arXiv subjects

Jun Huang

Publications and source records attributed to Jun Huang.

At least 55 records · Page 3Linked to original sources

arXiv2026

BCMDA: Bidirectional Correlation Maps Domain Adaptation for Mixed Domain Semi-Supervised Medical Image Segmentation

In mixed domain semi-supervised medical image segmentation (MiDSS), achieving superior performance under domain shift and limited annotations is challenging. This scenario presents two primary issues: (1) distributional differences between labeled and unlabeled data hinder effective knowledge transfer, and (2) inefficient learning from unlabeled data causes severe confirmation bias. In this paper, we propose the bidirectional correlation maps domain adaptation (BCMDA) framework to overcome these issues. On the one hand, we employ knowledge transfer via virtual domain bridging (KTVDB) to facilitate cross-domain learning. First, to construct a distribution-aligned virtual domain, we leverage bidirectional correlation maps between labeled and unlabeled data to synthesize both labeled and unlabeled images, which are then mixed with the original images to generate virtual images using two strategies, a fixed ratio and a progressive dynamic MixUp. Next, dual bidirectional CutMix is used to enable initial knowledge transfer within the fixed virtual domain and gradual knowledge transfer from the dynamically transitioning labeled domain to the real unlabeled domains. On the other hand, to alleviate confirmation bias, we adopt prototypical alignment and pseudo label correction (PAPLC), which utilizes learnable prototype cosine similarity classifiers for bidirectional prototype alignment between the virtual and real domains, yielding smoother and more compact feature representations. Finally, we use prototypical pseudo label correction to generate more reliable pseudo labels. Empirical evaluations on three public multi-domain datasets demonstrate the superiority of our method, particularly showing excellent performance even with very limited labeled samples. Code available at https://github.com/pascalcpp/BCMDA.

cs.CV↗

arXiv2026

Enhancing Credit Risk Prediction: A Multi-stage Ensemble Pipeline

Effective credit risk management is fundamental to financial decision-making, requiring robust models to predict default probabilities and classify financial entities. Traditional machine learning approaches face significant challenges when confronted with high-dimensional data, limited interpretability, rare-event detection, and multi-class risk imbalance. This research proposes a comprehensive multi-stage ensemble pipeline that synthesizes multiple complementary models: econometric models including Ordered logit and ordered probit, supervised learning algorithms, including XGBoost, Random Forest, Support Vector Machine, and Decision Tree; unsupervised methods such as K-Nearest Neighbors; deep learning architectures like Multilayer Perceptron; alongside LASSO regularization for feature selection and dimensionality reduction; and Error-Correcting Output Codes as an Ensemble classifier for handling imbalanced multi-class problems. We implement Permutation Feature Importance analysis for each prediction class across all constituent models to enhance model transparency. Our framework can optimize predictive performance while providing a more holistic approach to credit risk assessment. This research contributes to the development of more accurate and reliable computational models for strategic financial decision support by addressing three fundamental challenges in credit risk modeling. The empirical validation of our approach involves analyzing the Corporate Credit Ratings dataset, which contains credit ratings for 2,029 publicly listed US companies. Results demonstrate that our multi-stage ensemble pipeline significantly enhances the accuracy of financial entity classification regarding credit rating migrations (upgrades and downgrades) and default probability estimation.

cs.LG↗

arXiv2026

DSCSNet: A Dynamic Sparse Compression Sensing Network for Closely-Spaced Infrared Small Target Unmixing

Due to the limitations of optical lens focal length and detector resolution, distant clustered infrared small targets often appear as mixed spots. The Close Small Object Unmixing (CSOU) task aims to recover the number, sub-pixel positions, and radiant intensities of individual targets from these spots, which is a highly ill-posed inverse problem. Existing methods struggle to balance the rigorous sparsity guarantees of model-driven approaches and the dynamic scene adaptability of data-driven methods. To address this dilemma, this paper proposes a Dynamic Sparse Compressed Sensing Network (DSCSNet), a deep-unfolded network that couples the Alternating Direction Method of Multipliers (ADMM) with learnable parameters. Specifically, we embed a strict $\ell_1$-norm sparsity constraint into the auxiliary variable update step of ADMM to replace the traditional $\ell_2$-norm smoothness-promoting terms, which effectively preserves the discrete energy peaks of small targets. We also integrate a self-attention-based dynamic thresholding mechanism into the reconstruction stage, which adaptively adjusts the sparsification intensity using the sparsity-enhanced information from the iterative process. These modules are jointly optimized end-to-end across the three iterative steps of ADMM. Retaining the physical logic of compressed sensing, DSCSNet achieves robust sparsity induction and scene adaptability, thus enhancing the unmixing accuracy and generalization in complex infrared scenarios. Extensive experiments on the synthetic infrared dataset CSIST-100K demonstrate that DSCSNet outperforms state-of-the-art methods in key metrics such as CSO-mAP and sub-pixel localization error.

cs.CV↗

arXiv2026

Short-Range Solvent-Solvent and Ion-Solvent Correlations at Metal-Electrolyte Interfaces: Parameterization and Benchmarking

Short-range correlations in electrolyte solutions lead to oscillatory profiles of water polarization and ionic concentration at electrode-electrolyte interfaces. The recently developed density-potential-polarization functional theory (DPPFT) provides a comprehensive framework to incorporate these short-range correlation effects. In the present work, the parameters describing short-range solvent-solvent and ion-solvent correlations in DPPFT are determined from the wavenumber-dependent dielectric susceptibility spectrum of pure water and from ion solvation energies derived within nonlocal electrostatics, respectively. The experimental ionic-radius-dependent hydration energies of alkali metal cations and halide anions are well reproduced by the solvation model. The charge hydration asymmetry is explained as the stronger short-range repulsion between cations and water molecules compared to that between anions and water molecules. Using these parameters, DPPFT is then applied to investigate short-range correlation effects at the Ag(111)-NaF aqueous electrolyte interface. The water polarization profiles obtained from DPPFT calculations agree with AIMD simulations. Furthermore, as the strength of short-range ion-solvent repulsion increases, the peaks of anionic/layers shift from regions near centers of positive/negative polarization charges toward those of opposite sign, thereby preserving solvation configurations similar to those in bulk solution. This work develops a consistent procedure for parameterizing short-range correlation effects within the DPPFT framework, thereby enabling a more quantitative and computationally efficient description of atomic-scale phenomena at electrochemical interfaces.

physics.chem-ph↗

arXiv2026

Mock Worlds, Real Skills: Building Small Agentic Language Models with Synthetic Tasks, Simulated Environments, and Rubric-Based Rewards

Small LLMs often struggle to match the agentic capabilities of large, costly models. While reinforcement learning can help, progress has been limited by two structural bottlenecks: existing open-source agentic training data are narrow in task variety and easily solved; real-world APIs lack diversity and are unstable for large-scale reinforcement learning rollout processes. We address these challenges with SYNTHAGENT, a framework that jointly synthesizes diverse tool-use training data and simulates complete environments. Specifically, a strong teacher model creates novel tasks and tool ecosystems, then rewrites them into intentionally underspecified instructions. This compels agents to actively query users for missing details. When handling synthetic tasks, an LLM-based user simulator provides user-private information, while a mock tool system delivers stable tool responses. For rewards, task-level rubrics are constructed based on required subgoals, user-agent interactions, and forbidden behaviors. Across 14 challenging datasets in math, search, and tool use, models trained on our synthetic data achieve substantial gains, with small models outperforming larger baselines.

cs.CL↗

arXiv2026

Electrochemical Electron Transfer: Key Concepts, Theories, and Parameterization via Atomistic Simulations

Electron transfer (ET) at electrochemical interfaces is central to energy conversion and storage, yet its theoretical and computational modeling remain active research areas. This review elucidates key concepts and theories of ET kinetics, focusing on coupling between classical solvent fluctuations and quantum electronic states of metallic electrodes and redox species. We begin with fundamental rate theories, reaction coordinates, and electrochemical timescales, then explore weak, strong, and intermediate electronic coupling regimes. Special attention is given to solvent dynamics and the structure of the electrical double layer (EDL), which critically impact ET kinetics. Atomistic simulations, particularly density functional theory (DFT) and molecular dynamics (MD), are highlighted for testing linear response and determining solvent reorganization energy, electronic coupling strengths, and solvent relaxation dynamics. A central theme is linear response enabling tractable treatments across Marcus theory, empirical valence bond (EVB) models, the Anderson-Newns-Schmickler framework, and generalized Langevin dynamics. While linear response offers useful simplifications, we assess its limitations, particularly for strong solvation changes or inner-sphere ET at catalytic interfaces. We discuss advances, including mapping Hamiltonian-based EVB-MD, constrained DFT, and non-Gaussian free energy formulations, enabling rigorous tests and access to diabatic and adiabatic free energy surfaces. We outline opportunities to advance multiscale, quantum-classical models that integrate EDL effects, multiple reaction coordinates, solvent-controlled dynamics, and transitions between adiabatic and nonadiabatic regimes. This review serves as a conceptual guide and practical resource for researchers integrating theory and simulation in studying electrochemical ET across diverse systems.

physics.chem-ph↗

arXiv2026

EasyAnimate: High-Performance Video Generation Framework with Hybrid Windows Attention and Reward Backpropagation

This paper introduces EasyAnimate, an efficient and high quality video generation framework that leverages diffusion transformers to achieve high-quality video production, encompassing data processing, model training, and end-to-end inference. Despite substantial advancements achieved by video diffusion models, existing video generation models still struggles with slow generation speeds and less-than-ideal video quality. To improve training and inference efficiency without compromising performance, we propose Hybrid Window Attention. We design the multidirectional sliding window attention in Hybrid Window Attention, which provides stronger receptive capabilities in 3D dimensions compared to naive one, while reducing the model's computational complexity as the video sequence length increases. To enhance video generation quality, we optimize EasyAnimate using reward backpropagation to better align with human preferences. As a post-training method, it greatly enhances the model's performance while ensuring efficiency. In addition to the aforementioned improvements, EasyAnimate integrates a series of further refinements that significantly improve both computational efficiency and model performance. We introduce a new training strategy called Training with Token Length to resolve uneven GPU utilization in training videos of varying resolutions and lengths, thereby enhancing efficiency. Additionally, we use a multimodal large language model as the text encoder to improve text comprehension of the model. Experiments demonstrate significant enhancements resulting from the above improvements. The EasyAnimate achieves state-of-the-art performance on both the VBench leaderboard and human evaluation. Code and pre-trained models are available at https://github.com/aigc-apps/EasyAnimate.

cs.CV↗

arXiv2026

VTC-R1: Vision-Text Compression for Efficient Long-Context Reasoning

Long-context reasoning has significantly empowered large language models (LLMs) to tackle complex tasks, yet it introduces severe efficiency bottlenecks due to the computational complexity. Existing efficient approaches often rely on complex additional training or external models for compression, which limits scalability and discards critical fine-grained information. In this paper, we propose VTC-R1, a new efficient reasoning paradigm that integrates vision-text compression into the reasoning process. Instead of processing lengthy textual traces, VTC-R1 renders intermediate reasoning segments into compact images, which are iteratively fed back into vision-language models as "optical memory." We construct a training dataset based on OpenR1-Math-220K achieving 3.4x token compression and fine-tune representative VLMs-Glyph and Qwen3-VL. Extensive experiments on benchmarks such as MATH500, AIME25, AMC23 and GPQA-D demonstrate that VTC-R1 consistently outperforms standard long-context reasoning. Furthermore, our approach significantly improves inference efficiency, achieving 2.7x speedup in end-to-end latency, highlighting its potential as a scalable solution for reasoning-intensive applications. Our code is available at https://github.com/w-yibo/VTC-R1.

cs.CL↗

arXiv2026

Reinforcement Learning-Based Energy-Aware Coverage Path Planning for Precision Agriculture

Coverage Path Planning (CPP) is a fundamental capability for agricultural robots; however, existing solutions often overlook energy constraints, resulting in incomplete operations in large-scale or resource-limited environments. This paper proposes an energy-aware CPP framework grounded in Soft Actor-Critic (SAC) reinforcement learning, designed for grid-based environments with obstacles and charging stations. To enable robust and adaptive decision-making under energy limitations, the framework integrates Convolutional Neural Networks (CNNs) for spatial feature extraction and Long Short-Term Memory (LSTM) networks for temporal dynamics. A dedicated reward function is designed to jointly optimize coverage efficiency, energy consumption, and return-to-base constraints. Experimental results demonstrate that the proposed approach consistently achieves over 90% coverage while ensuring energy safety, outperforming traditional heuristic algorithms such as Rapidly-exploring Random Tree (RRT), Particle Swarm Optimization (PSO), and Ant Colony Optimization (ACO) baselines by 13.4-19.5% in coverage and reducing constraint violations by 59.9-88.3%. These findings validate the proposed SAC-based framework as an effective and scalable solution for energy-constrained CPP in agricultural robotics.

cs.RO↗

arXiv2026

Natural Language-Driven Global Mapping of Martian Landforms

Planetary surfaces are typically analyzed using high-level semantic concepts in natural language, yet vast orbital image archives remain organized at the pixel level. This mismatch limits scalable, open-ended exploration of planetary surfaces. Here we present MarScope, a planetary-scale vision-language framework enabling natural language-driven, label-free mapping of Martian landforms. MarScope aligns planetary images and text in a shared semantic space, trained on over 200,000 curated image-text pairs. This framework transforms global geomorphic mapping on Mars by replacing pre-defined classifications with flexible semantic retrieval, enabling arbitrary user queries across the entire planet in 5 seconds with F1 scores up to 0.978. Applications further show that it extends beyond morphological classification to facilitate process-oriented analysis and similarity-based geomorphological mapping at a planetary scale. MarScope establishes a new paradigm where natural language serves as a direct interface for scientific discovery over massive geospatial datasets.

cs.AI↗

arXiv2026

On Exact Editing of Flow-Based Diffusion Models

Recent methods in flow-based diffusion editing have enabled direct transformations between source and target image distribution without explicit inversion. However, the latent trajectories in these methods often exhibit accumulated velocity errors, leading to semantic inconsistency and loss of structural fidelity. We propose Conditioned Velocity Correction (CVC), a principled framework that reformulates flow-based editing as a distribution transformation problem driven by a known source prior. CVC rethinks the role of velocity in inter-distribution transformation by introducing a dual-perspective velocity conversion mechanism. This mechanism explicitly decomposes the latent evolution into two components: a structure-preserving branch that remains consistent with the source trajectory, and a semantically-guided branch that drives a controlled deviation toward the target distribution. The conditional velocity field exhibits an absolute velocity error relative to the true underlying distribution trajectory, which inherently introduces potential instability and trajectory drift in the latent space. To address this quantifiable deviation and maintain fidelity to the true flow, we apply a posterior-consistent update to the resulting conditional velocity field. This update is derived from Empirical Bayes Inference and Tweedie correction, which ensures a mathematically grounded error compensation over time. Our method yields stable and interpretable latent dynamics, achieving faithful reconstruction alongside smooth local semantic conversion. Comprehensive experiments demonstrate that CVC consistently achieves superior fidelity, better semantic alignment, and more reliable editing behavior across diverse tasks.

cs.CV↗

arXiv2026

Dynamic Risk in the U.S. Banking System: An Analysis of Sentiment, Policy Shocks, and Spillover Effects

The 2023 U.S. banking crisis propagated not through direct financial linkages but through a high-frequency, information-based contagion channel. This paper moves beyond exploration analysis to test the "too-similar-to-fail" hypothesis, arguing that risk spillovers were driven by perceived similarities in bank business models under acute interest rate pressure. Employing a Time-Varying Parameter Vector Autoregression (TVP-VAR) model with 30-day rolling windows, a method uniquely suited for capturing the rapid network shifts inherent in a panic, we analyze daily stock returns for the four failed institutions and a systematically selected peer group of surviving banks vulnerable to the same risks from March 18, 2022, to March 15, 2023. Our results provide strong evidence for this contagion channel: total system connectedness surged dramatically during the crisis peak, and we identify SIVB, FRC, and WAL as primary net transmitters of risk while their perceived peers became significant net receivers, a key dynamic indicator of systemic vulnerability that cannot be captured by asset-by-asset analysis. We further demonstrate that these spillovers were significantly amplified by market sentiment (as measured by the VIX) and economic policy uncertainty (EPU). By providing a clear conceptual framework and robust empirical validation, our findings confirm the persistence of systemic risks within the banking network and highlight the importance of real-time monitoring in strengthening financial stability.

econ.EM↗

arXiv2025

Probing Anharmonic Lattice Dynamics and Thermal Transport in Layered Perovskite LiYTiO4 Anode

Layered perovskite lithium yttrium titanate ($\rm LiYTiO_4$) has recently emerged as a promising low-potential, ultrahigh-rate intercalation-type anode material for lithium-ion batteries; however, its lattice dynamics and thermal transport properties remain poorly understood, limiting a complete evaluation of its practical potential. Here, we combine experimental measurements with theoretical modeling to systematically investigate the anharmonic lattice dynamics and heat transport in $\rm LiYTiO_4$. We employ a neural evolution potential (NEP)-based framework that integrates the temperature-dependent effective potential method with the Wigner thermal transport (WTT) formalism, explicitly including both diagonal and off-diagonal terms of the heat-flux operator. Zero-temperature phonon calculations reveal dynamical instabilities associated with $\rm TiO_6$ octahedral rotation, which are stabilized at finite temperatures through anharmonic renormalization. Using the WTT approach with contributions from phonon propagation and coherence contributions, we predict a room-temperature lattice thermal conductivity ($κ_{\rm L}$) of 3.8 $\rm Wm^{-1}K^{-1}$ averaged over all crystal orientations, in close agreement with the measured value of 3.2 \pm 0.08 $\rm Wm^{-1}K^{-1}$ for polycrystalline samples. To further examine the possible influence of ionic motion on high-temperature thermal transport, we compute $κ_{\rm L}$ using a Green-Kubo equilibrium molecular dynamics approach based on the same NEP, which yields consistent results with both experiment and WTT predictions, confirming the negligible role of Li-ion mobility in heat conduction. Our study not only identifies the ultralow thermal conductivity of $\rm LiYTiO_4$ as a key limitation for its practical application but also establishes a reliable computational framework for studying thermal properties in battery materials.

cond-mat.mtrl-sci↗

arXiv2025

Renewable Energy Prediction: A Comparative Study of Deep Learning Models for Complex Dataset Analysis

The increasing focus on predicting renewable energy production aligns with advancements in deep learning (DL). The inherent variability of renewable sources and the complexity of prediction methods require robust approaches, such as DL models, in the renewable energy sector. DL models are preferred over traditional machine learning (ML) because they capture complex, nonlinear relationships in renewable energy datasets. This study examines key factors influencing DL technique accuracy, including sampling and hyperparameter optimization, by comparing various methods and training and test ratios within a DL framework. Seven machine learning methods, LSTM, Stacked LSTM, CNN, CNN-LSTM, DNN, Time-Distributed MLP (TD-MLP), and Autoencoder (AE), are evaluated using a dataset combining weather and photovoltaic power output data from 12 locations. Regularization techniques such as early stopping, neuron dropout, L1 and L2 regularization are applied to address overfitting. The results demonstrate that the combination of early stopping, dropout, and L1 regularization provides the best performance to reduce overfitting in the CNN and TD-MLP models with larger training set, while the combination of early stopping, dropout, and L2 regularization is the most effective to reduce the overfitting in CNN-LSTM and AE models with smaller training set.

cs.LG↗

arXiv2025

Enhancing Reasoning Abilities of Small LLMs with Cognitive Alignment

The reasoning capabilities of large reasoning models (LRMs), such as OpenAI's o1 and DeepSeek-R1, have seen substantial advancements through deep thinking. However, these enhancements come with significant resource demands, underscoring the need for training effective small reasoning models. A critical challenge is that small models possess different reasoning capacities and cognitive trajectories compared with their larger counterparts. Hence, directly distilling chain-of-thought (CoT) rationales from large LRMs to smaller ones can sometimes be ineffective and often requires a substantial amount of annotated data. In this paper, we first introduce a novel Critique-Rethink-Verify (CRV) system, designed for training smaller yet powerful LRMs. Our CRV system consists of multiple LLM agents, each specializing in unique tasks: (i) critiquing the CoT rationales according to the cognitive capabilities of smaller models, (ii) rethinking and refining these CoTs based on the critiques, and (iii) verifying the correctness of the refined results. Building on the CRV system, we further propose the Cognitive Preference Optimization (CogPO) algorithm to continuously enhance the reasoning abilities of smaller models by aligning their reasoning processes with their cognitive capacities. Comprehensive evaluations on challenging reasoning benchmarks demonstrate the efficacy of our CRV+CogPO framework, which outperforms other methods by a large margin.

cs.CL↗

arXiv2025

Thinking with DistilQwen: A Tale of Four Distilled Reasoning and Reward Model Series

Recently, the demand for small and efficient reasoning models to support real-world applications has driven the development of knowledge distillation techniques that balance reasoning performance and inference speed. In this paper, we further extend the DistilQwen model family, initialized from the Qwen models, by introducing four model series specifically designed to meet industrial requirements. The distilled model collection comprises: (1) slow-thinking models, optimized for reasoning tasks that require high accuracy; (2) two series of adaptive-thinking models, which dynamically adjust reasoning strategies based on input tasks to maximize efficiency across diverse scenarios; and (3) distilled reward models, which enable further reinforcement learning of reasoning models using distilled knowledge. Comprehensive evaluations across multiple benchmarks demonstrate both high inference efficiency and strong reasoning performance for these models, as well as the practical utility of distilled reward models. We further show that these models support industry practitioners by providing scalable training and inference functionalities on the Alibaba Cloud PAI (Platform for Artificial Intelligence) platform.

cs.CL↗

arXiv2025

Data-Juicer 2.0: Cloud-Scale Adaptive Data Processing for and with Foundation Models

Foundation models demand advanced data processing for their vast, multimodal datasets. However, traditional frameworks struggle with the unique complexities of multimodal data. In response, we present Data-Juicer 2.0, a data processing system backed by 100+ data processing operators spanning text, image, video, and audio modalities, supporting more critical tasks including data analysis, synthesis, annotation, and foundation model post-training. With seamless compatibility and dedicated optimization for popular dataset hubs like Hugging Face and computing engines like Ray, it improves upon its predecessor in terms of usability, efficiency, and programmability. It features an easily accessible user interface layer that supports decoupled Python interactions, RESTful APIs, and conversational commands. Its new runtime layer offers adaptive execution across diverse scales and environments, abstracting away system complexities. Extensive empirical evaluations demonstrate Data-Juicer 2.0's remarkable performance and scalability, highlighting its capability to efficiently process TB-level data with 10k+ CPU cores. The system is publicly available and has been widely adopted in diverse research fields and real-world products such as Alibaba Cloud PAI. We actively maintain the system and share practical insights to foster research and applications of next-generation foundation models.

cs.DC↗

arXiv2025

Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing

Automated parsing of scanned documents into richly structured, machine-readable formats remains a critical bottleneck in Document AI, as traditional multi-stage pipelines suffer from error propagation and limited adaptability to diverse layouts. We introduce layoutRL, an end-to-end reinforcement learning framework that trains models to be explicitly layout-aware by optimizing a composite reward of normalized edit distance, paragraph count accuracy, and reading order preservation. Leveraging our newly released dataset, Infinity-Doc-55K, which combines 55K high-fidelity synthetic scanned document parsing data with expert-filtered real-world documents, we instantiate layoutRL in a vision-language-model-based parser called Infinity-Parser. Evaluated on English and Chinese benchmarks for OCR, table and formula extraction, and reading order detection, Infinity-Parser achieves new state-of-the-art performance in both accuracy and structural fidelity, outpacing specialist pipelines and general-purpose vision-language models. We will publicly release our code and dataset to accelerate progress in robust document understanding.

cs.CV↗