arXiv subjects

Song Zhang

Publications and source records attributed to Song Zhang.

At least 19 recordsLinked to original sources

arXiv2026

A Top-Down Deriving Mechanism in Haskell

In Haskell, class instance deriving and related mechanisms are used pervasively. Their influence extends beyond Haskell: Rust adopts similar ideas in its trait system, and Java libraries such as Lombok use annotations to generate methods such as equals and toString. This paper proposes an extension to Haskell's existing deriving machinery so that it can operate over composite data types and multi-level type class hierarchies. With this approach, programmers no longer need to write deriving clauses for every data declaration or explicitly enumerate all superclasses in a type class hierarchy.

cs.PL↗

arXiv2026

Resonance Femtoscopy Beyond the On-Shell Approximation

The observed shift of the $\Delta(1232)$ resonance peak in $\pi$-$p$ 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 $\pi$-$p$ 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

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 $J/\psi$ source via $p$-$J/\psi$ correlations, using HAL QCD-derived $NJ/\psi$ 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

Beyond GSD-as-Token: Continuous Scale Conditioning for Remote Sensing VLMs

Remote sensing vision-language models (RS-VLMs) face a fundamental mismatch with natural-image counterparts: the same geographic object exhibits radically different visual evidence across ground sampling distances (GSDs) spanning multiple orders of magnitude. Yet existing RS-VLMs often discard GSD or inject it as a discrete text token, forcing a single static parameter set to absorb the entire scale spectrum. We introduce ScaleEarth, a parameter-efficient fine-tuning framework built on Qwen3-VL that treats GSD as a continuous conditioning variable governing the model's computation path. At its core, CS-HLoRA (Continuous Scale-Conditioned Hyper-LoRA) modulates the LoRA low-rank subspace through a GSD-driven gate, enabling the model to dynamically route computation by physical scale. To remove reliance on sensor metadata at deployment, we pair CS-HLoRA with SSE-U, a lightweight heteroscedastic sub-head that predicts GSD and its uncertainty from visual features. To provide matching supervision, we construct GeoScale-VQA, a 1.5M-sample scale-layered RS-VQA corpus whose question-answer generation is conditioned on the same physical scalar that drives CS-HLoRA, forming a closed method-data loop. Trained with QLoRA on an 8B backbone, ScaleEarth achieves state-of-the-art results on remote-sensing benchmarks covering diverse Earth-system tasks, including XLRS-Bench and OmniEarth-Bench.

cs.CV↗

arXiv2026

A Prediction-as-Perception Framework for 3D Object Detection

Humans combine prediction and perception to observe the world. When faced with rapidly moving birds or insects, we can only perceive them clearly by predicting their next position and focusing our gaze there. Inspired by this, this paper proposes the Prediction-As-Perception (PAP) framework, integrating a prediction-perception architecture into 3D object perception tasks to enhance the model's perceptual accuracy. The PAP framework consists of two main modules: prediction and perception, primarily utilizing continuous frame information as input. Firstly, the prediction module forecasts the potential future positions of ego vehicles and surrounding traffic participants based on the perception results of the current frame. These predicted positions are then passed as queries to the perception module of the subsequent frame. The perceived results are iteratively fed back into the prediction module. We evaluated the PAP structure using the end-to-end model UniAD on the nuScenes dataset. The results demonstrate that the PAP structure improves UniAD's target tracking accuracy by 10% and increases the inference speed by 15%. This indicates that such a biomimetic design significantly enhances the efficiency and accuracy of perception models while reducing computational resource consumption.

cs.CV↗

arXiv2026

Risk-Controllable Multi-View Diffusion for Driving Scenario Generation

Generating safety-critical driving scenarios is crucial for evaluating and improving autonomous driving systems, but long-tail risky situations are rarely observed in real-world data and difficult to specify through manual scenario design. Existing generative approaches typically treat risk as an after-the-fact label and struggle to maintain geometric consistency in multi-view driving scenes. We present RiskMV-DPO, a general and systematic pipeline for physically-informed, risk-controllable multi-view scenario generation. By integrating target risk levels with physically-grounded risk modeling, we synthesize diverse and high-stakes dynamic trajectories that serve as explicit geometric anchors for a diffusion-based video generator. To ensure spatial-temporal coherence and geometric fidelity, we introduce a geometry-appearance alignment module and a region-aware direct preference optimization (RA-DPO) strategy with motion-aware masking to focus learning on localized dynamic regions. Experiments on the nuScenes dataset show that RiskMV-DPO can freely generate a wide spectrum of diverse scenarios while maintaining visual quality, improving 3D detection mAP from 18.17 to 30.50 and reducing FID to 15.70. Our work shifts the role of world models from passive environment prediction to proactive, risk-controllable synthesis, providing a scalable toolchain for the development of embodied intelligence.

cs.CV↗

arXiv2025

Unfolding Baryon Number Fluctuations from Correlations of Light Nuclei Production in Heavy-Ion Collisions

Event-by-event fluctuations of the baryon number, which is mostly carried by protons and neutrons, in relativistic heavy-ion collisions provide a sensitive probe for locating the conjectured critical point in the quantum chromodynamics (QCD) phase diagram. Since current experiments have limited access to neutron fluctuations because detectors are largely insensitive to neutrons, measurements of (net-)proton fluctuations are often used as a proxy for (net-)baryon number fluctuations. Although direct measurements of neutron fluctuations are challenging, their information are encoded in the production and correlations of light nuclei, when they are formed through coalescence of nucleons at kinetic freeze-out. Here, we propose to unfold neutron fluctuations from correlations among light nuclei produced in heavy-ion collisions. Model calculations validate this approach and show that baryon number fluctuations can be unfolded up to the third order. For fourth and higher-order cumulants, however, the uncertainties become sizable, indicating that further methodological developments and refinements are required.

nucl-th↗

arXiv2025

Experimental Methods, Health Indicators, and Diagnostic Strategies for Retired Lithium-ion Batteries: A Comprehensive Review

Reliable health assessment of retired lithium-ion batteries is essential for safe and economically viable second-life deployment, yet remains difficult due to sparse measurements, incomplete historical records, heterogeneous chemistries, and limited or noisy battery health labels. Conventional laboratory diagnostics, such as full charge-discharge cycling, pulse tests, Electrochemical Impedance Spectroscopy (EIS) measurements, and thermal characterization, provide accurate degradation information but are too time-consuming, equipment-intensive, or condition-sensitive to be applied at scale during retirement-stage sorting, leaving real-world datasets fragmented and inconsistent. This review synthesizes recent advances that address these constraints through physical health indicators, experiment testing methods, data-generation and augmentation techniques, and a spectrum of learning-based modeling routes spanning supervised, semi-supervised, weakly supervised, and unsupervised paradigms. We highlight how minimal-test features, synthetic data, domain-invariant representations, and uncertainty-aware prediction enable robust inference under limited or approximate labels and across mixed chemistries and operating histories. A comparative evaluation further reveals trade-offs in accuracy, interpretability, scalability, and computational burden. Looking forward, progress toward physically constrained generative models, cross-chemistry generalization, calibrated uncertainty estimation, and standardized benchmarks will be crucial for building reliable, scalable, and deployment-ready health prediction tools tailored to the realities of retired-battery applications.

eess.SP↗

arXiv2025

Shedding Light on (Anti-)nuclei Production with Pion-Nucleus Femtoscopy

High-energy nuclear collisions provide a unique environment for synthesizing both nuclei and antinuclei (such as $\bar{d}$ and $^4\overline{\text{He}}$) at temperatures ($k_BT\sim100$ MeV) much higher than their binding energies per nucleon of a few MeV. The underlying production mechanism, whether through statistical hadronization, nucleon coalescence, or dynamical regeneration and disintegration, remains unsettled. Here we address this question using pion-nucleus femtoscopy. By solving relativistic kinetic equations for pion-catalyzed reactions ($\pi NN \leftrightarrow \pi d$) for deuteron production and including final-state $p-$wave scatterings derived from an established effective interaction, we successfully reproduce the resonance peaks of both $\pi^+-p$ and $\pi^+-d$ femtoscopic correlations observed in $pp$ collisions at $\sqrt{s} = 13~\mathrm{TeV}$. The interplay between $\Delta$ resonance and $p$-wave scatterings shifts both correlation peaks downward by about $70\text{ MeV}$ relative to vacuum $\Delta$ decay. Conversely, both the nucleon coalescence model and the statistical hadronization model significantly underestimate the data and produce additional dips that are absent from the data. These results provide compelling evidence that pion-catalyzed reactions play a dominant role in the production of light (anti-)nuclei in high-energy nuclear collisions and cosmic rays.

nucl-th↗

arXiv2025

Assessing background effects in search of the chiral vortical effect in relativistic heavy-ion collisions

The search for the Chiral Vortical Effect (CVE) in relativistic heavy-ion collisions is carried out by measuring azimuthal correlators for baryon pairs such as $\Lambda$ and protons. Experimental results from the ALICE collaboration show significant separations in these observables, however, the interpretation remains unclear. It is believed that background contributions from baryon production mechanisms may play an important role. Using three phenomenological models, the Blast Wave, AMPT, and AVFD+UrQMD, we systematically investigate the background effects in Pb--Pb collisions at \snn = 5.02 TeV. We demonstrate that local baryon conservation, as well as hadronic annihilation processes, can significantly influence the correlators. The feed-down contribution from secondary protons is also estimated. Our study provides a foundation for disentangling background mechanisms and further facilitates the search for the CVE.

nucl-th↗

arXiv2025

From Hyperons to Hypernuclei: A New Route to Unravel Proton Spin Polarization

Ultra-relativistic nuclear collisions create the quark-gluon plasma (QGP) known as the hottest, least viscous, and most vortical fluid ever produced in terrestrial laboratories. Its vortical structure has been uncovered through the spin polarization of Lambda ($\Lambda$) hyperons, attributed to the spin-orbit coupling that transfers the system's orbital angular momentum to the quark spin, which is then inherited by hadrons via quark recombination or coalescence. However, $\Lambda$ polarization reflects primarily the strange-quark component, leaving the spin dynamics of the up and down quarks largely unexplored. Although the proton is an ideal probe, its stability makes direct measurements experimentally challenging. Here, we propose to unravel proton spin polarization via hypertriton ($^3_\Lambda \text{H}$) measurements, exploiting the fact that spin information is preserved when polarized nucleons and $\Lambda$ coalesce to form hypertriton. We show that, over a broad range of collision energies, the polarizations of proton, $\Lambda$, and hypertriton are related by a simple linear scaling law. Since both $\Lambda$ and hypertriton polarizations can be measured via their self-analyzing weak decays, this linear relation provides a practical experimental avenue for accessing spin polarizations of protons and neutrons-the dominant baryonic degrees of freedom in nuclear collisions.

nucl-th↗

arXiv2025

Huawei Cloud Model-as-a-Service on the CloudMatrix384 SuperPod

Scaled-out MoE LLMs and scaled-up SuperPods create new systems challenges for production Model-as-a-Service (MaaS), requiring disaggregation, low-latency communication, and decentralized serving. This report presents xDeepServe, the production serving system behind Huawei Cloud's MaaS offering on CloudMatrix384, a 48-server SuperPod with 384 Ascend 910C chips connected by a high-bandwidth UB fabric and global shared memory. It serves models including DeepSeek, Kimi, GLM, Qwen, and MiniMax, among others. xDeepServe is built around Transformerless, a disaggregated execution architecture that decomposes transformer inference into modular units -- attention, feedforward, and MoE -- and supports disaggregated Prefill-Decode and MoE-Attention deployments. To enable disaggregation, we develop XCCL, a memory-semantic communication layer providing microsecond-level point-to-point and scalable all-to-all primitives, and we extend FlowServe with decentralized DP groups and techniques to mitigate stragglers and synchronization variance. In a peak decoding configuration, xDeepServe reaches 2400 tokens/s per Ascend 910C chip at ~50ms time-per-output-token (TPOT).

cs.DC↗

arXiv2025

Particle species dependence of elliptic flow fluctuations in Pb-Pb collisions at LHC energies in a multiphase transport model

The fluctuations of elliptic flow (\vtwo) in relativistic heavy-ion collisions offer a powerful tool to probe the collective behavior and transport properties of the quark-gluon plasma (QGP). The dependence of these fluctuations on particle species further sheds light on the hadronization mechanism. At LHC energies, the ALICE experiment has measured $v_2$ fluctuations for charged pions, kaons, and (anti-)protons via the ratio of \vtwo measured with respect to the spectator plane (\vtwosp) and from the four-particle cumulants (\vtwofour). However, the observed dependencies on transverse momentum and particle type remain not fully understood. In this study, we perform a phenomenological investigation using a multiphase transport (AMPT) model, which allows us to trace the full evolution of flow fluctuations intertwined with the quark coalescence. The results qualitatively reproduce the ALICE measurements and offer deeper insights into the transport dynamics and hadronization of the QGP.

nucl-th↗

arXiv2025

Investigating the pion emission source in pp collisions using the AMPT model with sub-nucleon structure

The measurement of momentum correlations of identical pions serves as a fundamental tool for probing the space-time properties of the particle emitting source created in high-energy collisions. Recent experimental results have shown that, in pp collisions, the size of the one-dimensional primordial source depends on the transverse mass (\mt) of hadron pairs, following a common scaling behavior, similar to that observed in Pb--Pb collisions. In this work, a systematic study of the \pipi source function and correlation function is performed using the multiphase transport model (AMPT) to understand the properties of the emitting source created in high multiplicity pp collisions at $\sqrt{s}=13$ TeV. The \mt scaling behavior and pion emission source radii measured by ALICE experiment can be well described the model with sub-nucleon structure. These studies shed new light on the understanding of the effective size of the \pipi emission source and on studying the intensity interferometry in small systems with a transport model.

nucl-th↗

arXiv2025

Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation

We present Hunyuan3D 2.0, an advanced large-scale 3D synthesis system for generating high-resolution textured 3D assets. This system includes two foundation components: a large-scale shape generation model -- Hunyuan3D-DiT, and a large-scale texture synthesis model -- Hunyuan3D-Paint. The shape generative model, built on a scalable flow-based diffusion transformer, aims to create geometry that properly aligns with a given condition image, laying a solid foundation for downstream applications. The texture synthesis model, benefiting from strong geometric and diffusion priors, produces high-resolution and vibrant texture maps for either generated or hand-crafted meshes. Furthermore, we build Hunyuan3D-Studio -- a versatile, user-friendly production platform that simplifies the re-creation process of 3D assets. It allows both professional and amateur users to manipulate or even animate their meshes efficiently. We systematically evaluate our models, showing that Hunyuan3D 2.0 outperforms previous state-of-the-art models, including the open-source models and closed-source models in geometry details, condition alignment, texture quality, and etc. Hunyuan3D 2.0 is publicly released in order to fill the gaps in the open-source 3D community for large-scale foundation generative models. The code and pre-trained weights of our models are available at: https://github.com/Tencent/Hunyuan3D-2

cs.CV↗

arXiv2025

TS-SatMVSNet: Slope Aware Height Estimation for Large-Scale Earth Terrain Multi-view Stereo

3D terrain reconstruction with remote sensing imagery achieves cost-effective and large-scale earth observation and is crucial for safeguarding natural disasters, monitoring ecological changes, and preserving the environment.Recently, learning-based multi-view stereo~(MVS) methods have shown promise in this task. However, these methods simply modify the general learning-based MVS framework for height estimation, which overlooks the terrain characteristics and results in insufficient accuracy. Considering that the Earth's surface generally undulates with no drastic changes and can be measured by slope, integrating slope considerations into MVS frameworks could enhance the accuracy of terrain reconstructions. To this end, we propose an end-to-end slope-aware height estimation network named TS-SatMVSNet for large-scale remote sensing terrain reconstruction.To effectively obtain the slope representation, drawing from mathematical gradient concepts, we innovatively proposed a height-based slope calculation strategy to first calculate a slope map from a height map to measure the terrain undulation. To fully integrate slope information into the MVS pipeline, we separately design two slope-guided modules to enhance reconstruction outcomes at both micro and macro levels. Specifically, at the micro level, we designed a slope-guided interval partition module for refined height estimation using slope values. At the macro level, a height correction module is proposed, using a learnable Gaussian smoothing operator to amend the inaccurate height values. Additionally, to enhance the efficacy of height estimation, we proposed a slope direction loss for implicitly optimizing height estimation results. Extensive experiments on the WHU-TLC dataset and MVS3D dataset show that our proposed method achieves state-of-the-art performance and demonstrates competitive generalization ability.

cs.CV↗

arXiv2024

EGSRAL: An Enhanced 3D Gaussian Splatting based Renderer with Automated Labeling for Large-Scale Driving Scene

3D Gaussian Splatting (3D GS) has gained popularity due to its faster rendering speed and high-quality novel view synthesis. Some researchers have explored using 3D GS for reconstructing driving scenes. However, these methods often rely on various data types, such as depth maps, 3D boxes, and trajectories of moving objects. Additionally, the lack of annotations for synthesized images limits their direct application in downstream tasks. To address these issues, we propose EGSRAL, a 3D GS-based method that relies solely on training images without extra annotations. EGSRAL enhances 3D GS's capability to model both dynamic objects and static backgrounds and introduces a novel adaptor for auto labeling, generating corresponding annotations based on existing annotations. We also propose a grouping strategy for vanilla 3D GS to address perspective issues in rendering large-scale, complex scenes. Our method achieves state-of-the-art performance on multiple datasets without any extra annotation. For example, the PSNR metric reaches 29.04 on the nuScenes dataset. Moreover, our automated labeling can significantly improve the performance of 2D/3D detection tasks. Code is available at https://github.com/jiangxb98/EGSRAL.

cs.CV↗

arXiv2024

PDCFNet: Enhancing Underwater Images through Pixel Difference Convolution

Majority of deep learning methods utilize vanilla convolution for enhancing underwater images. While vanilla convolution excels in capturing local features and learning the spatial hierarchical structure of images, it tends to smooth input images, which can somewhat limit feature expression and modeling. A prominent characteristic of underwater degraded images is blur, and the goal of enhancement is to make the textures and details (high-frequency features) in the images more visible. Therefore, we believe that leveraging high-frequency features can improve enhancement performance. To address this, we introduce Pixel Difference Convolution (PDC), which focuses on gradient information with significant changes in the image, thereby improving the modeling of enhanced images. We propose an underwater image enhancement network, PDCFNet, based on PDC and cross-level feature fusion. Specifically, we design a detail enhancement module based on PDC that employs parallel PDCs to capture high-frequency features, leading to better detail and texture enhancement. The designed cross-level feature fusion module performs operations such as concatenation and multiplication on features from different levels, ensuring sufficient interaction and enhancement between diverse features. Our proposed PDCFNet achieves a PSNR of 27.37 and an SSIM of 92.02 on the UIEB dataset, attaining the best performance to date. Our code is available at https://github.com/zhangsong1213/PDCFNet.

cs.CV↗