and social realities are inextricably intertwined. This position paper argues that the systematic, bidirectional unification of physical and social predictive capabilities is the next crucial frontier for world model development. We contend that comprehensive world models must holistically integrate objective physical laws with the subjective, evolving, and context-dependent nature of social dynamics. Such unification is paramount for AI to robustly navigate complex real-world challenges and achieve more generalizable intelligence. This paper substantiates this imperative by analyzing core impediments to integration, proposing foundational guiding principles (ACE Principles), and outlining a conceptual framework alongside a research roadmap towards truly holistic world models.

cs.CY↗

arXiv2025

Augmenting Limited and Biased RCTs through Pseudo-Sample Matching-Based Observational Data Fusion Method

In the online ride-hailing pricing context, companies often conduct randomized controlled trials (RCTs) and utilize uplift models to assess the effect of discounts on customer orders, which substantially influences competitive market outcomes. However, due to the high cost of RCTs, the proportion of trial data relative to observational data is small, which only accounts for 0.65\% of total traffic in our context, resulting in significant bias when generalizing to the broader user base. Additionally, the complexity of industrial processes reduces the quality of RCT data, which is often subject to heterogeneity from potential interference and selection bias, making it difficult to correct. Moreover, existing data fusion methods are challenging to implement effectively in complex industrial settings due to the high dimensionality of features and the strict assumptions that are hard to verify with real-world data. To address these issues, we propose an empirical data fusion method called pseudo-sample matching. By generating pseudo-samples from biased, low-quality RCT data and matching them with the most similar samples from large-scale observational data, the method expands the RCT dataset while mitigating its heterogeneity. We validated the method through simulation experiments, conducted offline and online tests using real-world data. In a week-long online experiment, we achieved a 0.41\% improvement in profit, which is a considerable gain when scaled to industrial scenarios with hundreds of millions in revenue. In addition, we discuss the harm to model training, offline evaluation, and online economic benefits when the RCT data quality is not high, and emphasize the importance of improving RCT data quality in industrial scenarios. Further details of the simulation experiments can be found in the GitHub repository https://github.com/Kairong-Han/Pseudo-Matching.

stat.ME↗

arXiv2025

FedSAF: A Federated Learning Framework for Enhanced Gastric Cancer Detection and Privacy Preservation

Gastric cancer is one of the most commonly diagnosed cancers and has a high mortality rate. Due to limited medical resources, developing machine learning models for gastric cancer recognition provides an efficient solution for medical institutions. However, such models typically require large sample sizes for training and testing, which can challenge patient privacy. Federated learning offers an effective alternative by enabling model training across multiple institutions without sharing sensitive patient data. This paper addresses the limited sample size of publicly available gastric cancer data with a modified data processing method. This paper introduces FedSAF, a novel federated learning algorithm designed to improve the performance of existing methods, particularly in non-independent and identically distributed (non-IID) data scenarios. FedSAF incorporates attention-based message passing and the Fisher Information Matrix to enhance model accuracy, while a model splitting function reduces computation and transmission costs. Hyperparameter tuning and ablation studies demonstrate the effectiveness of this new algorithm, showing improvements in test accuracy on gastric cancer datasets, with FedSAF outperforming existing federated learning methods like FedAMP, FedAvg, and FedProx. The framework's robustness and generalization ability were further validated across additional datasets (SEED, BOT, FashionMNIST, and CIFAR-10), achieving high performance in diverse environments.

cs.LG↗

arXiv2025

Differentiable Information Enhanced Model-Based Reinforcement Learning

Differentiable environments have heralded new possibilities for learning control policies by offering rich differentiable information that facilitates gradient-based methods. In comparison to prevailing model-free reinforcement learning approaches, model-based reinforcement learning (MBRL) methods exhibit the potential to effectively harness the power of differentiable information for recovering the underlying physical dynamics. However, this presents two primary challenges: effectively utilizing differentiable information to 1) construct models with more accurate dynamic prediction and 2) enhance the stability of policy training. In this paper, we propose a Differentiable Information Enhanced MBRL method, MB-MIX, to address both challenges. Firstly, we adopt a Sobolev model training approach that penalizes incorrect model gradient outputs, enhancing prediction accuracy and yielding more precise models that faithfully capture system dynamics. Secondly, we introduce mixing lengths of truncated learning windows to reduce the variance in policy gradient estimation, resulting in improved stability during policy learning. To validate the effectiveness of our approach in differentiable environments, we provide theoretical analysis and empirical results. Notably, our approach outperforms previous model-based and model-free methods, in multiple challenging tasks involving controllable rigid robots such as humanoid robots' motion control and deformable object manipulation.

cs.LG↗

arXiv2024

Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark

Artificial intelligence (AI) systems possess significant potential to drive societal progress. However, their deployment often faces obstacles due to substantial safety concerns. Safe reinforcement learning (SafeRL) emerges as a solution to optimize policies while simultaneously adhering to multiple constraints, thereby addressing the challenge of integrating reinforcement learning in safety-critical scenarios. In this paper, we present an environment suite called Safety-Gymnasium, which encompasses safety-critical tasks in both single and multi-agent scenarios, accepting vector and vision-only input. Additionally, we offer a library of algorithms named Safe Policy Optimization (SafePO), comprising 16 state-of-the-art SafeRL algorithms. This comprehensive library can serve as a validation tool for the research community. By introducing this benchmark, we aim to facilitate the evaluation and comparison of safety performance, thus fostering the development of reinforcement learning for safer, more reliable, and responsible real-world applications. The website of this project can be accessed at https://sites.google.com/view/safety-gymnasium.

cs.AI↗

arXiv2024

SafeDreamer: Safe Reinforcement Learning with World Models

The deployment of Reinforcement Learning (RL) in real-world applications is constrained by its failure to satisfy safety criteria. Existing Safe Reinforcement Learning (SafeRL) methods, which rely on cost functions to enforce safety, often fail to achieve zero-cost performance in complex scenarios, especially vision-only tasks. These limitations are primarily due to model inaccuracies and inadequate sample efficiency. The integration of the world model has proven effective in mitigating these shortcomings. In this work, we introduce SafeDreamer, a novel algorithm incorporating Lagrangian-based methods into world model planning processes within the superior Dreamer framework. Our method achieves nearly zero-cost performance on various tasks, spanning low-dimensional and vision-only input, within the Safety-Gymnasium benchmark, showcasing its efficacy in balancing performance and safety in RL tasks. Further details can be found in the code repository: \url{https://github.com/PKU-Alignment/SafeDreamer}.

cs.LG↗

arXiv2023

OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning Research

AI systems empowered by reinforcement learning (RL) algorithms harbor the immense potential to catalyze societal advancement, yet their deployment is often impeded by significant safety concerns. Particularly in safety-critical applications, researchers have raised concerns about unintended harms or unsafe behaviors of unaligned RL agents. The philosophy of safe reinforcement learning (SafeRL) is to align RL agents with harmless intentions and safe behavioral patterns. In SafeRL, agents learn to develop optimal policies by receiving feedback from the environment, while also fulfilling the requirement of minimizing the risk of unintended harm or unsafe behavior. However, due to the intricate nature of SafeRL algorithm implementation, combining methodologies across various domains presents a formidable challenge. This had led to an absence of a cohesive and efficacious learning framework within the contemporary SafeRL research milieu. In this work, we introduce a foundational framework designed to expedite SafeRL research endeavors. Our comprehensive framework encompasses an array of algorithms spanning different RL domains and places heavy emphasis on safety elements. Our efforts are to make the SafeRL-related research process more streamlined and efficient, therefore facilitating further research in AI safety. Our project is released at: https://github.com/PKU-Alignment/omnisafe.

cs.LG↗

arXiv2021

Ultra strong and ductile eutectic high entropy alloy fabricated by selective laser melting

With important application prospects, eutectic high entropy alloys have received extensive attention for their excellent strength and ductility in a large temperature range. The excellent casting characteristics of eutectic high entropy alloys make it possible to achieve well manufacturability of selective laser melting. For the first time, we have achieved crack-free eutectic high entropy alloy fabricated by selective laser melting, which has excellent mechanical properties in a wide temperature range of -196 degrees Celsius~760 degrees Celsius due to ultra-fine eutectic lamellar spacing of 150 ~ 200nm and lamellar colony of 2 ~ 6 μm. Specifically, the room temperature tensile strength exceeds 1400MPa and the elongation is more than 20%, significantly improved compared with those manufactured by other techniques with lower cooling rate.

physics.app-ph↗

arXiv2021

Facilitating Machine Learning Model Comparison and Explanation Through A Radial Visualisation

Building an effective Machine Learning (ML) model for a data set is a difficult task involving various steps. One of the most important steps is to compare generated substantial amounts of ML models to find the optimal one for the deployment. It is challenging to compare such models with dynamic number of features. Comparison is more than just finding differences of ML model performance, users are also interested in the relations between features and model performance such as feature importance for ML explanations. This paper proposes RadialNet Chart, a novel visualisation approach to compare ML models trained with a different number of features of a given data set while revealing implicit dependent relations. In RadialNet Chart, ML models and features are represented by lines and arcs respectively. These lines are generated effectively using a recursive function. The dependence of ML models with dynamic number of features is encoded into the structure of visualisation, where ML models and their dependent features are directly revealed from related line connections. ML model performance information is encoded with colour and line width in RadialNet Chart. Together with the structure of visualisation, feature importance can be directly discerned in RadialNet Chart for ML explanations.

cs.LG↗

arXiv2020

A new method for life table and life expectancy calculation

The existing life table method needs to calculate the age-specific mortality first, not only has too many and complicated calculation steps, but also introduces the multiple approximation to bring error. This paper redefines the probability of death for the life table as the average probability of death of a group of people born in a certain period at a later time. Based on this definition, a new method for the life table is proposed to obtain the life expectancy, which has the same meaning to that from the traditional life table. Using the Japanese population data to verify the method, the results show that it is consistent with the life expectancy of the birth of the baby, the maximum relative difference is no more than 0.1%, and average relative difference is less than 0.03%. The theory and method of life table described in this paper are simple and easy to understand. The needed data are easy to obtained from statistics, and the calculation is easy, the results obtained are accurate and reliable. It should be a very valuable demographic method for application.

q-bio.OT↗

arXiv2020

A new method to calculate the Total Fertility Rate from the number of birth

The standard methods to calculate the Total Fertility Rate require the reliable age-specific fertility rate including birth data and the related age-specific women's population data. Historically, the number of births was often not counted according to the age of the mother, so it is difficult to estimate the historical total fertility rate with the standard methods. Many empirical methods have been proposed, but their application is limited to specific period and place. This paper deduces a new method for calculating the total fertility rate from the number of birth and the population of women at childbearing age, can be applied to most of cases. The relative error is usually less than 5%. It is easier to calculate TFR, and may be applied to obtain more TFRs for the history.

q-bio.PE↗