arXiv subjects

Yiwen Hu

Publications and source records attributed to Yiwen Hu.

At least 19 recordsLinked to original sources

arXiv2026

Structure-Semantic Decoupled Modulation of Global Geospatial Embeddings for High-Resolution Remote Sensing Mapping

Fine-grained high-resolution remote sensing mapping typically relies on localized visual features, which restricts cross-domain generalizability and often leads to fragmented predictions of large-scale land covers. While global geospatial foundation models offer powerful, generalizable representations, directly fusing their high-dimensional implicit embeddings with high-resolution visual features frequently triggers feature interference and spatial structure degradation due to a severe semantic-spatial gap. To overcome these limitations, we propose a Structure-Semantic Decoupled Modulation (SSDM) framework, which decouples global geospatial representations into two complementary cross-modal injection pathways. First, the structural prior modulation branch introduces the macroscopic receptive field priors from global representations into the self-attention modules of the high-resolution encoder. By guiding local feature extraction with holistic structural constraints, it effectively suppresses prediction fragmentation caused by high-frequency detail noise and excessive intra-class variance. Second, the global semantic injection branch explicitly aligns holistic context with the deep high-resolution feature space and directly supplements global semantics via cross-modal integration, thereby significantly enhancing the semantic consistency and category-level discrimination of complex land covers. Extensive experiments demonstrate that our method achieves state-of-the-art performance compared to existing cross-modal fusion approaches. By unleashing the potential of global embeddings, SSDM consistently improves high-resolution mapping accuracy across diverse scenarios, providing a universal and effective paradigm for integrating geospatial foundation models into high-resolution vision tasks.

cs.CV↗

arXiv2026

Multi-Swing Transient Stability of Synchronous Generators and IBR Combined Generation Systems

In traditional views, the build-up of accelerating energy during faults can cause the well-known first-swing angle instability in synchronous generators (SGs). Interestingly, this letter presents a new insight that the accumulation of decelerating energy due to the low voltage ride-through (LVRT) and recovery control of grid-following inverter-based resources (GFL-IBRs), might also result in transient angle instability in SGs. The transient energy accumulated during angle-decreasing swing transforms into the acceleration energy of the subsequent swing, hence such phenomena often manifest as multi-swing instability. Both theoretical analysis and simulation support these findings.

eess.SY↗

arXiv2026

Entire Period Transient Stability of Synchronous Generators Considering LVRT Switching of Nearby Renewable Energy Sources

In scenarios where synchronous generators (SGs) and grid-following renewable energy sources (GFLR) are co-located, existing research, which mainly focuses on the first-swing stability of SGs, often overlooks ongoing dynamic interactions between GFLRs and SGs throughout the entire rotor swing period. To address this gap, this study first reveals that the angle oscillations of SG can cause periodic grid voltage fluctuations, potentially triggering low-voltage ride-through (LVRT) control switching of GFLR repeatedly. Then, the periodic energy changes of SGs under "circular" and "rectangular" LVRT limits are analyzed. The results indicate that circular limits are detrimental to SG's first-swing stability, while rectangular limits and their slow recovery strategies can lead to SG's multi-swing instability. Conservative stability criteria are also proposed for these phenomena. Furthermore, an additional controller based on feedback linearization is introduced to enhance the entire period transient stability of SG by adjusting the post-fault GFLR output current. Finally, the efficacy of the analysis is validated through electromagnetic transient simulations and controller hardware-in-the-loop (CHIL) tests.

eess.SY↗

arXiv2026

Controlled LLM Training on Spectral Sphere

Scaling large models requires optimization strategies that ensure rapid convergence grounded in stability. Maximal Update Parametrization ($\boldsymbolμ$P) provides a theoretical safeguard for width-invariant $Θ(1)$ activation control, whereas emerging optimizers like Muon are only ``half-aligned'' with these constraints: they control updates but allow weights to drift. To address this limitation, we introduce the \textbf{Spectral Sphere Optimizer (SSO)}, which enforces strict module-wise spectral constraints on both weights and their updates. By deriving the steepest descent direction on the spectral sphere, SSO realizes a fully $\boldsymbolμ$P-aligned optimization process. To enable large-scale training, we implement SSO as an efficient parallel algorithm within Megatron. Through extensive pretraining on diverse architectures, including Dense 1.7B, MoE 8B-A1B, and 200-layer DeepNet models, SSO consistently outperforms AdamW and Muon. Furthermore, we observe significant practical stability benefits, including improved MoE router load balancing, suppressed outliers, and strictly bounded activations.

cs.LG↗

arXiv2026

SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training

In this technical report, we present SWE-Master, an open-source and fully reproducible post-training framework for building effective software engineering agents. SWE-Master systematically explores the complete agent development pipeline, including teacher-trajectory synthesis and data curation, long-horizon SFT, RL with real execution feedback, and inference framework design. Starting from an open-source base model with limited initial SWE capability, SWE-Master demonstrates how systematical optimization method can elicit strong long-horizon SWE task solving abilities. We evaluate SWE-Master on SWE-bench Verified, a standard benchmark for realistic software engineering tasks. Under identical experimental settings, our approach achieves a resolve rate of 61.4\% with Qwen2.5-Coder-32B, substantially outperforming existing open-source baselines. By further incorporating test-time scaling~(TTS) with LLM-based environment feedback, SWE-Master reaches 70.8\% at TTS@8, demonstrating a strong performance potential. SWE-Master provides a practical and transparent foundation for advancing reproducible research on software engineering agents. The code is available at https://github.com/RUCAIBox/SWE-Master.

cs.SE↗

arXiv2026

SWE-World: Building Software Engineering Agents in Docker-Free Environments

Recent advances in large language models (LLMs) have enabled software engineering agents to tackle complex code modification tasks. Most existing approaches rely on execution feedback from containerized environments, which require dependency-complete setup and physical execution of programs and tests. While effective, this paradigm is resource-intensive and difficult to maintain, substantially complicating agent training and limiting scalability. We propose SWE-World, a Docker-free framework that replaces physical execution environments with a learned surrogate for training and evaluating software engineering agents. SWE-World leverages LLM-based models trained on real agent-environment interaction data to predict intermediate execution outcomes and final test feedback, enabling agents to learn without interacting with physical containerized environments. This design preserves the standard agent-environment interaction loop while eliminating the need for costly environment construction and maintenance during agent optimization and evaluation. Furthermore, because SWE-World can simulate the final evaluation outcomes of candidate trajectories without real submission, it enables selecting the best solution among multiple test-time attempts, thereby facilitating effective test-time scaling (TTS) in software engineering tasks. Experiments on SWE-bench Verified demonstrate that SWE-World raises Qwen2.5-Coder-32B from 6.2\% to 52.0\% via Docker-free SFT, 55.0\% with Docker-free RL, and 68.2\% with further TTS. The code is available at https://github.com/RUCAIBox/SWE-World

cs.SE↗

arXiv2026

CellularSpecSec-Bench: A Staged Benchmark for Evidence-Grounded Interpretation and Security Reasoning over 3GPP Specifications

Cellular networks are critical infrastructure supporting billions of worldwide users and safety- and mission-critical services. Vulnerabilities in cellular networks can therefore cause service disruption, privacy breaches, and broad societal harm, motivating growing efforts to analyze 3GPP specifications that define required device and operator behavior. While large language models (LLMs) have demonstrated the capability for reading technical documents, cellular specifications impose unique challenges: faithful interpretation of normative language, reasoning across cross-referenced clauses, and verifiable conclusions grounded in multimodal evidence such as tables and figures. To address these challenges, we propose CellSpecSec-ARI, a unified Adapt-Retrieve-Integrate framework for systematic understanding and standard-driven security analysis of 3GPP specifications; CellularSpecSec-Bench, a staged benchmark, containing newly constructed high-quality datasets with expert-verified and corrected subsets from prior open-source resources. Together, they establish an accessible and reproducible foundation for quantifying progress in specification understanding and security reasoning in the cellular network security domain.

cs.CR↗

arXiv2025

CellSecInspector: Safeguarding Cellular Networks via Automated Security Analysis on Specifications

The complexity, interdependence, and rapid evolution of 3GPP specifications present fundamental challenges for ensuring the security of modern cellular networks. Manual reviews and existing automated approaches, which often depend on rule-based parsing or small sets of manually crafted security requirements, fail to capture deep semantic dependencies, cross-sentence/clause relationships, and evolving specification behaviors. In this work, we present CellSecInspector, an automated framework for security analysis of 3GPP specifications. CellSecInspector extracts structured state-condition-action (SCA) representations, models mobile network procedures with comprehensive function chains, systematically validates them against 9 foundational security properties under 4 adversarial scenarios, and automatically generates test cases. This end-to-end approach enables the automated discovery of vulnerabilities without relying on manually predefined security requirements or rules. Applying CellSecInspector to the well-studied 5G and 4G NAS and RRC specifications and selected sections of TS 23.501 and TS 24.229, it discovers 43 vulnerabilities, 7 of which are previously unreported. Our findings show that CellSecInspector is a scalable, adaptive, and effective solution to assess 3GPP specifications for safeguarding operational and next-generation cellular networks.

cs.CR↗

arXiv2025

ReaSeq: Unleashing World Knowledge via Reasoning for Sequential Modeling

Industrial recommender systems face two fundamental limitations under the log-driven paradigm: (1) knowledge poverty in ID-based item representations that causes brittle interest modeling under data sparsity, and (2) systemic blindness to beyond-log user interests that constrains model performance within platform boundaries. These limitations stem from an over-reliance on shallow interaction statistics and close-looped feedback while neglecting the rich world knowledge about product semantics and cross-domain behavioral patterns that Large Language Models have learned from vast corpora. To address these challenges, we introduce ReaSeq, a reasoning-enhanced framework that leverages world knowledge in Large Language Models to address both limitations through explicit and implicit reasoning. Specifically, ReaSeq employs explicit Chain-of-Thought reasoning via multi-agent collaboration to distill structured product knowledge into semantically enriched item representations, and latent reasoning via Diffusion Large Language Models to infer plausible beyond-log behaviors. Deployed on Taobao's ranking system serving hundreds of millions of users, ReaSeq achieves substantial gains: >6.0% in IPV and CTR, >2.9% in Orders, and >2.5% in GMV, validating the effectiveness of world-knowledge-enhanced reasoning over purely log-driven approaches.

cs.IR↗

arXiv2025

Entropy-Guided Token Dropout: Training Autoregressive Language Models with Limited Domain Data

As access to high-quality, domain-specific data grows increasingly scarce, multi-epoch training has become a practical strategy for adapting large language models (LLMs). However, autoregressive models often suffer from performance degradation under repeated data exposure, where overfitting leads to a marked decline in model capability. Through empirical analysis, we trace this degradation to an imbalance in learning dynamics: predictable, low-entropy tokens are learned quickly and come to dominate optimization, while the model's ability to generalize on high-entropy tokens deteriorates with continued training. To address this, we introduce EntroDrop, an entropy-guided token dropout method that functions as structured data regularization. EntroDrop selectively masks low-entropy tokens during training and employs a curriculum schedule to adjust regularization strength in alignment with training progress. Experiments across model scales from 0.6B to 8B parameters show that EntroDrop consistently outperforms standard regularization baselines and maintains robust performance throughout extended multi-epoch training. These findings underscore the importance of aligning regularization with token-level learning dynamics when training on limited data. Our approach offers a promising pathway toward more effective adaptation of LLMs in data-constrained domains.

cs.CL↗

arXiv2025

From Pretraining to Privacy: Federated Ultrasound Foundation Model with Self-Supervised Learning

Ultrasound imaging is widely used in clinical diagnosis due to its non-invasive nature and real-time capabilities. However, traditional ultrasound diagnostics relies heavily on physician expertise and is often hampered by suboptimal image quality, leading to potential diagnostic errors. While artificial intelligence (AI) offers a promising solution to enhance clinical diagnosis by detecting abnormalities across various imaging modalities, existing AI methods for ultrasound face two major challenges. First, they typically require vast amounts of labeled medical data, raising serious concerns regarding patient privacy. Second, most models are designed for specific tasks, which restricts their broader clinical utility. To overcome these challenges, we present UltraFedFM, an innovative privacy-preserving ultrasound foundation model. UltraFedFM is collaboratively pre-trained using federated learning across 16 distributed medical institutions in 9 countries, leveraging a dataset of over 1 million ultrasound images covering 19 organs and 10 ultrasound modalities. This extensive and diverse data, combined with a secure training framework, enables UltraFedFM to exhibit strong generalization and diagnostic capabilities. It achieves an average area under the receiver operating characteristic curve (AUROC) of 0.927 for disease diagnosis and a dice similarity coefficient (DSC) of 0.878 for lesion segmentation. Notably, UltraFedFM surpasses the diagnostic accuracy of mid-level ultrasonographers (4-8 years of experience) and matches the performance of expert-level sonographers (10+ years of experience) in the joint diagnosis of 8 common systemic diseases.c These findings indicate that UltraFedFM can significantly enhance clinical diagnostics while safeguarding patient privacy, marking a significant advancement in AI-driven ultrasound imaging for future clinical applications.

eess.IV↗

arXiv2025

Multi-Task Temporal Fusion Transformer for Joint Sales and Inventory Forecasting in Amazon E-Commerce Supply Chain

Efficient inventory management and accurate sales forecasting are critical challenges in large-scale e-commerce platforms such as Amazon, where stockouts and overstocking can lead to substantial financial losses and operational inefficiencies. Traditional single-task forecasting models, which focus solely on sales or inventory, often fail to capture the complex temporal dependencies and cross-task interactions that characterize real-world supply chain dynamics. To address this limitation, this study proposes a Multi-Task Temporal Fusion Transformer (TFT-MTL) framework designed for joint sales and inventory forecasting within the Amazon e-commerce ecosystem. The model integrates heterogeneous data sources, including historical sales records, warehouse inventory levels, pricing, promotions, and event-driven factors such as holidays and Prime Day campaigns, through a unified deep learning architecture. A shared encoder captures long-term temporal patterns, while task-specific decoder heads predict sales volume, inventory turnover, and stockout probability simultaneously. Experiments on large-scale real-world datasets demonstrate that the proposed TFT-MTL model significantly outperforms baseline methods such as LSTM, GRU, and single-task TFT. Compared with the single-task TFT model, the proposed approach achieves a 6.2% reduction in Sales RMSE, a 12.7% decrease in Sales MAPE, a 6.4% reduction in Inventory RMSE, and a 12.4% decrease in Inventory MAPE. These results confirm the model's ability to effectively capture multi-dimensional dependencies across supply chain variables. The proposed framework provides an interpretable, data-driven decision support tool for optimizing Amazon's inventory scheduling and demand planning strategies.

cs.CE↗

arXiv2025

A FEDformer-Based Hybrid Framework for Anomaly Detection and Risk Forecasting in Financial Time Series

Financial markets are inherently volatile and prone to sudden disruptions such as market crashes, flash collapses, and liquidity crises. Accurate anomaly detection and early risk forecasting in financial time series are therefore crucial for preventing systemic instability and supporting informed investment decisions. Traditional deep learning models, such as LSTM and GRU, often fail to capture long-term dependencies and complex periodic patterns in highly nonstationary financial data. To address this limitation, this study proposes a FEDformer-Based Hybrid Framework for Anomaly Detection and Risk Forecasting in Financial Time Series, which integrates the Frequency Enhanced Decomposed Transformer (FEDformer) with a residual-based anomaly detector and a risk forecasting head. The FEDformer module models temporal dynamics in both time and frequency domains, decomposing signals into trend and seasonal components for improved interpretability. The residual-based detector identifies abnormal fluctuations by analyzing prediction errors, while the risk head predicts potential financial distress using learned latent embeddings. Experiments conducted on the S&P 500, NASDAQ Composite, and Brent Crude Oil datasets (2000-2024) demonstrate the superiority of the proposed model over benchmark methods, achieving a 15.7 percent reduction in RMSE and an 11.5 percent improvement in F1-score for anomaly detection. These results confirm the effectiveness of the model in capturing financial volatility, enabling reliable early-warning systems for market crash prediction and risk management.

cs.LG↗

arXiv2025

RecIS: Sparse to Dense, A Unified Training Framework for Recommendation Models

In this paper, we propose RecIS, a unified Sparse-Dense training framework designed to achieve two primary goals: 1. Unified Framework To create a Unified sparse-dense training framework based on the PyTorch ecosystem that meets the training needs of industrial-grade recommendation models that integrated with large models. 2.System Optimization To optimize the sparse component, offering superior efficiency over the TensorFlow-based recommendation models. The dense component, meanwhile, leverages existing optimization technologies within the PyTorch ecosystem. Currently, RecIS is being used in Alibaba for numerous large-model enhanced recommendation training tasks, and some traditional sparse models have also begun training in it.

cs.IR↗

arXiv2025

ICPC-Eval: Probing the Frontiers of LLM Reasoning with Competitive Programming Contests

With the significant progress of large reasoning models in complex coding and reasoning tasks, existing benchmarks, like LiveCodeBench and CodeElo, are insufficient to evaluate the coding capabilities of large language models (LLMs) in real competition environments. Moreover, current evaluation metrics such as Pass@K fail to capture the reflective abilities of reasoning models. To address these challenges, we propose \textbf{ICPC-Eval}, a top-level competitive coding benchmark designed to probing the frontiers of LLM reasoning. ICPC-Eval includes 118 carefully curated problems from 11 recent ICPC contests held in various regions of the world, offering three key contributions: 1) A challenging realistic ICPC competition scenario, featuring a problem type and difficulty distribution consistent with actual contests. 2) A robust test case generation method and a corresponding local evaluation toolkit, enabling efficient and accurate local evaluation. 3) An effective test-time scaling evaluation metric, Refine@K, which allows iterative repair of solutions based on execution feedback. The results underscore the significant challenge in evaluating complex reasoning abilities: top-tier reasoning models like DeepSeek-R1 often rely on multi-turn code feedback to fully unlock their in-context reasoning potential when compared to non-reasoning counterparts. Furthermore, despite recent advancements in code generation, these models still lag behind top-performing human teams. We release the benchmark at: https://github.com/RUCAIBox/Slow_Thinking_with_LLMs

cs.CL↗

arXiv2025

MARIO: A Mixed Annotation Framework For Polyp Segmentation

Existing polyp segmentation models are limited by high labeling costs and the small size of datasets. Additionally, vast polyp datasets remain underutilized because these models typically rely on a single type of annotation. To address this dilemma, we introduce MARIO, a mixed supervision model designed to accommodate various annotation types, significantly expanding the range of usable data. MARIO learns from underutilized datasets by incorporating five forms of supervision: pixel-level, box-level, polygon-level, scribblelevel, and point-level. Each form of supervision is associated with a tailored loss that effectively leverages the supervision labels while minimizing the noise. This allows MARIO to move beyond the constraints of relying on a single annotation type. Furthermore, MARIO primarily utilizes dataset with weak and cheap annotations, reducing the dependence on large-scale, fully annotated ones. Experimental results across five benchmark datasets demonstrate that MARIO consistently outperforms existing methods, highlighting its efficacy in balancing trade-offs between different forms of supervision and maximizing polyp segmentation performance

cs.CV↗

arXiv2025

Research on stock price forecast of general electric based on mixed CNN-LSTM model

Accurate stock price prediction is crucial for investors and financial institutions, yet the complexity of the stock market makes it highly challenging. This study aims to construct an effective model to enhance the prediction ability of General Electric's stock price trend. The CNN - LSTM model is adopted, combining the feature extraction ability of CNN with the long - term dependency handling ability of LSTM, and the Adam optimizer is used to adjust the parameters. In the data preparation stage, historical trading data of General Electric's stock is collected. After cleaning, handling missing values, and feature engineering, features with strong correlations to the closing price are selected and dimensionality reduction is performed. During model training, the data is divided into training, validation, and testing sets in a ratio of 7:2:1. The Stochastic Gradient Descent algorithm is used with a dynamic learning rate adjustment and L2 regularization, and the Mean Squared Error is used as the loss function, evaluated by variance, R - squared score, and maximum error. Experimental results show that the model loss decreases steadily, and the predicted values align well with the actual values, providing a powerful tool for investment decisions. However, the model's performance in real - time and extreme market conditions remains to be tested, and future improvements could consider incorporating more data sources.

cs.CE↗

arXiv2024

YuLan-Mini: An Open Data-efficient Language Model

Effective pre-training of large language models (LLMs) has been challenging due to the immense resource demands and the complexity of the technical processes involved. This paper presents a detailed technical report on YuLan-Mini, a highly capable base model with 2.42B parameters that achieves top-tier performance among models of similar parameter scale. Our pre-training approach focuses on enhancing training efficacy through three key technical contributions: an elaborate data pipeline combines data cleaning with data schedule strategies, a robust optimization method to mitigate training instability, and an effective annealing approach that incorporates targeted data selection and long context training. Remarkably, YuLan-Mini, trained on 1.08T tokens, achieves performance comparable to industry-leading models that require significantly more data. To facilitate reproduction, we release the full details of the data composition for each training phase. Project details can be accessed at the following link: https://github.com/RUC-GSAI/YuLan-Mini.

cs.CL↗