arXiv subjects

Liang Zhang

Publications and source records attributed to Liang Zhang.

At least 55 records · Page 3Linked to original sources

arXiv2026

ReaORE: Reasoning-Guided Progressive Open Relation Extraction Empowered by Large Reasoning Models

Open Relation Extraction (OpenRE) requires a model to extract unseen relations between head and tail entities from unstructured text for real-world applications. The core challenge of OpenRE lies in achieving reliable generalization to unseen relation types. Current OpenRE approaches either employ clustering techniques, which cannot generate relation labels and suffer from poor generalization, or rely on direct relation label generation via Large Language Models (LLMs), which lack sufficient discriminative capacity to distinguish easily confused relations. To address these limitations, we propose Reasoning-guided progressive OpenRE (ReaORE), a framework for performing relation extraction through coarse-to-fine relation reasoning. Specifically, ReaORE consists of two key stages: (i) relation filtering, which reasons over multiple aspects to understand relations and instances, yielding an initial relation set, and further supplements and filters relations via embedding-based similarity to ensure the target relation is included; (ii) relation prediction, which aims to predict the target relations from the above set via fine-grained comparative reasoning to better distinguish easily confused relations. Extensive experiments on two widely used OpenRE datasets demonstrate that ReaORE outperforms existing baselines.

cs.CL↗

arXiv2026

Reconstructing rare particle source by femtoscopic correlations

Measurement of particle emission source is a fundamental objective of femtoscopy in high-energy nuclear collisions. Conventional analyses rely on Gaussian parameterizations of pair emission sources, which makes the extraction of single-particle emission sources challenging, particularly for rare particles. Here, we introduce a novel statistical reconstruction method that allows extracting information of the target source relative to a data-constrained reference source instead of the Gaussian assumption. The correlation function is expressed as an ensemble average over the single-particle-conditioned correlation kernel, defined as the particle-by-particle contribution to the correlation function conditioned by the target particles. For particles with rare yields, the particle-by-particle distribution of this kernel can be transformed into event-by-event extraction and becomes experimentally accessible, enabling a direct statistical reconstruction of the emission source of single particles, instead of inferring a pair source. We apply this method to reconstruct $J/ψ$ source via $p$-$J/ψ$ correlations, using HAL QCD-derived $NJ/ψ$ potentials in $\sqrt{s}=13.6$~TeV $pp$ collisions simulated with EPOS4HQ. The reconstructed source reproduces the key characteristics and this new approach achieves a systematic uncertainty of approximately $13\%$ based on EPOS4 simulation.

hep-ph↗

arXiv2026

On the Benefits of Weight Normalization for Overparameterized Matrix Sensing

While normalization techniques are widely used in deep learning, their theoretical understanding remains relatively limited. In this work, we establish the benefits of (generalized) weight normalization (WN) applied to the overparameterized matrix sensing problem. We prove that WN with Riemannian optimization achieves linear convergence, yielding an exponential speedup over standard methods that do not use WN. Our analysis further demonstrates that both iteration and sample complexity improve polynomially as the level of overparameterization increases. To the best of our knowledge, this work provides the first characterization of how WN leverages overparameterization for faster convergence in matrix sensing.

cs.LG↗

arXiv2026

Carbon Layer Orientation and Closed-Pore Construction Achieving Ultra-Low Specific Surface Area Hard Carbon for High-Performance Na-ion Storage

Addressing the critical trade-off between initial Coulombic efficiency (ICE) and reversible capacity in hard carbon anodes for Na-ion batteries (NIBs), we introduce a novel coupling strategy that combines carbon layer orientation reconstruction with closed-pore construction to produce hard carbon with an ultra-low specific surface area. We demonstrate that the nanographite domains within the hard carbon precursor undergo entropy-driven orientation reconstruction through the synergistic regulation of heteroatom doping and medium-temperature carbonization. This process not only increases interlayer spacing and promotes structural disorder but also enables the formation of dense, closed pores and ultramicropores at domain boundaries via confined atomic migration, while simultaneously encapsulating surface open pores within internal closed ones. Due to this unique pore architecture, our hard carbon exhibits an ultra-low specific surface area of 1.89 m2 g-1 with a markedly higher proportion of closed pores. As a result, our hard carbon achieves a remarkable reversible capacity of 342.3 mAh g-1 at 20 mA g-1, with an exceptional ICE of 90.4% and a dominant plateau capacity of 262.3 mAh g-1 (76.6%) for NIBs. We believe this coupling strategy provides a new paradigm for the structural engineering of high-ICE anode materials in advanced NIBs.

cond-mat.mtrl-sci↗

arXiv2026

When Good Enough Is Optimal: Multiplication-Only Matrix Inversion Approximation for Quantized Gated DeltaNet

Matrix inversion in chunk-wise parallel linear attention is a major bottleneck for long-context modeling, particularly on NPUs, where forward-substitution-based methods exhibit limited parallelism and poor hardware utilization. We propose a fast, Matrix Multiplication (MatMul)-based algorithm tailored for strictly lower-triangular matrices arising in chunk-wise linear attention. Motivated by the rapid growth of Neumann-series terms and the diagonal concentration of the inverse matrix, we employ a truncated Neumann expansion with structural masking and parallel residual correction to eliminate sequential dependencies. We further extend our method to low-bits INT by mitigating the dynamic range expansion arising from repeated matrix power operations, and adapt the approximation order and residual step to the chunk size to minimize computational cost while preserving the model's accuracy. Experiments on Qwen3.5-family models demonstrate up to 5$\times$ kernel-level speedup and a 20% reduction in decode-layer overhead, while preserving accuracy under both floating-point and low-precision inference. Our method offers an efficient and hardware-friendly solution for scalable linear attention.

cs.LG↗

arXiv2026

IAF-Net: Illumination-Adaptive Fusion for Low-Light Urban Road Segmentation

Semantic road segmentation is important for autonomous driving, but existing methods suffer severe performance degradation under low-light conditions. Many existing multi-modal fusion methods do not explicitly adapt to illumination-dependent changes in modality reliability, which can propagate degraded RGB features into the fused representation at night. We propose IAF-Net (Illumination-Adaptive Fusion Network), an end-to-end framework with illumination-adaptive fusion for robust road segmentation across different lighting conditions. It dynamically adjusts fusion weights of RGB and geometric features via the core Illumination-Adaptive Fusion (IAF) module, and enhances low-light feature selection with a brightness-modulated attention decoder. We also construct two dedicated datasets: nuScenes Nighttime Road Segmentation (nuScenes-NRS) and CARLA Multi-Weather Road Segmentation (CARLA-MWRS). Experiments on nuScenes-NRS show state-of-the-art overall performance among the compared methods, while CARLA-MWRS further validates robustness across adverse weather conditions. Ablation studies on a 40% training subset further highlight the importance of the IAF module, which provides the largest individual gain of 0.70% in MaxF.

cs.CV↗

arXiv2026

From Meta-Thought to Execution: Cognitively Aligned Post-Training for Generalizable and Reliable LLM Reasoning

Current LLM post-training methods optimize complete reasoning trajectories through Supervised Fine-Tuning (SFT) followed by outcome-based Reinforcement Learning (RL). While effective, a closer examination reveals a fundamental gap: this approach does not align with how humans actually solve problems. Human cognition naturally decomposes problem-solving into two distinct stages: first acquiring abstract strategies (i.e., meta-knowledge) that generalize across problems, then adapting them to specific instances. In contrast, by treating complete trajectories as basic units, current methods are inherently problem-centric, entangling abstract strategies with problem-specific execution. To address this misalignment, we propose a cognitively-inspired framework that explicitly mirrors the two-stage human cognitive process. Specifically, Chain-of-Meta-Thought CoMT focuses supervised learning on abstract reasoning patterns without specific executions, enabling acquisition of generalizable strategies. Confidence-Calibrated Reinforcement Learning (CCRL) then optimizes task adaptation via confidence-aware rewards on intermediate steps, preventing overconfident errors from cascading and improving execution reliability. Experiments across four models and ten benchmarks show 2.10% and 3.86% improvements in-distribution and out-of-distribution respectively over standard methods, while remaining highly robust to variations in teacher model selection, optimization methods, and symbolic perturbations.

cs.AI↗

arXiv2026

SALAAD: Sparse And Low-Rank Adaptation via ADMM for Large Language Model Inference

Modern large language models are increasingly deployed under compute and memory constraints, making flexible control of model capacity a central challenge. While sparse and low-rank structures naturally trade off capacity and performance, existing approaches often rely on heuristic designs that ignore layer and matrix heterogeneity or require model-specific architectural modifications. We propose SALAAD, a plug-and-play framework applicable to different model architectures that induces sparse and low-rank structures during training. By formulating structured weight learning under an augmented Lagrangian framework and introducing an adaptive controller that dynamically balances the training loss and structural constraints, SALAAD preserves the stability of standard training dynamics while enabling explicit control over the evolution of effective model capacity during training. Experiments across model scales show that SALAAD substantially reduces memory consumption during deployment while achieving performance comparable to ad-hoc methods. Moreover, a single training run yields a continuous spectrum of model capacities, enabling smooth and elastic deployment across diverse memory budgets without the need for retraining.

cs.LG↗

arXiv2026

Knowing What to Solve Before How: Preplan Empowered LLM Mathematical Reasoning

Current plan-based reasoning methods improve large language models (LLMs) by inserting a planning stage before execution, giving rise to the question $\rightarrow$ plan $\rightarrow$ cot paradigm. While effective, a closer examination reveals an inherent paradigm-level gap: both the planning and its execution stages decide how to solve a problem, while the prior question of what to solve; recognizing the problem type, the applicable tools, and the foreseeable pitfalls; remains entirely implicit. To bridge this gap, we propose PPC (Preplan-Plan-CoT), a framework that introduces an explicit problem-understanding stage, the preplan, yielding a new question $\rightarrow$ preplan $\rightarrow$ plan $\rightarrow$ cot paradigm. Realizing this paradigm requires safeguarding the conceptual integrity of preplan at both ends. Specifically, we design a three-stage synthesis pipeline with a spoiler-score detector that filters out leakage and spoiler failures to build clean preplan supervision, and a composite GRPO reward enforces that the generated plan genuinely follows from the preplan. Experiments across four backbones and five mathematical reasoning benchmarks show that PPC achieves the best results on 39 of 40 metrics, improving maj@16 and pass@16 by +2.23 and +3.06 over the strongest baseline without introducing additional inference token overhead.

cs.CL↗

arXiv2026

Agentic Nesting: A New Methodology for Existing Enterprise Application Integration and Services

Enterprise operations extensively rely on multiple heterogeneous business systems and information applications, which also result in severe data silos and process fragmentation. Enterprises have invested considerable financial and material resources in building these applications, however, effectively leveraging and orchestrating them remains a formidable challenge. Conventional approaches to enterprise application integration, encompassing middleware architectures such as Enterprise Service Bus (ESB), API gateway infrastructures, and Robotic Process Automation (RPA), suffer from inherent limitations like high architectural coupling, escalating operation and maintenance costs, and limited intelligence capabilities. This paper proposes Agentic Nesting, a multi-agent collaboration framework in which existing enterprise applications are encapsulated as autonomous AI agents within a hierarchically nested structure. Rather than flat interconnection, agents are organized into layered stewardship topologies that mirror the compositional complexity of enterprise ecosystems. The framework extracts a digital agent proxy from each legacy application to enable natural-language interaction and autonomous manipulation, coordinates multiple agents through a central orchestrator for task decomposition and dynamic dispatching, and exposes a unified conversational interface for cross-application querying and process orchestration. The main contributions of this paper are the proposition of the "Application-as-Agent" integration paradigm and the "Conversation-as-Integration" interaction philosophy, together with an exploration of the generalization potential of this methodology in scenarios encompassing heterogeneous system coordination, and large-scale data applications.

cs.AI↗

arXiv2026

STM3: Mixture of Multiscale Mamba for Long-Term Spatio-Temporal Time-Series Prediction

Recently, spatio-temporal time-series prediction has developed rapidly, yet existing deep learning methods struggle with learning complex long-term spatio-temporal dependencies efficiently. The long-term spatio-temporal dependency learning brings two new challenges: 1) The long-term temporal sequence naturally includes multiscale information, which is hard to extract efficiently; 2) The multiscale temporal information from different nodes is highly correlated and hard to model. To address these challenges, we propose Spatio-Temporal Mixture of Multiscale Mamba (STM3). STM3 integrates a Multiscale Mamba architecture within a novel Disentangled Mixture-of-Experts (DMoE) framework to capture diverse multiscale information efficiently, while utilizing an adaptive graph causal network to model complex spatial dependencies. To ensure robust representation learning, we introduce a stable routing strategy and a causal contrastive learning strategy, which work in tandem with hierarchical information aggregation to guarantee scale distinguishability. We theoretically prove that STM3 achieves superior routing smoothness and guarantees pattern disentanglement for each expert. Extensive experiments on 10 real-world benchmarks across domains demonstrate STM3's superior performance, achieving state-of-the-art results in long-term spatio-temporal time-series prediction. Notably, on the PEMSD8 dataset, it achieves significant improvements, surpassing the second-best model by 7.1% in MAE, 8.5% in RMSE, and 15.9% in MAPE. Code is available at https://github.com/IfReasonable/STM3_KDD26.

cs.LG↗

arXiv2026

Beyond One-Size-Fits-All: Adaptive Subgraph Denoising for Zero-Shot Graph Learning with Large Language Models

Graph-based tasks in the zero-shot setting remain a significant challenge due to data scarcity and the inability of traditional Graph Neural Networks (GNNs) to generalize to unseen domains or label spaces. While recent advancements have transitioned toward leveraging Large Language Models (LLMs) as predictors to enhance GNNs, these methods often suffer from cross-modal alignment issues. A recent paradigm (i.e., Graph-R1) overcomes the aforementioned architectural dependencies by adopting a purely text-based format and utilizing LLM-based graph reasoning, showing improved zero-shot generalization. However, it employs a task-agnostic, one-size-fits-all subgraph extraction strategy, which inevitably introduces significant structural noise--irrelevant neighbors and edges--that distorts the LLMs' receptive field and leads to suboptimal predictions. To address this limitation, we introduce GraphSSR, a novel framework designed for adaptive subgraph extraction and denoising in zero-shot LLM-based graph reasoning. Specifically, we propose the SSR pipeline, which dynamically tailors subgraph extraction to specific contexts through a "Sample-Select-Reason" process, enabling the model to autonomously filter out task-irrelevant neighbors and overcome the one-size-fits-all issue. To internalize this capability, we develop SSR-SFT, a data synthesis strategy that generates high-quality SSR-style graph reasoning traces for supervised fine-tuning of LLMs. Furthermore, we propose SSR-RL, a two-stage reinforcement learning framework that explicitly regulates sampling and selection operations within the proposed SSR pipeline designed for adaptive subgraph denoising. By incorporating Authenticity-Reinforced and Denoising-Reinforced RL, we guide the model to achieve accurate predictions using parsimonious, denoised subgraphs for reasoning.

cs.LG↗

arXiv2026

Search for the Highest-energy Quasiperiodic Oscillation in the Black Hole X-Ray Binary Candidate Swift J1727.8-1613

We report the first detection of a low-frequency quasiperiodic oscillation (QPO) extending above 250 keV in the black hole X-ray binary candidate Swift J1727.8-1613 using Insight-HXMT observations during its 2023 outburst. Swift J1727.8-1613 is one of the brightest X-ray transients discovered and presents a valuable opportunity for studying high-energy properties of QPOs. Owing to the large effective area of Insight-HXMT in hard X-ray, our observations indicate a remarkably strong QPO signal in the power spectrum above 100 keV. We utilize advanced Hilbert-Huang transform techniques to analyze phase-folded light curves across a wide range of energy bands, observing significant QPOs from 100 to 300 keV in the NaI and CsI detectors, respectively. The detection of QPO profiles above 250 keV can achieve significance levels of ${\sim} 8.9σ$ for the NaI detector and ${\sim} 5.7σ$ for the CsI detector. Our results indicate a decrease in QPO fractional rms above 100 keV and an increased soft phase lag with energy, suggesting a geometric origin for the QPOs, likely linked to the precession of a small-scale jet.

astro-ph.HE↗

arXiv2026

Rethinking Priority Scheduling for Sequential Multi-Agent Decision Making in Stackelberg Games

Current research applying N-level Stackelberg Game to multi-agent systems often uses the default decision order of agents provided by the environment. However, this raises the question: does the order of agents necessarily affect the final equilibrium point of the game? To address this, we formally analyze the N-level Stackelberg Game, where changing the order in which agents make decisions typically leads to an overdetermined system. As a result, the equilibrium point shifts unless special structural conditions are satisfied. Based on this analysis, we propose the Hierarchical Priority Adjustment (HPA) method, which adjusts and selects the agents' decision order. At the upper level, an upper policy dynamically selects the optimal decision order of agents based on the current game state. At the lower level, agents execute strategies in the Spatio-Temporal Sequential Markov Game (STMG) according to the selected order. To coordinate learning across time scales, we employ a slow-fast update scheme with shared intrinsic rewards derived from the advantage function of the upper policy. Experimental results on high-precision control tasks, including multi-agent MuJoCo, show that HPA outperforms benchmark algorithms and robustly adapts to changing environments. These results highlight the crucial role of optimizing the agents' decision order in N-level Stackelberg Game.

cs.MA↗

arXiv2026

Compound effects of traffic and climate on electric vehicle HVAC energy consumption: a spatiotemporal framework with city-level attribution

Real-world electric vehicle (EV) energy consumption can deviate by 20-40% from rated values, driven by ambient temperature, traffic congestion, and route characteristics. Existing studies treat these factors in isolation or as static loads, leaving the compound effect of co-varying climate and traffic on HVAC energy unquantified and per-route attribution unavailable. We develop a spatiotemporal simulation framework that couples traffic-aware driving speed, time- and location-specific ambient temperature, and physics-based submodels (cabin HVAC, traction, battery thermal management) at the segment level, paired with a regression-based decomposition that attributes HVAC variability to temperature and trip-duration components on a per-route basis. Applied through a factorial design across seven UK cities and eight radial routes from Manchester, the framework shows total energy varying by 14\% across cities while HVAC energy varies by up to 89\%, making cabin thermal management the primary differentiator under winter conditions. Trip duration, set by traffic and road type, is frequently the dominant driver of HVAC variability: in London, 83\% of above-average HVAC energy is attributable to congestion-extended trip time rather than to temperature. The decomposition yields a closed-form HVAC model from three inputs (ambient temperature, average speed, trip distance), with physically interpretable coefficients and straightforward transfer to other vehicles or regions through three coefficient re-fits. EV range variability is substantially shaped by traffic and road-network characteristics, with implications for route planning, infrastructure design, and energy equity.

physics.soc-ph↗

arXiv2026

An Insight-HXMT View of the Evolution of the Type-C Quasiperiodic Oscillation during the Flaring State of Swift J1727.8-1613

We present a detailed analysis of the evolution of type-C quasiperiodic oscillations (QPOs) observed during the flaring state of the recently discovered black hole X-ray binary Swift J1727.8-1613, utilizing data from the Insight Hard X-ray Modulation Telescope. By examining the relation between the QPO fractional rms amplitude and QPO frequency across various energy bands, we discover that the behavior significantly differs between these energy bands. Below 10 keV, the QPO fractional rms generally decreases with increasing QPO frequency, whereas above 10 keV, the QPO fractional rms remains relatively stable with frequency. Additionally, we report, for the first time, the detection of a common break at around 4 Hz in the relation between QPO fractional rms and frequency in both the 2-4 and 50-100 keV energy bands. We also find that the evolution of all the spectral parameters alters its behavior at around 4 Hz, with the changes in all parameters becoming flatter. This suggests a significant change in the geometry of the accretion flow. We attribute the observed break to the overall changes in the spectrum.

astro-ph.HE↗

arXiv2026

Unveiling hidden millihertz quasi-periodic oscillations in 1A 0535+262

Be/X-ray binary pulsars show transient outbursts and complex timing behaviour, including millihertz quasi-periodic oscillations (QPOs), whose physical origin and energy dependence remain poorly understood. We aim to characterise the temporal evolution and energy-dependent properties of the mHz QPO during the 2020 giant outburst of 1A 0535+262. We use the multi-Lorentzian fitting framework to jointly model the power spectra and the real and imaginary parts of the cross-spectrum, incorporating simultaneous broadband X-ray observations from NICER and Insight-HXMT (0.2-120 keV). We report the first detection of weak, but significant, mHz QPOs at low X-ray energies (below 27 keV), extending their detection to a new energy regime. The centroid frequency evolves from 41 to 93 mHz, with the peak root-mean-square (rms) amplitude detected in the 50-65 keV. Throughout the outburst, the QPOs generally exhibit a hard lag between 0.12 pi rad and 0.9 pi rad. However, at the outburst peak, the higher-energy bands (above 35 keV) display a soft lag of up to -0.93 pi rad. We propose that interactions between soft seed photons and an extended outflow located outside the magnetosphere can account for the observed hard lags. Furthermore, we detect a double-peaked mHz QPO only at high energies (E above 35 keV) near peak luminosity. The two peaks maintain an approximately constant separation of 2*nu_spin and exhibit anti-correlated phase evolution. Our results indicate that the mHz QPOs in 1A 0535+262 are closely linked to the coupled evolution of a soft-photon source and a Comptonizing outflow or corona. The joint cross-spectral framework provides a complementary probe of mHz QPOs beyond traditional power-spectral analyses.

astro-ph.HE↗

arXiv2026

Deep VLBI constraints on compact radio cores in four ultraluminous X-ray sources

We present high-sensitivity Very Long Baseline Interferometry (VLBI) observations of four ultraluminous X-ray sources (ULXs): Holmberg II X-1, IC 342 X-1, NGC 6946 X-1, and NGC 925 X-1. No compact emission was detected on milliarcsecond scales, with rms noise levels reaching approximately 5--20 $μ$Jy. The corresponding $5σ$ flux density upper limits reach $\sim 26\,μ\mathrm{Jy}$, implying radio luminosity limits $L_{\rm R} \lesssim 2 \times 10^{33}\,\mathrm{erg\,s^{-1}}$. This disfavors any persistently bright hard-state-like compact core at our sensitivity level. The previously reported VLBI core in Holmberg II X-1 exhibits significant long-term variability, broadly consistent with an overall decline over the past decades. This behavior is consistent with emission from optically-thin ejecta undergoing adiabatic expansion. The VLBI non-detections may reflect intrinsically weak/intermittent compact emission, and/or low--surface--brightness structure that is resolved out by VLBI, and/or absorption/propagation effects such as free--free absorption in dense, ionized winds.

astro-ph.HE↗