arXiv subjects

Di Wu

Publications and source records attributed to Di Wu.

At least 253 records · Page 14Linked to original sources

arXiv2025

Geometric-Perturbation-Robust Cut-Cell Scheme for Two-Material Flows: Exact Pressure-Equilibrium Preservation and Rigorous Analysis

Preserving pressure equilibrium across material interfaces is critical for the stability of compressible multi-material flow simulations, yet most interface-fitted sharp-interface schemes are notoriously sensitive to interface geometry: even slight perturbations of the captured (or tracked) interface can trigger large spurious pressure oscillations. We present a cut-cell method that is geometric-perturbation-robust (GPR) for the compressible two-material flows. By construction, the scheme provably preserves exact interfacial pressure equilibrium in the presence of small interface-position errors. The key is a strict consistency between the conserved variables and the geometric moments (i.e., the integrals of monomials) of every cut cell. We formulate auxiliary transport equations, whose discrete solutions furnish evolved geometric moment, these geometric moments remain perfectly synchronized with the conserved variables -- even on a deforming mesh. Surpassing the classical geometric conservation law, our approach keeps all higher-order geometric moments consistent, thereby eliminating accuracy loss due to geometric mismatches. To prevent the reconstruction step from destroying pressure equilibrium, we introduce the notion of equilibrium-compatible (EC) reconstructions. A carefully designed modification equips any conventional weighted essentially non-oscillatory (WENO) reconstruction with the EC property; we detail a third-order EC multi-resolution WENO (EC-MRWENO) variant. The tight coupling of EC-MRWENO with the evolved moments yields the first cut-cell solver that is simultaneously provably GPR and genuinely high-order: it attains second-order accuracy precisely at material interfaces, while preserving third-order accuracy in smooth regions. Extensive two-dimensional tests confirm the framework's robustness, accuracy and stability under geometric perturbations and topology changes.

math.NA↗

arXiv2025

Deep Koopman Learning of Nonlinear Time-Varying Systems

This paper presents a data-driven approach to approximate the dynamics of a nonlinear time-varying system (NTVS) by a linear time-varying system (LTVS), which is resulted from the Koopman operator and deep neural networks. Analysis of the approximation error between states of the NTVS and the resulting LTVS is presented. Simulations on a representative NTVS show that the proposed method achieves small approximation errors, even when the system changes rapidly. Furthermore, simulations in an example of quadcopters demonstrate the computational efficiency of the proposed approach.

eess.SY↗

arXiv2025

LONGER: Scaling Up Long Sequence Modeling in Industrial Recommenders

Modeling ultra-long user behavior sequences is critical for capturing both long- and short-term preferences in industrial recommender systems. Existing solutions typically rely on two-stage retrieval or indirect modeling paradigms, incuring upstream-downstream inconsistency and computational inefficiency. In this paper, we present LONGER, a Long-sequence Optimized traNsformer for GPU-Efficient Recommenders. LONGER incorporates (i) a global token mechanism for stabilizing attention over long contexts, (ii) a token merge module with lightweight InnerTransformers and hybrid attention strategy to reduce quadratic complexity, and (iii) a series of engineering optimizations, including training with mixed-precision and activation recomputation, KV cache serving, and the fully synchronous model training and serving framework for unified GPU-based dense and sparse parameter updates. LONGER consistently outperforms strong baselines in both offline metrics and online A/B testing in both advertising and e-commerce services at ByteDance, validating its consistent effectiveness and industrial-level scaling laws. Currently, LONGER has been fully deployed at more than 10 influential scenarios at ByteDance, serving billion users.

cs.IR↗

arXiv2025

Extension OL-MDISF: Online Learning from Mix-Typed, Drifted, and Incomplete Streaming Features

Online learning, where feature spaces can change over time, offers a flexible learning paradigm that has attracted considerable attention. However, it still faces three significant challenges. First, the heterogeneity of real-world data streams with mixed feature types presents challenges for traditional parametric modeling. Second, data stream distributions can shift over time, causing an abrupt and substantial decline in model performance. Additionally, the time and cost constraints make it infeasible to label every data instance in a supervised setting. To overcome these challenges, we propose a new algorithm Online Learning from Mix-typed, Drifted, and Incomplete Streaming Features (OL-MDISF), which aims to relax restrictions on both feature types, data distribution, and supervision information. Our approach involves utilizing copula models to create a comprehensive latent space, employing an adaptive sliding window for detecting drift points to ensure model stability, and establishing label proximity information based on geometric structural relationships. To demonstrate the model's efficiency and effectiveness, we provide theoretical analysis and comprehensive experimental results. This extension serves as a standalone technical reference to the original OL-MDISF method. It provides (i) a contextual analysis of OL-MDISF within the broader landscape of online learning, covering recent advances in mixed-type feature modeling, concept drift adaptation, and weak supervision, and (ii) a comprehensive set of experiments across 14 real-world datasets under two types of drift scenarios. These include full CER trends, ablation studies, sensitivity analyses, and temporal ensemble dynamics. We hope this document can serve as a reproducible benchmark and technical resource for researchers working on nonstationary, heterogeneous, and weakly supervised data streams.

cs.LG↗

arXiv2025

Reinforced Reasoning for Embodied Planning

Embodied planning requires agents to make coherent multi-step decisions based on dynamic visual observations and natural language goals. While recent vision-language models (VLMs) excel at static perception tasks, they struggle with the temporal reasoning, spatial understanding, and commonsense grounding needed for planning in interactive environments. In this work, we introduce a reinforcement fine-tuning framework that brings R1-style reasoning enhancement into embodied planning. We first distill a high-quality dataset from a powerful closed-source model and perform supervised fine-tuning (SFT) to equip the model with structured decision-making priors. We then design a rule-based reward function tailored to multi-step action quality and optimize the policy via Generalized Reinforced Preference Optimization (GRPO). Our approach is evaluated on Embench, a recent benchmark for interactive embodied tasks, covering both in-domain and out-of-domain scenarios. Experimental results show that our method significantly outperforms models of similar or larger scale, including GPT-4o-mini and 70B+ open-source baselines, and exhibits strong generalization to unseen environments. This work highlights the potential of reinforcement-driven reasoning to advance long-horizon planning in embodied AI.

cs.AI↗

arXiv2025

Optimal Power Management of Battery Energy Storage Systems via Ensemble Kalman Inversion

Optimal power management of battery energy storage systems (BESS) is crucial for their safe and efficient operation. Numerical optimization techniques are frequently utilized to solve the optimal power management problems. However, these techniques often fall short of delivering real-time solutions for large-scale BESS due to their computational complexity. To address this issue, this paper proposes a computationally efficient approach. We introduce a new set of decision variables called power-sharing ratios corresponding to each cell, indicating their allocated power share from the output power demand. We then formulate an optimal power management problem to minimize the system-wide power losses while ensuring compliance with safety, balancing, and power supply-demand match constraints. To efficiently solve this problem, a parameterized control policy is designed and leveraged to transform the optimal power management problem into a parameter estimation problem. We then implement the ensemble Kalman inversion to estimate the optimal parameter set. The proposed approach significantly reduces computational requirements due to 1) the much lower dimensionality of the decision parameters and 2) the estimation treatment of the optimal power management problem. Finally, we conduct extensive simulations to validate the effectiveness of the proposed approach. The results show promise in accuracy and computation time compared with explored numerical optimization techniques.

eess.SY↗

arXiv2025

Dual State-space Fidelity Blade (D-STAB): A Novel Stealthy Cyber-physical Attack Paradigm

This paper presents a novel cyber-physical attack paradigm, termed the Dual State-Space Fidelity Blade (D-STAB), which targets the firmware of core cyber-physical components as a new class of attack surfaces. The D-STAB attack exploits the information asymmetry caused by the fidelity gap between high-fidelity and low-fidelity physical models in cyber-physical systems. By designing precise adversarial constraints based on high-fidelity state-space information, the attack induces deviations in high-fidelity states that remain undetected by defenders relying on low-fidelity observations. The effectiveness of D-STAB is demonstrated through a case study in cyber-physical battery systems, specifically in an optimal charging task governed by a Battery Management System (BMS).

eess.SY↗

arXiv2025

AI-based Environment-Aware XL-MIMO Channel Estimation with Location-Specific Prior Knowledge Enabled by CKM

Accurate and efficient acquisition of wireless channel state information (CSI) is crucial to enhance the communication performance of wireless systems. However, with the continuous densification of wireless links, increased channel dimensions, and the use of higher-frequency bands, channel estimation in the sixth generation (6G) and beyond wireless networks faces new challenges, such as insufficient orthogonal pilot sequences, inadequate signal-to-noise ratio (SNR) for channel training, and more sophisticated channel statistical distributions in complex environment. These challenges pose significant difficulties for classical channel estimation algorithms like least squares (LS) and maximum a posteriori (MAP). To address this problem, we propose a novel environment-aware channel estimation framework with location-specific prior channel distribution enabled by the new concept of channel knowledge map (CKM). To this end, we propose a new type of CKM called channel score function map (CSFM), which learns the channel probability density function (PDF) using artificial intelligence (AI) techniques. To fully exploit the prior information in CSFM, we propose a plug-and-play (PnP) based algorithm to decouple the regularized MAP channel estimation problem, thereby reducing the complexity of the optimization process. Besides, we employ Tweedie's formula to establish a connection between the channel score function, defined as the logarithmic gradient of the channel PDF, and the channel denoiser. This allows the use of the high-precision, environment-aware channel denoiser from the CSFM to approximate the channel score function, thus enabling efficient processing of the decoupled channel statistical components. Simulation results show that the proposed CSFM-PnP based channel estimation technique significantly outperforms the conventional techniques in the aforementioned challenging scenarios.

eess.SP↗

arXiv2025

Multi-Branch DNN and CRLB-Ratio-Weight Fusion for Enhanced DOA Sensing via a Massive H$^2$AD MIMO Receiver

As a green MIMO structure, massive H$^2$AD is viewed as a potential technology for the future 6G wireless network. For such a structure, it is a challenging task to design a low-complexity and high-performance fusion of target direction values sensed by different sub-array groups with fewer use of prior knowledge. To address this issue, a lightweight Cramer-Rao lower bound (CRLB)-ratio-weight fusion (WF) method is proposed, which approximates inverse CRLB of each subarray using antenna number reciprocals to eliminate real-time CRLB computation. This reduces complexity and prior knowledge dependence while preserving fusion performance. Moreover, a multi-branch deep neural network (MBDNN) is constructed to further enhance direction-of-arrival (DOA) sensing by leveraging candidate angles from multiple subarrays. The subarray-specific branch networks are integrated with a shared regression module to effectively eliminate pseudo-solutions and fuse true angles. Simulation results show that the proposed CRLB-ratio-WF method achieves DOA sensing performance comparable to CRLB-based methods, while significantly reducing the reliance on prior knowledge. More notably, the proposed MBDNN has superior performance in low-SNR ranges. At SNR $= -15$ dB, it achieves an order-of-magnitude improvement in estimation accuracy compared to CRLB-ratio-WF method.

eess.SP↗

arXiv2025

A Survey on Soft Robot Adaptability: Implementations, Applications, and Prospects

Soft robots, compared to rigid robots, possess inherent advantages, including higher degrees of freedom, compliance, and enhanced safety, which have contributed to their increasing application across various fields. Among these benefits, adaptability is particularly noteworthy. In this paper, adaptability in soft robots is categorized into external and internal adaptability. External adaptability refers to the robot's ability to adjust, either passively or actively, to variations in environments, object properties, geometries, and task dynamics. Internal adaptability refers to the robot's ability to cope with internal variations, such as manufacturing tolerances or material aging, and to generalize control strategies across different robots. As the field of soft robotics continues to evolve, the significance of adaptability has become increasingly pronounced. In this review, we summarize various approaches to enhancing the adaptability of soft robots, including design, sensing, and control strategies. Additionally, we assess the impact of adaptability on applications such as surgery, wearable devices, locomotion, and manipulation. We also discuss the limitations of soft robotics adaptability and prospective directions for future research. By analyzing adaptability through the lenses of implementation, application, and challenges, this paper aims to provide a comprehensive understanding of this essential characteristic in soft robotics and its implications for diverse applications.

cs.RO↗

arXiv2025

MalGuard: Towards Real-Time, Accurate, and Actionable Detection of Malicious Packages in PyPI Ecosystem

Malicious package detection has become a critical task in ensuring the security and stability of the PyPI. Existing detection approaches have focused on advancing model selection, evolving from traditional machine learning (ML) models to large language models (LLMs). However, as the complexity of the model increases, the time consumption also increases, which raises the question of whether a lightweight model achieves effective detection. Through empirical research, we demonstrate that collecting a sufficiently comprehensive feature set enables even traditional ML models to achieve outstanding performance. However, with the continuous emergence of new malicious packages, considerable human and material resources are required for feature analysis. Also, traditional ML model-based approaches lack of explainability to malicious packages.Therefore, we propose a novel approach MalGuard based on graph centrality analysis and the LIME (Local Interpretable Model-agnostic Explanations) algorithm to detect malicious packages.To overcome the above two challenges, we leverage graph centrality analysis to extract sensitive APIs automatically to replace manual analysis. To understand the sensitive APIs, we further refine the feature set using LLM and integrate the LIME algorithm with ML models to provide explanations for malicious packages. We evaluated MalGuard against six SOTA baselines with the same settings. Experimental results show that our proposed MalGuard, improves precision by 0.5%-33.2% and recall by 1.8%-22.1%. With MalGuard, we successfully identified 113 previously unknown malicious packages from a pool of 64,348 newly-uploaded packages over a five-week period, and 109 out of them have been removed by the PyPI official.

cs.CR↗

arXiv2025

MogaNet: Multi-order Gated Aggregation Network

By contextualizing the kernel as global as possible, Modern ConvNets have shown great potential in computer vision tasks. However, recent progress on multi-order game-theoretic interaction within deep neural networks (DNNs) reveals the representation bottleneck of modern ConvNets, where the expressive interactions have not been effectively encoded with the increased kernel size. To tackle this challenge, we propose a new family of modern ConvNets, dubbed MogaNet, for discriminative visual representation learning in pure ConvNet-based models with favorable complexity-performance trade-offs. MogaNet encapsulates conceptually simple yet effective convolutions and gated aggregation into a compact module, where discriminative features are efficiently gathered and contextualized adaptively. MogaNet exhibits great scalability, impressive efficiency of parameters, and competitive performance compared to state-of-the-art ViTs and ConvNets on ImageNet and various downstream vision benchmarks, including COCO object detection, ADE20K semantic segmentation, 2D&3D human pose estimation, and video prediction. Notably, MogaNet hits 80.0% and 87.8% accuracy with 5.2M and 181M parameters on ImageNet-1K, outperforming ParC-Net and ConvNeXt-L, while saving 59% FLOPs and 17M parameters, respectively. The source code is available at https://github.com/Westlake-AI/MogaNet.

cs.CV↗

arXiv2025

Large Language Model (LLM)-enabled In-context Learning for Wireless Network Optimization: A Case Study of Power Control

Large language model (LLM) has recently been considered a promising technique for many fields. This work explores LLM-based wireless network optimization via in-context learning. To showcase the potential of LLM technologies, we consider the base station (BS) power control as a case study, a fundamental but crucial technique that is widely investigated in wireless networks. Different from existing machine learning (ML) methods, our proposed in-context learning algorithm relies on LLM's inference capabilities. It avoids the complexity of tedious model training and hyper-parameter fine-tuning, which is a well-known bottleneck of many ML algorithms. Specifically, the proposed algorithm first describes the target task via formatted natural language, and then designs the in-context learning framework and demonstration examples. After that, it considers two cases, namely discrete-state and continuous-state problems, and proposes state-based and ranking-based methods to select appropriate examples for these two cases, respectively. Finally, the simulations demonstrate that the proposed algorithm can achieve comparable performance as conventional deep reinforcement learning (DRL) techniques without dedicated model training or fine-tuning. Such an efficient and low-complexity approach has great potential for future wireless network optimization.

eess.SY↗

arXiv2025

Lorentz violation signatures in the low-energy sector of Hořava gravity from black hole shadow observations

In this paper, we use the Hořava gravity model and EHT observations of supermassive black holes (BHs) to investigate signatures of Lorentz violation in real astrophysical environments. The Lorentz violation in the rotating Hořava BH spacetime are confined to the strong gravitational field region, being induced by the BH's rotation. Due to the non-separability of the photon motion equations in this spacetime, we employed a numerical backward ray-tracing method to generate shadow images for various BH parameters. Subsequently, we extracted coordinate positions characterizing the shadow shape from high-pixel images to evaluate the parameter space of the BH. When evaluating M87*, Lorentz violation can occur with arbitrary strength. However, for Sgr A*, we can impose certain parameter constraints on Lorentz violation. These constraints depend on the BH's spin. If future observations confirm Sgr A*'s spin parameter less than 0.81 at maximum inclination, current EHT results would challenge general relativity and support Lorentz violation in low-energy regimes.

gr-qc↗

arXiv2025

Leveraging Photonic Interconnects for Scalable and Efficient Fully Homomorphic Encryption

Fully Homomorphic Encryption (FHE) facilitates secure computations on encrypted data but imposes significant demands on memory bandwidth and computational power. While current FHE accelerators focus on optimizing computation, they often face bandwidth limitations that result in performance bottlenecks, particularly in memory-intensive operations. This paper presents OptoLink, a scalable photonic interconnect architecture designed to address these bandwidth and latency challenges in FHE systems. OptoLink achieves a throughput of 1.6 TB/s with 128 channels, providing 300 times the bandwidth of conventional electrical interconnects. The proposed architecture improves data throughput, scalability, and reduces latency, making it an effective solution for meeting the high memory and data transfer requirements of modern FHE accelerators.

cs.ET↗

arXiv2025

Learning-Based Stable Optimal Control for Infinite-Time Nonlinear Regulation Problems

Infinite-time nonlinear optimal regulation control is widely utilized in aerospace engineering as a systematic method for synthesizing stable controllers. However, conventional methods often rely on linearization hypothesis, while recent learning-based approaches rarely consider stability guarantees. This paper proposes a learning-based framework to learn a stable optimal controller for nonlinear optimal regulation problems. First, leveraging the equivalence between Pontryagin Maximum Principle (PMP) and Hamilton-Jacobi-Bellman (HJB) equation, we improve the backward generation of optimal examples (BGOE) method for infinite-time optimal regulation problems. A state-transition-matrix-guided data generation method is then proposed to efficiently generate a complete dataset that covers the desired state space. Finally, we incorporate the Lyapunov stability condition into the learning framework, ensuring the stability of the learned optimal policy by jointly learning the optimal value function and control policy. Simulations on three nonlinear optimal regulation problems show that the learned optimal policy achieves near-optimal regulation control and the code is provided at https://github.com/wong-han/PaperNORC

eess.SY↗

arXiv2025

FAPS: A Fast Platform for Protein Structureomics Analysis

Protein quantification and analysis are well-accepted approaches for biomarker discovery but are limited to identification without structural information. High-throughput omics data (i.e., genomics, transcriptomics, and proteomics) have become pervasive in cancer biology studies and reach well beyond more specialized areas such as metabolomics, epigenomics, pharmacogenomics, and interact-omics. However, large-scale analysis based on the structure of the biomolecules, namely structure-omics, is still underexplored due to a lack of handy tools. In response, we developed the Fast Analysis of Protein Structure (FAPS) database, a platform designed to advance quantitative proteomics to structure-omics analysis, which significantly shortens large-scale structure-omics from weeks to seconds. FAPS can serve as a new protein secondary structure database, providing a centralized and functional database for both simulated and experimentally determined bioinformatics statistics relating to secondary structure. Stored data is generated both through the structure simulation, currently SWISS-MODEL and AlphaFold, performed by high-performance computers, and the pre-existing UniProt database. FAPS provides user-friendly features that create a straightforward and effective way of accessing accurate data on the proportion of secondary structure in different protein chains, providing a fast numerical and visual reference for protein structure calculations and analysis. FAPS is accessible through http://fapsdb.org.

q-bio.QM↗

arXiv2025

TextAtari: 100K Frames Game Playing with Language Agents

We present TextAtari, a benchmark for evaluating language agents on very long-horizon decision-making tasks spanning up to 100,000 steps. By translating the visual state representations of classic Atari games into rich textual descriptions, TextAtari creates a challenging test bed that bridges sequential decision-making with natural language processing. The benchmark includes nearly 100 distinct tasks with varying complexity, action spaces, and planning horizons, all rendered as text through an unsupervised representation learning framework (AtariARI). We evaluate three open-source large language models (Qwen2.5-7B, Gemma-7B, and Llama3.1-8B) across three agent frameworks (zero-shot, few-shot chain-of-thought, and reflection reasoning) to assess how different forms of prior knowledge affect performance on these long-horizon challenges. Four scenarios-Basic, Obscured, Manual Augmentation, and Reference-based-investigate the impact of semantic understanding, instruction comprehension, and expert demonstrations on agent decision-making. Our results reveal significant performance gaps between language agents and human players in extensive planning tasks, highlighting challenges in sequential reasoning, state tracking, and strategic planning across tens of thousands of steps. TextAtari provides standardized evaluation protocols, baseline implementations, and a framework for advancing research at the intersection of language models and planning. Our code is available at https://github.com/Lww007/Text-Atari-Agents.

cs.CL↗