arXiv subjects

Shiliang Zhang

Publications and source records attributed to Shiliang Zhang.

At least 19 recordsLinked to original sources

arXiv2026

VeriTS: Verifiable Model-Enhanced Time-Series Queries on Blockchain Systems

Blockchain data is temporal. Every transaction carries a timestamp and the chain imposes a total order, so on-chain data forms per-source time-series streams. However, existing systems support only basic lookups on blocks and transactions, and cannot answer time-series queries such as time-range retrieval and windowed aggregation. Offloading queries off-chain restores expressiveness, but the off-chain query layer is untrusted, so results must be verifiable. To this end, we propose VeriTS, the first verifiable time-series query framework for blockchain systems. It supports efficient range and aggregation queries without altering blockchain storage structures. VeriTS maintains an off-chain query layer that represents each stream through an authenticated aggregate interval tree. The tree serves as the query index and as the authenticated data structure at once, so a windowed aggregate is answered by folding a logarithmic number of node aggregates. VeriTS verifies completeness through a minimum covering set and soundness through aggregate folding. It extends both guarantees to an approximate path over model segments, redefining completeness and soundness under bounded error. Miners validate a model's residual rather than replay its computation, so even an adversarial encoder can inflate proof size and answer width but never correctness. Experiments offer evidence that on windowed aggregation, VeriTS improves verification efficiency by more than two orders of magnitude over per-record proofs. Range-query proofs shrink by up to 14.5x.

cs.DB↗

arXiv2026

A Distinct Covering System with Minimum Modulus 7 and Minimal Least Common Multiple 10080

We determine the minimum possible least common multiple of a distinct covering system whose minimum modulus is $7$. Klein previously constructed such a system with least common multiple $15120$ and conjectured that this value was minimal. We give a construction with least common multiple $10080$, and we prove that no smaller least common multiple can occur. The proof is organized as a successive filtering argument. Starting from the possible multiples of $7$ below $10080$, we first apply a reciprocal-sum filter, then a divisor-completed integer-programming filter, then a stronger partial-sum filter. The few remaining hard cases are finally certified by complete Gurobi computations.

math.NT↗

arXiv2026

Urban Power Grid Topology and Hierarchy Identification from Open Data

Understanding the complex topology and hierarchy of urban power grid is crucial for energy prognosis, power flow management, and system resilience analysis. However, detailed grid information remains largely proprietary. This creates significant barriers for research and innovation, especially when analyzing the last-mile distribution networks connecting individual buildings. This paper addresses this challenge by developing an open-data-driven framework for the complete identification of urban power grid topology, from high-voltage transmission down to individual building connections. Particularly, we fuse public infrastructure data (power-lines, substations, transformers, poles) to map the high and medium-voltage skeleton using graph-based algorithms. We then leverage geospatial machine learning on OpenStreetMap building data to group power demand clusters, and infer the physical topology of the final distribution lines linking the clustered buildings. We apply the developed framework to the district of Alna in Oslo, Norway, and we reconstruct the complete grid topology that connects 7,330 buildings and all major electricity infrastructure assets. With the research in this work, we provide a critical tool that facilitates power system analysis, e.g., power flow optimization, cascading failure simulation, and grid resilience against the penetration of distributed renewable generation.

cs.LG↗

arXiv2026

PixelGen: Improving Pixel Diffusion with Perceptual Supervision

Pixel diffusion generates images directly in pixel space, avoiding the VAE artifacts and representational bottlenecks of two-stage latent diffusion. Recent JiT further simplifies pixel diffusion with x-prediction, where the model predicts clean images rather than velocity. However, the standard pixel-wise diffusion loss treats all pixels equally, spending model capacity to perceptually insignificant signals and often leading to blurry samples. We propose PixelGen, an end-to-end pixel diffusion framework that augments x-prediction with perceptual supervision. Specifically, PixelGen introduces two complementary perceptual losses on top of x-prediction: an LPIPS loss for local textures and a P-DINO loss for global semantics. To preserve sample coverage, PixelGen further proposes a noise-gating strategy that applies these losses only at lower-noise timesteps. On ImageNet-256 without classifier-free guidance, PixelGen achieves an FID of 5.11 in 80 training epochs, surpassing the latent diffusion baselines. Moreover, PixelGen scales efficiently to text-to-image generation, reaching a GenEval score of 0.79 with only 6 days of training on 8xH800 GPUs. These results show that perceptual supervision substantially narrows the gap between pixel and latent diffusion while preserving a simple one-stage pipeline. Codes are available at https://github.com/Zehong-Ma/PixelGen.

cs.CV↗

arXiv2026

Prompt-Anchored Vision-Text Distillation for Lifelong Person Re-identification

Lifelong person re-identification (LReID) aims to train a generalizable model with sequentially collected data. However, such models often suffer from semantic drift, limited adaptability, and catastrophic forgetting as new domains emerge. Existing exemplar-free approaches largely rely on visual-only distillation or parameter regularization, while overlooking the potential of auxiliary modalities, such as text, to preserve semantic stability and enable incremental plasticity. We observe that the frozen text encoder in pretrained vision-language models can serve as a stable semantic anchor across domains. To decouple the roles of vision and text, we propose Prompt-Anchored vision-text Distillation (PAD), an asymmetric vision-text framework for semantic alignment and cross-domain generalization. On the textual side, we distill prompts to preserve vision-text alignment under a fixed semantic space, acting as a global semantic reference rather than a dominant learning signal. On the visual side, an EMA-based teacher with an adaptive prompt pool enables domain-wise adaptation by allocating new slots while freezing past ones. Extensive experiments show that PAD substantially outperforms state-of-the-art methods across seen and unseen domains, achieving a strong balance between stability and plasticity. Project page is available at https://github.com/zu-zi/PAD.

cs.CV↗

arXiv2026

AI and Open-data Driven Scalable Solar Power Profiling

Solar photovoltaic (PV) deployment is expanding rapidly, yet detailed, up-to-date information on the spatial distribution and capacity of rooftop PV remains limited. This paper presents an open, scalable framework for detecting solar panels from open data and generating city-level solar power profiles. We leverage foundation vision AI models to detect solar panel geometries from open-source satellite imagery. This avoids manual data labeling and case-specific model training while maintaining robustness across heterogeneous imagery. Detected solar panels are converted into georeferenced polygons, yielding spatially explicit and incrementally extensible inventories. By integrating open weather data, we translate panel footprints into regional solar power profiles. The framework reduces dependency on proprietary imagery, manual labeling, and closed-source models, and offers a transparent and scalable approach for solar planning and analysis. We released the data and an API resulted from this work. For any user-specified building location, our API retrieves aerial imagery, detects rooftop solar panels, and returns georeferenced polygons. This empowers researchers and developers to scan user-defined areas to build solar panel maps and associated solar production profiles, thus facilitating advanced analysis like distributed solar production integration, local power flow optimization, energy tariff design, and infrastructure planning.

cs.AI↗

arXiv2026

DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation

Pixel diffusion aims to generate images directly in pixel space in an end-to-end fashion. This approach avoids the limitations of VAE in the two-stage latent diffusion, offering higher model capacity. Existing pixel diffusion models suffer from slow training and inference, as they usually model both high-frequency signals and low-frequency semantics within a single diffusion transformer (DiT). To pursue a more efficient pixel diffusion paradigm, we propose the frequency-DeCoupled pixel diffusion framework. With the intuition to decouple the generation of high and low frequency components, we leverage a lightweight pixel decoder to generate high-frequency details conditioned on semantic guidance from the DiT. This thus frees the DiT to specialize in modeling low-frequency semantics. In addition, we introduce a frequency-aware flow-matching loss that emphasizes visually salient frequencies while suppressing insignificant ones. Extensive experiments show that DeCo achieves superior performance among pixel diffusion models, attaining FID of 1.62 (256x256) and 2.22 (512x512) on ImageNet, closing the gap with latent diffusion methods. Furthermore, our pretrained text-to-image model achieves a leading overall score of 0.86 on GenEval in system-level comparison. Codes are publicly available at https://github.com/Zehong-Ma/DeCo.

cs.CV↗

arXiv2026

Cenergy3: An Open Software Package for City Energy 3D Modeling

The efficient management and planning of urban energy systems require integrated three-dimensional (3D) models that accurately represent both consumption nodes and distribution networks. This paper introduces our developed approach and openly released software that automate the generation of digital 3D urban energy model from open data. We synthesize data from OpenTopography, OpenStreetMap, and Overture Maps in generating 3D models. The rendered model visualizes and contextualizes distribution power grids alongside the built environment and transportation networks. Our developed software, including an open python library and a free API, provides interactive figures for the 3D models. The rendered models are essential for analyzing infrastructure alignment and spatially linking energy demand nodes (buildings) with energy supply (utility grids). The developed API leverages standard Web Mercator coordinates (EPSG:3857) and JSON serialization to ensure interoperability within smart city and energy simulation platforms. We also provide a graphic user interface (GUI) where end-users can access our API via a cloud-based server, regardless of their programming skills and what devices and platforms their are using. We anticipate that our approach and software can support field researchers, developers, end-users, and policy-makers in a varieties of applications like urban energy monitoring, demand-supply analysis, and energy digital twins.

cs.DL↗

arXiv2026

Security, privacy, and agentic AI in a regulatory view: From definitions and distinctions to provisions and reflections

The rapid proliferation of artificial intelligence (AI) technologies has led to a dynamic regulatory landscape, where legislative frameworks strive to keep pace with technical advancements. As AI paradigms shift towards greater autonomy, specifically in the form of agentic AI, it becomes increasingly challenging to precisely articulate regulatory stipulations. This challenge is even more acute in the domains of security and privacy, where the capabilities of autonomous agents often blur traditional legal and technical boundaries. This paper reviews the evolving European Union (EU) AI regulatory provisions via analyzing 24 relevant documents published between 2024 and 2025. From this review, we provide a clarification of critical definitions. We deconstruct the regulatory interpretations of security, privacy, and agentic AI, distinguishing them from closely related concepts to resolve ambiguity. We synthesize the reviewed documents to articulate the current state of regulatory provisions targeting different types of AI, particularly those related to security and privacy aspects. We analyze and reflect on the existing provisions in the regulatory dimension to better align security and privacy obligations with AI and agentic behaviors. These insights serve to inform policymakers, developers, and researchers on the compliance and AI governance in the society with increasing algorithmic agencies.

cs.CR↗

arXiv2026

SyncSpeech: Efficient and Low-Latency Text-to-Speech based on Temporal Masked Transformer

Current text-to-speech (TTS) models face a persistent limitation: autoregressive (AR) models suffer from low generation efficiency, while modern non-autoregressive (NAR) models experience high latency due to their unordered temporal nature. To bridge this divide, we introduce SyncSpeech, an efficient and low-latency TTS model based on the proposed Temporal Mask Transformer (TMT) paradigm. TMT synergistically unifies the temporally ordered generation of AR models with the parallel decoding efficiency of NAR models. TMT is realized through a meticulously designed sequence construction rule, a corresponding training objective, and a specialized hybrid attention mask. Furthermore, with the primary aim of enhancing training efficiency, a high-probability masking strategy is introduced, which also leads to a significant improvement in overall model performance. During inference, SyncSpeech achieves high efficiency by decoding all speech tokens corresponding to each newly arrived text token in a single step, and low latency by beginning to generate speech immediately upon receiving the second text token from the streaming input. Evaluations show that SyncSpeech maintains speech quality comparable to the modern AR TTS model, while achieving a 5.8-fold reduction in first-packet latency and an 8.8-fold improvement in real-time factor. Speech samples are available at https://SyncSpeech.github.io/}{https://SyncSpeech.github.io/.

cs.SD↗

arXiv2026

MoSA: Motion-Coherent Human Video Generation via Structure-Appearance Decoupling

Existing video generation models predominantly emphasize appearance fidelity while exhibiting limited ability to synthesize complex human motions, such as whole-body movements, long-range dynamics, and fine-grained human-environment interactions. This often leads to unrealistic or physically implausible movements with inadequate structural coherence. To conquer these challenges, we propose MoSA, which decouples the process of human video generation into two components, i.e., structure generation and appearance generation. MoSA first employs a 3D structure transformer to generate a human motion sequence from the text prompt. The remaining video appearance is then synthesized under the guidance of this structural sequence. We achieve fine-grained control over the sparse human structures by introducing Human-Aware Dynamic Control modules with a dense tracking constraint during training. The modeling of human-environment interactions is improved through the proposed contact constraint. Those two components work comprehensively to ensure the structural and appearance fidelity across the generated videos. This paper also contributes a large-scale human video dataset, which features more complex and diverse motions than existing human video datasets. We conduct comprehensive comparisons between MoSA and a variety of approaches, including general video generation models, human video generation models, and human animation models. Experiments demonstrate that MoSA substantially outperforms existing approaches across the majority of evaluation metrics.

cs.CV↗

arXiv2026

FlattenGPT: Depth Compression for Transformer with Layer Flattening

Recent works have indicated redundancy across transformer blocks, prompting the research of depth compression to prune less crucial blocks. However, current ways of entire-block pruning suffer from risks of discarding meaningful cues learned in those blocks, leading to substantial performance degradation. As another line of model compression, channel pruning can better preserve performance, while it cannot reduce model depth and is challenged by inconsistent pruning ratios for individual layers. To pursue better model compression and acceleration, this paper proposes \textbf{FlattenGPT}, a novel way to detect and reduce depth-wise redundancies. By flatting two adjacent blocks into one, it compresses the network depth, meanwhile enables more effective parameter redundancy detection and removal. FlattenGPT allows to preserve the knowledge learned in all blocks, and remains consistent with the original transformer architecture. Extensive experiments demonstrate that FlattenGPT enhances model efficiency with a decent trade-off to performance. It outperforms existing pruning methods in both zero-shot accuracies and WikiText-2 perplexity across various model types and parameter sizes. On LLaMA-2/3 and Qwen-1.5 models, FlattenGPT retains 90-96\% of zero-shot performance with a compression ratio of 20\%. It also outperforms other pruning methods in accelerating LLM inference, making it promising for enhancing the efficiency of transformers.

cs.CV↗

arXiv2026

Looping Back to Move Forward: Recursive Transformers for Efficient and Flexible Large Multimodal Models

Large Multimodal Models (LMMs) have achieved remarkable success in vision-language tasks, yet their vast parameter counts are often underutilized during both training and inference. In this work, we embrace the idea of looping back to move forward: reusing model parameters through recursive refinement to extract stronger multimodal representations without increasing model size. We propose RecursiveVLM, a recursive Transformer architecture tailored for LMMs. Two key innovations enable effective looping: (i) a Recursive Connector that aligns features across recursion steps by fusing intermediate-layer hidden states and applying modality-specific projections, respecting the distinct statistical structures of vision and language tokens; (ii) a Monotonic Recursion Loss that supervises every step and guarantees performance improves monotonically with recursion depth. This design transforms recursion into an on-demand refinement mechanism: delivering strong results with few loops on resource-constrained devices and progressively improving outputs when more computation resources are available. Experiments show consistent gains of +3% over standard Transformers and +7% over vanilla recursive baselines, demonstrating that strategic looping is a powerful path toward efficient, deployment-adaptive LMMs.

cs.LG↗

arXiv2026

Exploring the Interpretability of Forecasting Models for Energy Balancing Market

The balancing market in the energy sector plays a critical role in physically and financially balancing the supply and demand. Modeling dynamics in the balancing market can provide valuable insights and prognosis for power grid stability and secure energy supply. While complex machine learning models can achieve high accuracy, their black-box nature severely limits the model interpretability. In this paper, we explore the trade-off between model accuracy and interpretability for the energy balancing market. Particularly, we take the example of forecasting manual frequency restoration reserve (mFRR) activation price in the balancing market using real market data from different energy price zones. We explore the interpretability of mFRR forecasting using two models: extreme gradient boosting (XGBoost) machine and explainable boosting machine (EBM). We also integrate the two models, and we benchmark all the models against a baseline naive model. Our results show that EBM provides forecasting accuracy comparable to XGBoost while yielding a considerable level of interpretability. Our analysis also underscores the challenge of accurately predicting the mFRR price for the instances when the activation price deviates significantly from the spot price. Importantly, EBM's interpretability features reveal insights into non-linear mFRR price drivers and regional market dynamics. Our study demonstrates that EBM is a viable and valuable interpretable alternative to complex black-box AI models in the forecast for the balancing market.

q-fin.ST↗

arXiv2026

SLAM-LLM: A Modular, Open-Source Multimodal Large Language Model Framework and Best Practice for Speech, Language, Audio and Music Processing

The recent surge in open-source Multimodal Large Language Models (MLLM) frameworks, such as LLaVA, provides a convenient kickoff for artificial intelligence developers and researchers. However, most of the MLLM frameworks take vision as the main input modality, and provide limited in-depth support for the modality of speech, audio, and music. This situation hinders the development of audio-language models, and forces researchers to spend a lot of effort on code writing and hyperparameter tuning. We present SLAM-LLM, an open-source deep learning framework designed to train customized MLLMs, focused on speech, language, audio, and music processing. SLAM-LLM provides a modular configuration of different encoders, projectors, LLMs, and parameter-efficient fine-tuning plugins. SLAM-LLM also includes detailed training and inference recipes for mainstream tasks, along with high-performance checkpoints like LLM-based Automatic Speech Recognition (ASR), Automated Audio Captioning (AAC), and Music Captioning (MC). Some of these recipes have already reached or are nearing state-of-the-art performance, and some relevant techniques have also been accepted by academic papers. We hope SLAM-LLM will accelerate iteration, development, data engineering, and model training for researchers. We are committed to continually pushing forward audio-based MLLMs through this open-source framework, and call on the community to contribute to the LLM-based speech, audio and music processing.

cs.SD↗

arXiv2026

Adaptive Robust Control for Uncertain Systems with Ellipsoid-Set Learning

Despite the celebrated success of stochastic control approaches for uncertain systems, such approaches are limited in the ability to handle non-Gaussian uncertainties. This work presents an adaptive robust control for linear uncertain systems, whose process noise, observation noise, and system states are depicted by ellipsoid sets rather than Gaussian distributions. We design an ellipsoid-set learning method to estimate the boundaries of state sets, and incorporate the learned sets into the control law derivation to reduce conservativeness in robust control. Further, we consider the parametric uncertainties in state-space matrices. Particularly, we assign finite candidates for the uncertain parameters, and construct a bank of candidate-conditional robust control problems for each candidate. We derive the final control law by aggregating the candidate-conditional control laws. In this way, we separate the control scheme into parallel robust controls, decoupling the learning and control, which otherwise renders the control unattainable. We demonstrate the effectiveness of the proposed control in numerical simulations in the cases of linear quadratic regulation and tracking control.

math.OC↗

arXiv2025

Linear quadratic control for discrete-time systems with stochastic and bounded noises

This paper focuses on the linear quadratic control (LQC) design of systems corrupted by both stochastic noise and bounded noise simultaneously. When only of these noises are considered, the LQC strategy leads to stochastic or robust controllers, respectively. However, there is no LQC strategy that can simultaneously handle stochastic and bounded noises efficiently. This limits the scope where existing LQC strategies can be applied. In this work, we look into the LQC problem for discrete-time systems that have both stochastic and bounded noises in its dynamics. We develop a state estimation for such systems by efficiently combining a Kalman filter and an ellipsoid set-membership filter. The developed state estimation can recover the estimation optimality when the system is subject to both kinds of noise, the stochastic and the bounded. Upon the estimated state, we derive a robust state-feedback optimal control law for the LQC problem. The control law derivation takes into account both stochastic and bounded-state estimation errors, so as to avoid over-conservativeness while sustaining stability in the control. In this way, the developed LQC strategy extends the range of scenarios where LQC can be applied, especially those of real-world control systems with diverse sensing which are subject to different kinds of noise. We present numerical simulations, and the results demonstrate the enhanced control performance with the proposed strategy.

math.OC↗

arXiv2025

Fault Tolerant Control of Mecanum Wheeled Mobile Robots

Mecanum wheeled mobile robots (MWMRs) are highly susceptible to actuator faults that degrade performance and risk mission failure. Current fault tolerant control (FTC) schemes for MWMRs target complete actuator failures like motor stall, ignoring partial faults e.g., in torque degradation. We propose an FTC strategy handling both fault types, where we adopt posterior probability to learn real-time fault parameters. We derive the FTC law by aggregating probability-weighed control laws corresponding to predefined faults. This ensures the robustness and safety of MWMR control despite varying levels of fault occurrence. Simulation results demonstrate the effectiveness of our FTC under diverse scenarios.

cs.RO↗