arXiv subjects

Xingyu Zhou

Publications and source records attributed to Xingyu Zhou.

At least 55 records · Page 3Linked to original sources

arXiv2025

Odin: Effective End-to-End SLA Decomposition for 5G/6G Network Slicing via Online Learning

Network slicing plays a crucial role in realizing 5G/6G advances, enabling diverse Service Level Agreement (SLA) requirements related to latency, throughput, and reliability. Since network slices are deployed end-to-end (E2E), across multiple domains including access, transport, and core networks, it is essential to efficiently decompose an E2E SLA into domain-level targets, so that each domain can provision adequate resources for the slice. However, decomposing SLAs is highly challenging due to the heterogeneity of domains, dynamic network conditions, and the fact that the SLA orchestrator is oblivious to the domain's resource optimization. In this work, we propose Odin, a Bayesian Optimization-based solution that leverages each domain's online feedback for provably-efficient SLA decomposition. Through theoretical analyses and rigorous evaluations, we demonstrate that Odin's E2E orchestrator can achieve up to 45% performance improvement in SLA satisfaction when compared with baseline solutions whilst reducing overall resource costs even in the presence of noisy feedback from the individual domains.

cs.NI↗

arXiv2025

Apple Intelligence Foundation Language Models: Tech Report 2025

We introduce two multilingual, multimodal foundation language models that power Apple Intelligence features across Apple devices and services: i a 3B-parameter on-device model optimized for Apple silicon through architectural innovations such as KV-cache sharing and 2-bit quantization-aware training; and ii a scalable server model built on a novel Parallel-Track Mixture-of-Experts PT-MoE transformer that combines track parallelism, mixture-of-experts sparse computation, and interleaved global-local attention to deliver high quality with competitive cost on Apple's Private Cloud Compute platform. Both models are trained on large-scale multilingual and multimodal datasets sourced via responsible web crawling, licensed corpora, and high-quality synthetic data, then further refined with supervised fine-tuning and reinforcement learning on a new asynchronous platform. The resulting models support several additional languages while understanding images and executing tool calls. In public benchmarks and human evaluations, both the server model and the on-device model match or surpass comparably sized open baselines. A new Swift-centric Foundation Models framework exposes guided generation, constrained tool calling, and LoRA adapter fine-tuning, allowing developers to integrate these capabilities with a few lines of code. The latest advancements in Apple Intelligence models are grounded in our Responsible AI approach with safeguards like content filtering and locale-specific evaluation, as well as our commitment to protecting our users' privacy with innovations like Private Cloud Compute.

cs.LG↗

arXiv2025

Learning-Aided Iterative Receiver for Superimposed Pilots: Design and Experimental Evaluation

The superimposed pilot transmission scheme offers substantial potential for improving spectral efficiency in MIMO-OFDM systems, but it presents significant challenges for receiver design due to pilot contamination and data interference. To address these issues, we propose an advanced iterative receiver based on joint channel estimation, detection, and decoding, which refines the receiver outputs through iterative feedback. The proposed receiver incorporates two adaptive channel estimation strategies to enhance robustness under time-varying and mismatched channel conditions. First, a variational message passing (VMP) method and its low-complexity variant (VMP-L) are introduced to perform inference without relying on time-domain correlation. Second, a deep learning (DL) based estimator is developed, featuring a convolutional neural network with a despreading module and an attention mechanism to extract and fuse relevant channel features. Extensive simulations under multi-stream and high-mobility scenarios demonstrate that the proposed receiver consistently outperforms conventional orthogonal pilot baselines in both throughput and block error rate. Moreover, over-the-air experiments validate the practical effectiveness of the proposed design. Among the methods, the DL based estimator achieves a favorable trade-off between performance and complexity, highlighting its suitability for real-world deployment in dynamic wireless environments.

cs.IT↗

arXiv2025

Maneuver Detection via a Confidence Dominance Maneuver Indicator

Accurate and efficient maneuver detection is critical for ensuring the safety and predictability of spacecraft trajectories. This paper presents a novel maneuver detection approach based on comparing the confidence levels associated with the orbital state estimation and the observation likelihood. First, a confidence-dominance maneuver indicator (CDMI) is proposed by setting a confidence level for the state estimation and computing the maximum likelihood of the observation and its confidence level. The CDMI then flag a maneuver when the observation's confidence level exceeds that of the state estimation, indicating that the observation is unlikely under the no-maneuver hypothesis while maintaining consistency with the prior state estimation confidence. To efficiently compute the maximum likelihood of the observation and obtain the CDMI, a recursive polynomial optimization method is developed, taking advantage of convex optimization and polynomial approximation. In addition, an integrated CDMI approach is developed to eliminate the need to manually select the state confidence level. The integrated CDMI approach maintains high detection accuracy while simultaneously providing an indication of maneuver likelihood, thereby enhancing robustness and practical applicability. The performance of the proposed CDMI-based maneuver detection approaches is evaluated against an optimal control distance metric and two mixture-based approaches. The simulation results demonstrate that the proposed integrated CDMI approach can achieve up to 99.33\% detection accuracy, at least 10% higher than the competing methods, while substantially reducing computational costs.

eess.SY↗

arXiv2025

A Wireless Foundation Model for Multi-Task Prediction

With the growing complexity and dynamics of the mobile communication networks, accurately predicting key system parameters, such as channel state information (CSI), user location, and network traffic, has become essential for a wide range of physical (PHY)-layer and medium access control (MAC)-layer tasks. Although traditional deep learning (DL)-based methods have been widely applied to such prediction tasks, they often struggle to generalize across different scenarios and tasks. In response, we propose a unified foundation model for multi-task prediction in wireless networks that supports diverse prediction intervals. The proposed model enforces univariate decomposition to unify heterogeneous tasks, encodes granularity for interval awareness, and uses a causal Transformer backbone for accurate predictions. Additionally, we introduce a patch masking strategy during training to support arbitrary input lengths. After trained on large-scale datasets, the proposed foundation model demonstrates strong generalization to unseen scenarios and achieves zero-shot performance on new tasks that surpass traditional full-shot baselines.

cs.AI↗

arXiv2025

Unsupervised Learning-Based Joint Resource Allocation and Beamforming Design for RIS-Assisted MISO-OFDMA Systems

Reconfigurable intelligent surfaces (RIS) are key enablers for 6G wireless systems. This paper studies downlink transmission in an RIS-assisted MISO-OFDMA system, addressing resource allocation challenges. A two-stage unsupervised learning-based framework is proposed to jointly design RIS phase shifts, BS beamforming, and resource block (RB) allocation. The framework includes BeamNet, which predicts RIS phase shifts from CSI, and AllocationNet, which allocates RBs using equivalent CSI derived from BeamNet outputs. Active beamforming is implemented via maximum ratio transmission and water-filling. To handle discrete constraints while ensuring differentiability, quantization and the Gumbel-softmax trick are adopted. A customized loss and phased training enhance performance under QoS constraints. Simulations show the method achieves 99.93% of the sum rate of the SCA baseline with only 0.036% of its runtime, and it remains robust across varying channel and user conditions.

eess.SP↗

arXiv2025

Square$χ$PO: Differentially Private and Robust $χ^2$-Preference Optimization in Offline Direct Alignment

In this paper, we theoretically study the offline alignment of language models with human preference feedback, under both preference label corruption and privacy protections. To this end, we propose Square$χ$PO, a simple one-line change to $χ$PO where the standard log-loss is replaced by a new square loss over probability. Thanks to the inherent properties of this new loss, we have advanced the state-of-the-art of differentially private and robust offline direct alignment. Specifically, for the local model of label privacy, Square$χ$PO is the first algorithm that attains an optimal rate based on single-policy concentrability even with general function approximations. It also gives the first result under the central model of privacy protection over both prompts (responses) and labels. On the robustness side against Huber label corruption, Square$χ$PO is the first alignment method that has a meaningful theoretical guarantee under general function approximations. More importantly, Square$χ$PO can address privacy protection and corruption simultaneously, where an interesting separation is observed, implying that the order of privacy and corruption matters. Furthermore, we show that Square$χ$PO can also be easily extended to handle the scenario of the general preference model with state-of-the-art guarantees under corruption and privacy. Last but not least, all of our theoretical guarantees enjoy a unified analysis, building upon a new result on the generalization error bounds of least-square regression under corruption and privacy constraints, which we believe is of independent interest to the community.

cs.LG↗

arXiv2025

A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPO

In this paper, we theoretically investigate the effects of noisy labels in offline alignment, with a focus on the interplay between privacy and robustness against adversarial corruption. Specifically, under linear modeling assumptions, we present a unified analysis covering both reinforcement learning from human feedback (RLHF) and direct preference optimization (DPO) under different privacy-corruption scenarios, such as Local differential privacy-then-Corruption (LTC), where human preference labels are privatized before being corrupted by an adversary, and Corruption-then-Local differential privacy (CTL), where labels are corrupted before privacy protection. Our analysis leverages a reduction framework that reduces the offline alignment problem under linear modeling assumptions to parameter estimation in logistic regression. This framework allows us to establish an interesting separation result between LTC and CTL, demonstrating that LTC presents a greater challenge than CTL in offline alignment, even under linear models. As important by-products, our findings also advance the state-of-the-art theoretical results in offline alignment under privacy-only or corruption-only scenarios.

cs.LG↗

arXiv2025

Learned Image Compression with Dictionary-based Entropy Model

Learned image compression methods have attracted great research interest and exhibited superior rate-distortion performance to the best classical image compression standards of the present. The entropy model plays a key role in learned image compression, which estimates the probability distribution of the latent representation for further entropy coding. Most existing methods employed hyper-prior and auto-regressive architectures to form their entropy models. However, they only aimed to explore the internal dependencies of latent representation while neglecting the importance of extracting prior from training data. In this work, we propose a novel entropy model named Dictionary-based Cross Attention Entropy model, which introduces a learnable dictionary to summarize the typical structures occurring in the training dataset to enhance the entropy model. Extensive experimental results have demonstrated that the proposed model strikes a better balance between performance and latency, achieving state-of-the-art results on various benchmark datasets.

cs.CV↗

arXiv2025

Small Clips, Big Gains: Learning Long-Range Refocused Temporal Information for Video Super-Resolution

Video super-resolution (VSR) can achieve better performance compared to single image super-resolution by additionally leveraging temporal information. In particular, the recurrent-based VSR model exploits long-range temporal information during inference and achieves superior detail restoration. However, effectively learning these long-term dependencies within long videos remains a key challenge. To address this, we propose LRTI-VSR, a novel training framework for recurrent VSR that efficiently leverages Long-Range Refocused Temporal Information. Our framework includes a generic training strategy that utilizes temporal propagation features from long video clips while training on shorter video clips. Additionally, we introduce a refocused intra&inter-frame transformer block which allows the VSR model to selectively prioritize useful temporal information through its attention module while further improving inter-frame information utilization in the FFN module. We evaluate LRTI-VSR on both CNN and transformer-based VSR architectures, conducting extensive ablation studies to validate the contribution of each component. Experiments on long-video test sets demonstrate that LRTI-VSR achieves state-of-the-art performance while maintaining training and computational efficiency.

cs.CV↗

arXiv2025

Courteous MPC for Autonomous Driving with CBF-inspired Risk Assessment

With more autonomous vehicles (AVs) sharing roadways with human-driven vehicles (HVs), ensuring safe and courteous maneuvers that respect HVs' behavior becomes increasingly important. To promote both safety and courtesy in AV's behavior, an extension of Control Barrier Functions (CBFs)-inspired risk evaluation framework is proposed in this paper by considering both noisy observed positions and velocities of surrounding vehicles. The perceived risk by the ego vehicle can be visualized as a risk map that reflects the understanding of the surrounding environment and thus shows the potential for facilitating safe and courteous driving. By incorporating the risk evaluation framework into the Model Predictive Control (MPC) scheme, we propose a Courteous MPC for ego AV to generate courteous behaviors that 1) reduce the overall risk imposed on other vehicles and 2) respect the hard safety constraints and the original objective for efficiency. We demonstrate the performance of the proposed Courteous MPC via theoretical analysis and simulation experiments.

cs.RO↗

arXiv2025

Optimal Rates for Robust Stochastic Convex Optimization

Machine learning algorithms in high-dimensional settings are highly susceptible to the influence of even a small fraction of structured outliers, making robust optimization techniques essential. In particular, within the $ε$-contamination model, where an adversary can inspect and replace up to an $ε$-fraction of the samples, a fundamental open problem is determining the optimal rates for robust stochastic convex optimization (SCO) under such contamination. We develop novel algorithms that achieve minimax-optimal excess risk (up to logarithmic factors) under the $ε$-contamination model. Our approach improves over existing algorithms, which are not only suboptimal but also require stringent assumptions, including Lipschitz continuity and smoothness of individual sample functions. By contrast, our optimal algorithms do not require these stringent assumptions, assuming only population-level smoothness of the loss. Moreover, our algorithms can be adapted to handle the case in which the covariance parameter is unknown, and can be extended to nonsmooth population risks via convolutional smoothing. We complement our algorithmic developments with a tight information-theoretic lower bound for robust SCO.

cs.LG↗

arXiv2025

Joint Channel Estimation and Signal Detection for MIMO-OFDM: A Novel Data-Aided Approach with Reduced Computational Overhead

The acquisition of channel state information (CSI) is essential in MIMO-OFDM communication systems. Data-aided enhanced receivers, by incorporating domain knowledge, effectively mitigate performance degradation caused by imperfect CSI, particularly in dynamic wireless environments. However, existing methodologies face notable challenges: they either refine channel estimates within MIMO subsystems separately, which proves ineffective due to deviations from assumptions regarding the time-varying nature of channels, or fully exploit the time-frequency characteristics but incur significantly high computational overhead due to dimensional concatenation. To address these issues, this study introduces a novel data-aided method aimed at reducing complexity, particularly suited for fast-fading scenarios in fifth-generation (5G) and beyond networks. We derive a general form of a data-aided linear minimum mean-square error (LMMSE)-based algorithm, optimized for iterative joint channel estimation and signal detection. Additionally, we propose a computationally efficient alternative to this algorithm, which achieves comparable performance with significantly reduced complexity. Empirical evaluations reveal that our proposed algorithms outperform several state-of-the-art approaches across various MIMO-OFDM configurations, pilot sequence lengths, and in the presence of time variability. Comparative analysis with basis expansion model-based iterative receivers highlights the superiority of our algorithms in achieving an effective trade-off between accuracy and computational complexity.

cs.IT↗

arXiv2025

BagChain: A Dual-functional Blockchain Leveraging Bagging-based Distributed Learning

This work proposes a dual-functional blockchain framework named BagChain for bagging-based decentralized learning. BagChain integrates blockchain with distributed machine learning by replacing the computationally costly hash operations in proof-of-work with machine-learning model training. BagChain utilizes individual miners' private data samples and limited computing resources to train potentially weak base models, which may be very weak, and further aggregates them into strong ensemble models. Specifically, we design a three-layer blockchain structure associated with the corresponding generation and validation mechanisms to enable distributed machine learning among uncoordinated miners in a permissionless and open setting. To reduce computational waste due to blockchain forking, we further propose the cross fork sharing mechanism for practical networks with lengthy delays. Extensive experiments illustrate the superiority and efficacy of BagChain when handling various machine learning tasks on both independently and identically distributed (IID) and non-IID datasets. BagChain remains robust and effective even when facing constrained local computing capability, heterogeneous private user data, and sparse network connectivity.

cs.DC↗

arXiv2025

Progressive Focused Transformer for Single Image Super-Resolution

Transformer-based methods have achieved remarkable results in image super-resolution tasks because they can capture non-local dependencies in low-quality input images. However, this feature-intensive modeling approach is computationally expensive because it calculates the similarities between numerous features that are irrelevant to the query features when obtaining attention weights. These unnecessary similarity calculations not only degrade the reconstruction performance but also introduce significant computational overhead. How to accurately identify the features that are important to the current query features and avoid similarity calculations between irrelevant features remains an urgent problem. To address this issue, we propose a novel and effective Progressive Focused Transformer (PFT) that links all isolated attention maps in the network through Progressive Focused Attention (PFA) to focus attention on the most important tokens. PFA not only enables the network to capture more critical similar features, but also significantly reduces the computational cost of the overall network by filtering out irrelevant features before calculating similarities. Extensive experiments demonstrate the effectiveness of the proposed method, achieving state-of-the-art performance on various single image super-resolution benchmarks.

cs.CV↗

arXiv2025

DeepSeek Powered Solid Dosage Formulation Design and Development

Pharmaceutical process design and development for generic, innovative, or personalized drugs have always been a time-consuming, costly, rigorous process, that involves multi-stage evaluation for better quality control and assurance. Large language models (LLMs), a type of generative artificial intelligence system, can augment laboratory research in the pharmaceutical engineering process by helping scientists to extract knowledge from literature, design parameters, and collect and interpret experimental data ultimately accelerating scientific discovery. LLMs with prompt engineering technologies change the researchers thinking protocol from traditional empirical knowledge to streamlined thinking that connects the performance and structured parameters together. In this work, we investigate and evaluate how prompt engineering technologies can enhance the drug design process from different strategies such as zero-shot, few-shot, chain-of-thought, etc. The dissolution profile for specific drugs is predicted and suggested from the LLMs model. Furthermore, the fundamental physical properties such as PSD, aspect ratio, and specific surface area could be inversely designed from the LLMs model. Finally, all the results are evaluated and validated by real-world cases to prove the reliability of prompt engineering techniques. Initial evaluations show an MSE of 23.61 and R2 of 0.97 in zero-shot, an MSE of 114.89 and R2 of 0.90 in zero-shot-CoT, an MSE of 57.0 and R2 of 0.92 in few-shot, a MSE of 22.56 and R2 of 0.97 in few-shot-CoT and a MSE of 10.56 and R2 of 0.99 with the involvement of RAG. This work breaks down any barriers in developing a systematic framework where LLMs assist in formulation design, process control, and decision-making. Finally, we conclude the work by discussing open challenges and future research directions in pharmaceutical processes.

cs.ET↗

arXiv2025

Hybrid Implementation for Untrusted-node-based Quantum Key Distribution Network

Quantum key distribution (QKD) serves as a cornerstone of secure quantum communication, providing unconditional security grounded in quantum mechanics. While trusted-node networks have facilitated early QKD deployment, their vulnerability to node compromise underscores the need for untrusted-node architectures. Measurement-device-independent QKD (MDI-QKD) and twin-field QKD (TF-QKD) have emerged as leading candidates, addressing security vulnerabilities and extending transmission distances. Despite the wide adoptions in various fiber scaling, no integrated implementation of these two protocols has been demonstrated to date. Here, we present a hybrid system that seamlessly integrates TF-QKD and MDI-QKD into one untrusted-node-based architecture. Utilizing an efficient phase estimation method based on asymmetric interferometers, we convert twin-field global phase tracking to relative phase calibration, allowing near continuous running of both protocols. Experiments demonstrate secure finite-size key rates for sending-or-not-sending QKD and MDI-QKD over fiber distances of 150 to 431 km. The results align with theoretical simulations and show the ability to surpass the absolute repeaterless key capacity. Our work offers an unified framework for deploying multi-protocol QKD networks, laying the foundation for adaptable and scalable quantum infrastructures that can meet a wide range of security and performance needs.

quant-ph↗

arXiv2025

Single-Impulse Reachable Set in Arbitrary Dynamics Using Polynomials

This paper presents a method to determine the reachable set (RS) of spacecraft after a single velocity impulse with an arbitrary direction, which is appropriate for the RS in both the state and observation spaces under arbitrary dynamics, extending the applications of current RS methods from two-body to arbitrary dynamics. First, the single-impulse RS model is generalized as a family of two-variable parameterized polynomials in the differential algebra scheme. Then, using the envelope theory, the boundary of RS is identified by solving the envelope equation. A framework is proposed to reduce the complexity of solving the envelope equation by converting it to the problem of searching the root of a one-variable polynomial. Moreover, a high-order local polynomial approximation for the RS envelope is derived to improve computational efficiency. The method successfully determines the RSs of two near-rectilinear halo orbits in the cislunar space. Simulation results show that the RSs in both state and observation spaces can be accurately approximated under the three-body dynamics, with relative errors of less than 0.0658%. In addition, using the local polynomial approximation, the computational time for solving the envelope equation is reduced by more than 84%.

astro-ph.IM↗