arXiv subjects

Liang Zhang

Publications and source records attributed to Liang Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2026

Knowledge-guided Disentanglement with Atomic Actions for Action Recognition

Action recognition in complex scenes often involves multiple concurrent fine-grained actions, making it challenging to model internal action structures. Most existing methods rely on holistic representations, which are insufficient for capturing subtle interactions and fine-grained semantics. While recent prompt-based approaches introduce disentanglement, they lack explicit semantic guidance, and methods based solely on visual or structured cues remain coarse-grained. In this paper, we propose Knowledge-guided Disentanglement with Atomic Actions (KDA), which leverages fine-grained semantic knowledge to enhance action representations and enable more precise disentanglement. Specifically, we use Large Language Models (LLMs) to decompose action labels into atomic actions, providing explicit spatial-temporal semantics. A Knowledge Injection Module (KIM) first integrates atomic action knowledge into video features. Based on this enhanced representation, a Knowledge Disentanglement Module (KDM) further disentangles atomic action knowledge to produce more precise semantic guidance for action disentanglement. A Knowledge Disentanglement Loss (KD Loss) is introduced to encourage clearer disentanglement of knowledge components within KDM. Extensive experiments demonstrate that KDA improves feature discriminability and achieves state-of-the-art performance on multi-label action recognition benchmarks. Moreover, KIM and KDM can be readily integrated into other methods, demonstrating strong generality.

cs.CV↗

arXiv2026

CTR-Sink: Attention Sink for Language Models in Click-Through Rate Prediction

Click-Through Rate (CTR) prediction, a core task in recommendation systems, estimates user click likelihood using historical behavioral data. Modeling user behavior sequences as text to leverage Language Models (LMs) for this task has gained traction, owing to LMs' strong semantic understanding and contextual modeling capabilities. However, a critical structural gap exists: user behavior sequences consist of discrete actions connected by semantically empty separators, differing fundamentally from the coherent natural language in LM pre-training. This mismatch causes semantic fragmentation, where LM attention scatters across irrelevant tokens instead of focusing on meaningful behavior boundaries and inter-behavior relationships, degrading prediction performance. To address this, we propose $\textit{CTR-Sink}$, a novel framework introducing behavior-level attention sinks tailored for recommendation scenarios. Inspired by attention sink theory, it constructs attention focus sinks and dynamically regulates attention aggregation via external information. Specifically, we insert sink tokens between consecutive behaviors, incorporating recommendation-specific signals such as temporal distance to serve as stable attention sinks. To enhance generality, we design a two-stage training strategy that explicitly guides LM attention toward sink tokens and a attention sink mechanism that amplifies inter-sink dependencies to better capture behavioral correlations. Experiments on one industrial dataset and two open-source datasets (MovieLens, Kuairec), alongside visualization results, validate the method's effectiveness across scenarios. The source code of this paper has been made publicly available at https://github.com/UGUESS-lzx/CTR-SINK.

cs.CL↗

arXiv2026

X-ray and Radio campaign of the Z-source GX 340+0: discovery of X-ray polarization and its implications

We present the discovery of X-ray polarization from the neutron star low-mass X-ray binary and Z-source, GX~340$+$0, using an Imaging X-ray Polarimetry Explorer (IXPE) observation in March 2024. Along with the IXPE observation, we conducted an extensive X-ray and radio monitoring campaign to ascertain the source properties during and around the IXPE observation. The source was within the horizontal branch throughout the multiwavelength campaign. We measured a significant X-ray polarization in 2--8 keV with polarization degree (PD) = $4.02 \pm 0.35$% and polarization angle (PA) = $37.6 \pm 2.5^\circ$. The energy-dependent polarization indicates that in the 2-2.5 keV energy range, the PA is much lower, $\sim9\pm8^\circ$, while other energy bands are consistent with the PA found over 2.5--8 keV. The simultaneous AstroSat-IXPE spectro-polarimetric observations provide some evidence for independent polarization from various spectral components, hinting at a disparity in the PA from the accretion disk and the Comptonized emission, while suggesting an unpolarized emission from the blackbody component. Radio observations in the 0.7--9 GHz frequency range reveal a non-detection of radio emission in 0.7-1.5 GHz and a significant detection in 5.5--9 GHz, suggesting the presence of a spectral break in 1.5-5.5 GHz. Using ATCA observation we place upper limits on the radio polarization at $<$6% on the linear polarization and $<$4% on the circular polarization at 3$σ$ level. We discuss the origin of the X-ray polarization and its implications on the geometry of the spectral components.

astro-ph.HE↗

arXiv2026

Tensor Reduction of Sunset by Generating Function

Recently, the generating function has been proposed as an alternative reduction method. This method has been tested at the one-loop level, including the tensor reduction and propagators with higher powers. In this work, we initiate the study of the method for higher loops by focusing on the sunset diagram, which is the simplest nontrivial two-loop integral. By employing PV reduction equations together with syzygy equations, we construct a complete system of differential equations. Through series expansion, we derive a complete set of recurrence relations, which can efficiently reduce any high-rank tensor structure.

hep-th↗

arXiv2026

Resonance Femtoscopy Beyond the On-Shell Approximation

The observed shift of the $Δ(1232)$ resonance peak in $π$-$p$ femtoscopic correlations challenges the conventional Breit-Wigner description of resonances in femtoscopy. We revisit the Koonin-Pratt framework by formulating femtoscopy in the momentum-space representation. By employing the T-matrix approach to disentangle on-shell and off-shell contributions, we show that the finite spatial extent of the emission source naturally induces sensitivity to off-shell scattering dynamics. Using a Friedrichs-Lee model constrained by low-energy $π$-$p$ scattering data, we numerically demonstrate that this off-shell sensitivity leads to a peak shift accompanied by a dip on the high-momentum side of the peak. The predicted high-momentum side dip is absent in the data, pointing to source properties beyond the simple Gaussian approximation.

nucl-th↗

arXiv2026

Fast Optical Variability of the TeV Blazar PKS 1725+123 Observed by SVOM-VT and Insights from Multi-wavelength Follow-up Observations

PKS 1725+123 is a flat-spectrum radio quasar (FSRQ) with a redshift of $z=0.586$. The detection of this object in the TeV band was reported by the MAGIC telescopes and H.E.S.S. in August 2025. Subsequently, we promptly initiated Target-of-Opportunity observations using the Space-based multi-band astronomical Variable Objects Monitor (SVOM) satellite. By analyzing the observational optical data from SVOM-VT and comprehensively examining the Fermi-LAT and Swift-XRT observational data, it was found that the source is in a high-flux state across the optical, X-ray, and GeV $γ$-ray bands around the time of the TeV detections. Its optical flux reaches a historically unprecedented high level and shows significant variability on timescale as short as minutes. The variability is accompanied by changes in the color index, exhibiting a bluer when brighter behavior during the high-flux state. Based on the simultaneous multi-wavelength data, we construct the broadband spectral energy distribution (SED) of the source in the high-flux state. PKS 1725+123 demonstrates a remarkably high synchrotron peak frequency, which is distinctly different from that of other FSRQs. We propose a two-zone spine-sheath jet model to reproduce this SED. The optical--X-ray emission is generated by the synchrotron process of the relativistic electrons within a compact zone. The inverse Compton (IC) scattering processes of the same electron population contribute to the low-energy end of the Fermi-LAT spectrum, while the high-energy end of the Fermi-LAT spectrum is ascribed to the IC scattering of the synchrotron photons within the compact zone by the higher-energy electrons in an extended region.

astro-ph.HE↗

arXiv2026

A second-scale periodicity in an active repeating fast radio burst source

Fast radio bursts (FRBs) are fierce radio flashes from the deep sky. Abundant observations have indicated that highly magnetized neutron stars might be involved in these energetic bursts, but the underlying trigger mechanism is still enigmatic. Especially, the widely expected periodicity connected to the spin of the central engine has never been discovered, which leads to further debates on the nature of FRBs. Here we report the first discovery of a $\sim$ 1.7 s period in the repeating source of FRB 20201124A. This is an active repeater, from which more than 2800 bursts have been detected over a total of 49 days. The phase-folding method is adopted to analyze the bursts on each day separately. While no significant periodic signal is found in most days, a clear periodicity does appear on two specific days: a period of 1.706024(13) s on MJD 59310, and a slightly larger period of 1.707968(9) s on MJD 59347. A global Monte Carlo analysis based on all single-day datasets yields a significance level of $5.5 σ$ for the periodicity. A period derivative of $6.11(5)\times10^{-10}$ s s$^{-1}$ can be derived from these two periods, which further implies a surface magnetic field strength of $1.03\times10^{15}$ G and a spin-down age of $44$ years for the central engine. It is concluded that FRB 20201124A should be associated with a young magnetar.

astro-ph.HE↗

arXiv2026

Time domain Stokes mechanism of pair correlated k gap solitons in nonlinear photonic time crystal slabs

Pair generation in time-varying media is commonly attributed to time reflection at temporal boundaries or to amplification inside momentum k gaps. Here we show that these two processes are connected by the time domain Stokes phenomenon. A finite duration photonic time crystal (PTC) slab provides the necessary Stokes connection between the incident vacuum mode, transient k gap amplification, and time boundary scattering. With Kerr nonlinearity, the otherwise unbounded amplification is arrested, spawning Kerr stabilized k gap solitons. When these solitons cross the exit boundary of the time slab, Stokes induced mode conversion produces a secondary pair generation process, yielding four spatially separated and entangled pulse branches. Detection of a backward propagating light pulse therefore heralds its forward propagating partner. We further propose combined Hanbury Brown Twiss and Hong Ou Mandel measurements to test their nonclassical correlations. These results reveal a link between asymptotic Stokes physics and quantum temporal scattering in PTCs, and suggest a route toward ultrafast heralded quantum light sources.

physics.optics↗

arXiv2026

Representation Robustness Under Executable Reasoning Constraints in Large Language Models for Mathematical Problem Solving

Large language models (LLMs) are increasingly evaluated on mathematical problem solving, yet prior work often treats representationally equivalent formulations as interchangeable and conflates reasoning errors with interface failures. This paper investigates representation robustness in LLM-based mathematical problem solving by systematically varying surface representations of the same underlying problems, including story problems, word-equations, symbolic equations, and isomorphic paraphrases. Using a curated dataset of mathematically equivalent problems, we evaluate five contemporary LLMs under a direct answer generation condition. We find substantial representational sensitivity: models frequently change correctness across equivalent formulations, with nontrivial flip rates across story, symbolic, and word-equation variants. We also observe systematic regressions under isomorphic reformulations, showing that even subtle paraphrase-level changes can degrade performance despite preserved mathematical structure. We then evaluate a code-augmented condition in which models externalize reasoning as executable Python code that is run locally for validation. This interface reveals strong latent reasoning capability in some models that perform poorly under direct prompting, but it does not uniformly improve robustness. Instead, failures shift across interaction layers, from opaque reasoning errors to protocol violations and execution failures. Even when executable reasoning succeeds, representation sensitivity often persists. Overall, our results show that reasoning scaffolds do not eliminate representational brittleness, but expose new tradeoffs among correctness, reliability, latency, and cost. We argue that representation should be treated as a first-class interface design variable in LLM evaluation and deployment, especially for AI-assisted problem-solving systems.

cs.AI↗

arXiv2026

Breathing k-Gap Events and Instability on Instability in Nonlinear Photonic Time Crystals

Photonic time crystals (PTCs) host momentum bandgaps, or k gaps, that enable parametric amplification and lasing of seeded fields. In nonlinear PTCs, Kerr saturation dynamically suppresses the exponential growth, reshaping k-gap amplification into an active, spatially homogeneous k gap soliton train. Here, we show that a localized perturbation on this unstable background then nucleates a transient spatiotemporal excitation: the breathing k gap event. Unlike Peregrine breathers emerging from modulational instability on a planewave background, this event extracts energy from competing host k gap solitons and remains sustained by their interaction. We identify this process as an instability on instability mechanism intrinsic to nonlinear k gap dynamics. The event is robust against noise and disorder, and can be deterministically reshaped into collective breathing patterns by periodic and phase engineered seeding. These results establish k gap engineering as a route to generating and controlling extreme spatiotemporal waves in photonic time varying media.

physics.optics↗

arXiv2026

Lower Bounds for Anytime Acceleration of Gradient Descent

Recent work suggests that the convergence rate of gradient descent (GD) in smooth convex optimization can be significantly improved by employing large stepsizes that may violate the descent property. In particular, if the total number of iterations $n$ is given, an $O(n^{-1.271})$ convergence rate can be achieved for both function value and squared gradient norm minimization. On the other hand, in the setting of anytime convergence, where $n$ is not known in advance, the best known rates of GD are much slower: $O(n^{-1.119})$ for function value minimization and $O(n^{-1})$ for squared gradient norm minimization. It remains open whether any of these upper bounds can be improved, as they are far from the classical $Ω(n^{-2})$ lower bound for any first-order method. In this work, we establish two lower bounds on the anytime convergence of GD. We show that no positive stepsize schedule can achieve an $o(n^{-1.334})$ anytime rate for function value minimization, nor an $o(n^{-1})$ anytime rate for squared gradient norm minimization. The key ingredients of our analysis are novel upper bounds on the number and the magnitude of large stepsizes, derived by analyzing GD on quadratic functions and variants of Huber functions. Our work provides the first lower bounds for the COLT 2024 open problem posed by Kornowski and Shamir regarding the optimal anytime convergence rates of GD.

math.OC↗

arXiv2026

Zeroth-Order Optimization at the Edge of Stability

Zeroth-order (ZO) methods are widely used when gradients are unavailable or prohibitively expensive, including black-box learning and memory-efficient fine-tuning of large models, yet their optimization dynamics in deep learning remain underexplored. In this work, we provide an explicit step size condition that exactly captures the (mean-square) linear stability of a family of ZO methods based on the standard two-point estimator. Our characterization reveals a sharp contrast with first-order (FO) methods: whereas FO stability is governed solely by the largest Hessian eigenvalue, mean-square stability of ZO methods depends on the entire Hessian spectrum. Since computing the full Hessian spectrum is infeasible in practical neural network training, we further derive tractable stability bounds that depend only on the largest eigenvalue and the Hessian trace. Empirically, we find that full-batch ZO methods operate at the edge of stability: ZO-GD, ZO-GDM, and ZO-Adam consistently stabilize near the predicted stability boundary across a range of deep learning training problems. Our results highlight an implicit regularization effect specific to ZO methods, where large step sizes primarily regularize the Hessian trace, whereas in FO methods they regularize the top eigenvalue.

cs.LG↗

arXiv2026

Direction-Magnitude Decomposition for Low-Rank Matrix Optimization: Faster Convergence and Saddle-to-saddle Dynamics

Low-rank matrix optimization is often carried out via the Burer-Monteiro (BM) formulation, but choosing the factorization rank $r$ is delicate and can substantially slow optimization. We propose a unified framework, termed direction-magnitude decomposition (DMD), that decomposes the optimization variable to improve optimization efficiency even when the target rank is unknown. We develop two DMD-based approaches and establish their theoretical advantages on the canonical problem of matrix factorization. The first, overparameterized DMD, uses a rank $r$ larger than necessary and enjoys faster convergence as $r$ increases. The second, recursive DMD, is motivated by the incremental eigenpair learning, or saddle-to-saddle, behavior of overparameterized DMD. It achieves lower memory and computational costs, complementing overparameterized DMD. Both approaches are exponentially faster than gradient descent applied to the BM formulation. Numerical experiments on matrix factorization, sensing, and completion corroborate our theoretical findings and demonstrate the practical effectiveness of DMD.

math.OC↗

arXiv2026

Quantization and Biphoton Statistics of k-Gap Solitons in Nonlinear Photonic Time Crystals

Nonlinear photonic time crystals (PTCs) can support solitons inside momentum k gaps, where the amplification of k gap modes is saturated by Kerr nonlinearity, forming spatially homogeneous but temporally localized excitations. Yet their quantum nature remains unclear. Here we quantize nonlinear k gap dynamics of PTCs and show that k gap solitons are represented by biphoton Fock ladder states. K gap amplification drives two-mode squeezing of the biphoton, while Kerr nonlinearity generates an anharmonic potential along the biphoton Fock ladder that balances this squeezing process, creating a finite biphoton number turning point and giving rise to quantum collapse and revival dynamics and nonclassical phase space interference. We further analyze how photon loss and dephasing reshape the biphoton statistics of quantized k gap solitons. Our results establish a biphoton Fock space description of k gap soliton quantization and provide a framework for studying quantum nonlinear excitations and entangled light generation in photonic time crystals.

physics.optics↗

arXiv2026

TrajRS: Towards Certified Robustness in Pedestrian Trajectory Prediction

The robustness of trajectory prediction models is crucial for developing safe autonomous driving systems. Adversarial attacks on trajectory prediction can significantly impair the accuracy of predicted trajectories, leading to hazardous driving behaviors. While heuristic defense strategies have been implemented to enhance the robustness of trajectory prediction models, these measures often fail against more sophisticated, targeted adversarial attacks. Hence, there is a pressing need to establish verifiable safety assurances for trajectory prediction models. In this paper, we extend the traditional Randomized Smoothing framework to "TrajRS", which provides a certified robust radius for smoothed trajectory predictors. We clarify and expand the formal definitions of robustness in trajectory prediction and tailor the practical TrajRS scheme specifically to "robustness for the optimal prediction" and "robustness for all possible predictions". An extensive set of experiments demonstrates that TrajRS effectively achieves robustness certification for all smoothed pedestrian trajectory predictors in this work.

cs.AI↗

arXiv2026

Bridging Vision and Language Concepts through Optimal Transport Semantic Flow

Concept Bottleneck Models (CBMs) promise transparent reasoning by predicting through human-interpretable concepts, yet their effectiveness fundamentally depends on how well visual and textual representations are aligned or matched. Existing vision-language CBMs often rely on pre-aligned encoders or global cosine similarity, which obscures fine-grained concept localization and fails to reflect true semantic geometry. In this work, we rethink concept alignment as a dynamic cross-modal transport process instead of static projection and propose the Optimal Transport Flow Concept Bottleneck Model (OTF-CBM). It first learns a data-driven semantic cost via Inverse Optimal Transport to measure cross-modal distances, and then performs unbalanced optimal-transport-based flow matching to model semantic transitions between visual patches and textual concepts. With velocity-based concept activation, OTF-CBM captures interpretable geometric relations without ODE integration. Experiments further show that OTF-CBM achieves superior classification accuracy and concept faithfulness, offering a new geometric and dynamical perspective for interpretable cross-modal reasoning.

cs.CV↗

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↗