arXiv subjects

Wei Zuo

Publications and source records attributed to Wei Zuo.

At least 19 recordsLinked to original sources

arXiv2026

Embodied Multimedia: A Tutorial

Traditional multimedia technology has been built around optimizing content delivery for human observers, from perceptually driven compression standards to human-centric quality metrics. With the rapid rise of embodied intelligence, autonomous agents must perceive, reason, and act within the physical world in real time, exposing fundamental mismatches between conventional multimedia infrastructure and the demands of embodied tasks. In this regard, this tutorial paper formally introduces Embodied Multimedia as a cross-disciplinary research paradigm that treats multimodal data as the perceptual and communicative substrate spanning the full perception-decision-action loop. To be specific, we present a four-layer unified architecture comprising Data, Communication, Cognitive, and Evaluation layers, and provide a structured review of key enabling technologies within each layer. Furthermore, we identify five frontier application directions where Embodied Multimedia is positioned to serve a foundational role: multimedia communication, physical intelligence, embodied anomaly perception, the metaverse and interactive multimedia, and AI-driven art creation. Open technical challenges and future research directions are discussed to guide the community in this emerging field.

cs.MM↗

arXiv2026

LAGS: Low-Altitude Gaussian Splatting with Groupwise Heterogeneous Graph Learning

Low-altitude Gaussian splatting (LAGS) facilitates 3D scene reconstruction by aggregating aerial images from distributed drones. However, as LAGS prioritizes maximizing reconstruction quality over communication throughput, existing low-altitude resource allocation schemes become inefficient. This inefficiency stems from their failure to account for image diversity introduced by varying viewpoints. To fill this gap, we propose a groupwise heterogeneous graph neural network (GW-HGNN) for LAGS resource allocation. GW-HGNN explicitly models the non-uniform contribution of different image groups to the reconstruction process, thus automatically balancing data fidelity and transmission cost. The key insight of GW-HGNN is to transform LAGS losses and communication constraints into graph learning costs for dual-level message passing. Experiments on real-world LAGS datasets demonstrate that GW-HGNN significantly outperforms state-of-the-art benchmarks across key rendering metrics, including PSNR, SSIM, and LPIPS. Furthermore, GW-HGNN reduces computational latency by approximately 100x compared to the widely-used MOSEK solver, achieving millisecond-level inference suitable for real-time deployment.

cs.CV↗

arXiv2026

Efficient Transceiver Design for Aerial Image Transmission and Large-scale Scene Reconstruction

Large-scale three-dimensional (3D) scene reconstruction in low-altitude intelligent networks (LAIN) demands highly efficient wireless image transmission. However, existing schemes struggle to balance severe pilot overhead with the transmission accuracy required to maintain reconstruction fidelity. To strike a balance between efficiency and reliability, this paper proposes a novel deep learning-based end-to-end (E2E) transceiver design that integrates 3D Gaussian Splatting (3DGS) directly into the training process. By jointly optimizing the communication modules via the combined 3DGS rendering loss, our approach explicitly improves scene recovery quality. Furthermore, this task-driven framework enables the use of a sparse pilot scheme, significantly reducing transmission overhead while maintaining robust image recovery under low-altitude channel conditions. Extensive experiments on real-world aerial image datasets demonstrate that the proposed E2E design significantly outperforms existing baselines, delivering superior transmission performance and accurate 3D scene reconstructions.

cs.CV↗

arXiv2026

Impact of neutron-proton pairing on the nucleon high-momentum distribution in symmetric nuclear matter

The effect of neutron-proton ($np$) pairing on the high-momentum tail (HMT) of nucleon momentum distributions in symmetric nuclear matter is investigated within a combined framework of the extended Brueckner-Hartree-Fock approach with off-shell BCS theory. The HMT ratio, quantifying the high-momentum fraction in the BCS state relative to the normal state, reaches about $1.06$ around the density of $0.052\ \mathrm{fm}^{-3}$, indicating that the maximal contribution of the $np$ pairing, amounts to approximately 6\% that from short-range correlations (SRCs). This contribution exhibits a density dependence that closely follows the squared relative pairing gap $\widetilde{\Delta}_F=Z_F\Delta(k_F)$ with respect to the kinetic energy $E_{k_F}^*$ evaluated using the effective mass, suggesting that $\widetilde{\Delta}_F^2/E_{k_F}^{*2}$ provides a qualitative measure of the $np$ pairing effect on the HMT. These findings highlight the significant role of $np$ pairing and its interplay with SRCs in shaping nucleon momentum distributions in nuclear matter.

nucl-th↗

arXiv2026

ReMemNav: A Rethinking and Memory-Augmented Framework for Zero-Shot Object Navigation

Zero-shot object navigation requires agents to locate unseen target objects in unfamiliar environments without prior maps or task-specific training which remains a significant challenge. Although recent advancements in vision-language models(VLMs) provide promising commonsense reasoning capabilities for this task, these models still suffer from spatial hallucinations, local exploration deadlocks, and a disconnect between high-level semantic intent and low-level control. In this regard, we propose a novel hierarchical navigation framework named ReMemNav, which seamlessly integrates panoramic semantic priors and episodic memory with VLMs. We introduce the Recognize Anything Model to anchor the spatial reasoning process of the VLM. We also design an adaptive dual-modal rethinking mechanism based on an episodic semantic buffer queue. The proposed mechanism actively verifies target visibility and corrects decisions using historical memory to prevent deadlocks. For low-level action execution, ReMemNav extracts a sequence of feasible actions using depth masks, allowing the VLM to select the optimal action for mapping into actual spatial movement. Extensive evaluations on HM3D and MP3D demonstrate that ReMemNav outperforms existing training-free zero-shot baselines in both success rate and exploration efficiency. Specifically, we achieve significant absolute performance improvements, with SR and SPL increasing by 1.7% and 7.0% on HM3D v0.1, 18.2% and 11.1% on HM3D v0.2, and 8.7% and 7.9% on MP3D.

cs.RO↗

arXiv2026

Microscopic Optical Potential from Brueckner-Hartree-Fock Theory

Modern Brueckner-Hartree-Fock (BHF) calculations are very successful in describing various properties of symmetric and asymmetric nuclear matter. Within BHF theory a microscopic optical potential (MOP) for nucleon-nucleus scattering is developed. First, we parametrize the energy and density dependence of complex optical potentials in nuclear matter based on BHF calculations and then we construct the MOP for finite nuclei with the local density approximation extended to include the finite-range effects. The density distribution and the spin-orbit contribution are calculated from the Hartree-Fock (HF) approximation with LNS5 Skyrme interaction, the latter being constrained by the BHF results. The central real and imaginary potentials turn out to be quantitatively consistent with the phenomenological global Koning-Delaroche (KD) potentials. The performance of MOP is evaluated by considering neutron/proton scattering on $^{40,48}$Ca. The elastic scattering differential cross sections, analyzing powers and total/reaction cross sections are analyzed in the energy below 200 MeV. A good agreement between the theoretical results and the measurements is achieved. Since our results are presented in the analytic forms, they can thus be used easily in the analysis of the experimental data of the nucleon scattering on exotic nuclei.

nucl-th↗

arXiv2026

HPTune: Hierarchical Proactive Tuning for Collision-Free Model Predictive Control

Parameter tuning is a powerful approach to enhance adaptability in model predictive control (MPC) motion planners. However, existing methods typically operate in a myopic fashion that only evaluates executed actions, leading to inefficient parameter updates due to the sparsity of failure events (e.g., obstacle nearness or collision). To cope with this issue, we propose to extend evaluation from executed to non-executed actions, yielding a hierarchical proactive tuning (HPTune) framework that combines both a fast-level tuning and a slow-level tuning. The fast one adopts risk indicators of predictive closing speed and predictive proximity distance, and the slow one leverages an extended evaluation loss for closed-loop backpropagation. Additionally, we integrate HPTune with the Doppler LiDAR that provides obstacle velocities apart from position-only measurements for enhanced motion predictions, thus facilitating the implementation of HPTune. Extensive experiments on high-fidelity simulator demonstrate that HPTune achieves efficient MPC tuning and outperforms various baseline schemes in complex environments. It is found that HPTune enables situation-tailored motion planning by formulating a safe, agile collision avoidance strategy.

cs.RO↗

arXiv2025

DPNet: Doppler LiDAR Motion Planning for Highly-Dynamic Environments

Existing motion planning methods often struggle with rapid-motion obstacles due to an insufficient understanding of environmental changes. To address this, we propose integrating motion planners with Doppler LiDARs, which provide not only ranging measurements but also instantaneous point velocities. However, this integration is nontrivial due to the requirements of high accuracy and high frequency. To this end, we introduce Doppler Planning Network (DPNet), which tracks and reacts to rapid obstacles via Doppler model-based learning. We first propose a Doppler Kalman neural network (D-KalmanNet) to track obstacle states under a partially observable Gaussian state space model. We then leverage the predicted motions of obstacles to construct a Doppler-tuned model predictive control (DT-MPC) framework for ego-motion planning, enabling runtime auto-tuning of controller parameters. These two modules allow DPNet to learn fast environmental changes from minimal data while remaining lightweight, achieving high frequency and high accuracy in both tracking and planning. Experiments on high-fidelity simulator and real-world datasets demonstrate the superiority of DPNet over extensive benchmark schemes. Code available at https://github.com/UUwei-zuo/DPNet

cs.RO↗

arXiv2025

NTK-Guided Implicit Neural Teaching

Implicit Neural Representations (INRs) parameterize continuous signals via multilayer perceptrons (MLPs), enabling compact, resolution-independent modeling for tasks like image, audio, and 3D reconstruction. However, fitting high-resolution signals demands optimizing over millions of coordinates, incurring prohibitive computational costs. To address it, we propose NTK-Guided Implicit Neural Teaching (NINT), which accelerates training by dynamically selecting coordinates that maximize global functional updates. Leveraging the Neural Tangent Kernel (NTK), NINT scores examples by the norm of their NTK-augmented loss gradients, capturing both fitting errors and heterogeneous leverage (self-influence and cross-coordinate coupling). This dual consideration enables faster convergence compared to existing methods. Through extensive experiments, we demonstrate that NINT significantly reduces training time by nearly half while maintaining or improving representation quality, establishing state-of-the-art acceleration among recent sampling-based strategies.

cs.LG↗

arXiv2025

Temperature dependence of the nucleon-nucleon inelastic cross section in an isospin-asymmetric nuclear medium

The nucleon-nucleon ($NN$) inelastic cross section plays an important role in constraining the nuclear equation of state at high baryon density and in describing the formation and evolution of compact astrophysical objects. In this study, the temperature $T$ dependence of the $\Delta^{++}$ and $\Delta^{-}$ production cross sections in the isospin-symmetric and -asymmetric nuclear medium is investigated within the self-consistent and relativistic Boltzmann-Uehling-Uhlenbeck (RBUU) framework. Two relativistic mean-field parameterizations are employed: the density-dependent parameterization (called DD-ME$\delta$) and the nonlinear-dependent parameterization (called OMEG). Both parameterizations yield similar $T$-dependent baryon effective masses and mass splittings, although the OMEG set exhibits a stronger density dependence, particularly at higher densities ($> 1.5\rho_{0}$). Consequently, at lower densities, the energy, density, temperature, and isospin dependence of both $\Delta^{++}$ and $\Delta^{-}$ production cross sections are comparable for both sets, whereas at higher densities, the OMEG set predicts a stronger temperature and density sensitivity. Moreover, the $T$ dependence of the $NN$ inelastic cross section is enhanced with increasing density, but is suppressed in isospin-asymmetric nuclear matter compared to that in isospin-symmetric nuclear matter. The isospin dependence of the cross section remains nearly $T$-independent at small asymmetries, yet becomes more intricate in highly asymmetric systems. These findings provide valuable testing inputs for improving the thermal treatment of $\Delta$ related dynamical processes in transport models and offer insights into the behavior of $\Delta$ in astrophysical environments, such as core-collapse supernovae and binary neutron star mergers.

nucl-th↗

arXiv2025

UniVerse-1: Unified Audio-Video Generation via Stitching of Experts

We introduce UniVerse-1, a unified, Veo-3-like model capable of simultaneously generating coordinated audio and video. To enhance training efficiency, we bypass training from scratch and instead employ a stitching of experts (SoE) technique. This approach deeply fuses the corresponding blocks of pre-trained video and music generation experts models, thereby fully leveraging their foundational capabilities. To ensure accurate annotations and temporal alignment for both ambient sounds and speech with video content, we developed an online annotation pipeline that processes the required training data and generates labels during training process. This strategy circumvents the performance degradation often caused by misalignment text-based annotations. Through the synergy of these techniques, our model, after being finetuned on approximately 7,600 hours of audio-video data, produces results with well-coordinated audio-visuals for ambient sounds generation and strong alignment for speech generation. To systematically evaluate our proposed method, we introduce Verse-Bench, a new benchmark dataset. In an effort to advance research in audio-video generation and to close the performance gap with state-of-the-art models such as Veo3, we make our model and code publicly available. We hope this contribution will benefit the broader research community. Project page: https://dorniwang.github.io/UniVerse-1/.

cs.CV↗

arXiv2025

In-medium effects of nucleon-nucleon cross sections in heavy-ion collisions

Based on the isospin-dependent Boltzmann-Uehling-Uhlenbeck transport model, we systematically investigate the in-medium effects of nucleon-nucleon ($NN$) cross sections on nucleonic and pionic observables in heavy-ion collisions, employing microscopic cross sections derived from the Brueckner-Hartree-Fock approach. Key observables include nuclear stopping, the neutron-to-proton ($n/p$) ratio, neutron-proton transverse flow differences, differential collective flow, pion multiplicities, and the resulting $(\pi^-/\pi^+)_{\rm like}$ ratio. The analysis disentangles the respective contributions from the scattering amplitude, the density of states, and the total momentum ($K$) of the colliding pairs. We find that larger in-medium $NN$ cross sections generally enhance free nucleon emission and nuclear stopping, with the nucleon effective mass playing a dominant suppressive role. However, it is insufficient to account only for the medium corrections from effective mass: both the medium effect from the scattering amplitude and the $K$-dependence exert noticeable influences on the observables. In particular, nuclear stopping is found to be highly sensitive to these in-medium modifications of cross sections. While the $n/p$ ratio and transverse flow difference remain largely insensitive, the differential collective flow and pion yields are strongly affected. These results indicate that the interplay between scattering amplitude, density-of-states and $K$-dependence is essential to accurately describe medium effects in heavy-ion collisions.

nucl-th↗

arXiv2025

DreamDance: Animating Character Art via Inpainting Stable Gaussian Worlds

This paper presents DreamDance, a novel character art animation framework capable of producing stable, consistent character and scene motion conditioned on precise camera trajectories. To achieve this, we re-formulate the animation task as two inpainting-based steps: Camera-aware Scene Inpainting and Pose-aware Video Inpainting. The first step leverages a pre-trained image inpainting model to generate multi-view scene images from the reference art and optimizes a stable large-scale Gaussian field, which enables coarse background video rendering with camera trajectories. However, the rendered video is rough and only conveys scene motion. To resolve this, the second step trains a pose-aware video inpainting model that injects the dynamic character into the scene video while enhancing background quality. Specifically, this model is a DiT-based video generation model with a gating strategy that adaptively integrates the character's appearance and pose information into the base background video. Through extensive experiments, we demonstrate the effectiveness and generalizability of DreamDance, producing high-quality and consistent character animations with remarkable camera dynamics.

cs.CV↗

arXiv2025

Complex-scaled no-core shell model calculations of bound and unbound nuclear states in light nuclei

The complex scaling method is commonly used to describe decaying states, but its applications are limited because the Hamiltonian operator must contain only relative coordinates. This has hindered the use of complex scaling in models defined with laboratory single-particle coordinates, and in particular one of the most important model in low-energy nuclear physics, the no-core shell model. We will then present a straightforward procedure for introducing complex scaling in the no-core shell model in order to calculate nuclear resonance states. For that matter, the complex-scaled two-body matrix elements must firstly be determined, and the resulting many-body Hamiltonian complex symmetric matrix must be diagonalized afterwards. Applications pertain to the bound ground states of the lightest nuclei $^2{\rm H}$, $^3{\rm H}$, $^3{\rm He}$, and $^4{\rm He}$, as well as the resonance ground states of $^5$He and $^5$Li, whereby the realistic interaction Daejeon16 is utilized.

nucl-th↗

arXiv2024

Nucleon-$\Delta$ elastic cross section in isospin-asymmetric nuclear medium with inclusion of scalar-isovector $\delta$ meson field

The production, dynamic evolution, and decay of $\Delta$ particles play a crucial role in understanding the properties of high baryon density nuclear matter in intermediate-energy heavy-ion collisions. In this work, the energy-, density-, and isospin-dependent nucleon-$\Delta$ elastic cross section ($\sigma^{*}_{N \Delta}$) is studied within the relativistic Boltzmann-Uehling-Uhlenbeck framework, in which the $\delta$ meson field is further considered. The results show that the $\delta$ and $\rho$ meson related exchange terms have a nonnegligible contribution to the $\sigma^{*}_{N \Delta}$ compared to only considering the $\rho$ meson exchange terms, although there is a significant cancellation on the cross section among these meson exchange terms. In addition, due to the different effects of the medium correction on the effective mass of neutrons, protons, and differently charged $\Delta$s, the individual $\sigma^{*}_{N \Delta}$ exhibits an ordered isospin-asymmetry ($\alpha$) dependence, and $\sigma^{*}_{n\Delta}$ and $\sigma^{*}_{p\Delta}$ have opposite $\alpha$ dependencies. And the $\alpha$ dependence of the ratio $R(\alpha)=\sigma^{*}(\alpha)/\sigma^{*}(\alpha=0)$ for $n\Delta$ reaction channels follow $n\Delta^{++}>n\Delta^{+}>n\Delta^{0}>n\Delta^{-}$, while for $p\Delta$ it is $p\Delta^{-}>p\Delta^{0}>p\Delta^{+}>p\Delta^{++}$. Moreover, the results also indicate that the isospin effect on the $\sigma^{*}_{N \Delta}$, which is dominantly caused by the isovector $\rho$ and $\delta$ meson fields, is still pronounced at densities up to 3 times normal nuclear density. Finally, a parametrization of the energy-, density-, and isospin-dependent $N\Delta$ elastic cross section is proposed based on the microscopic calculated results, and the in-medium $\sigma^{*}_{N \Delta}$ in the energy range of $\sqrt{s}$=2.3$\sim$3.0 GeV can be well described.

nucl-th↗

arXiv2024

Exploring the nuclear momentum anisotropy based on intermediate-energy heavy-ion collisions

We simulate ultra-central collisions of prolate uranium-uranium nuclei at intermediate energies using the isospin-dependent Boltzmann-Uehling-Uhlenbeck model to investigate the impact of momentum anisotropy on spatial geometric effects. By defining the quadrupole deformation parameter in momentum space $\beta_\text{p}$, we establish an ellipsoidal Fermi surface, aligning its rotational symmetry axis with the one in coordinate space. It is found that oblate momentum density enhances elliptic flow $v_2$, while prolate momentum density has the opposite effect, particularly pronounced in the outer, high transverse momentum $p_\text{t}$ region. Momentum anisotropy also causes differences in the initial momentum mean projection along the beam direction, with larger projections producing more pion mesons. Additionally, significant effects on mean square elliptic flow are observed in non-polarized collisions. We further examine the relationship between the $v_2$-$p_\text{t}$ slope and $\beta_\text{p}$, eliminating systematic errors through the two-system ratio. These findings provide important references for experimentalists in heavy-ion collisions and valuable feedback to theorists regarding nuclear structure.

nucl-th↗

arXiv2024

MikuDance: Animating Character Art with Mixed Motion Dynamics

We propose MikuDance, a diffusion-based pipeline incorporating mixed motion dynamics to animate stylized character art. MikuDance consists of two key techniques: Mixed Motion Modeling and Mixed-Control Diffusion, to address the challenges of high-dynamic motion and reference-guidance misalignment in character art animation. Specifically, a Scene Motion Tracking strategy is presented to explicitly model the dynamic camera in pixel-wise space, enabling unified character-scene motion modeling. Building on this, the Mixed-Control Diffusion implicitly aligns the scale and body shape of diverse characters with motion guidance, allowing flexible control of local character motion. Subsequently, a Motion-Adaptive Normalization module is incorporated to effectively inject global scene motion, paving the way for comprehensive character art animation. Through extensive experiments, we demonstrate the effectiveness and generalizability of MikuDance across various character art and motion guidance, consistently producing high-quality animations with remarkable motion dynamics.

cs.CV↗

arXiv2024

Direct ab initio calculation of the $^{4}$He nuclear electric dipole polarizability

The calculation of nuclear electromagnetic sum rules by directly diagonalizing the nuclear Hamiltonian in a large basis is numerically challenging and has not been performed for $A>2$ nuclei. With the significant progress of high performance computing, we show that calculating sum rules using numerous discretized continuum states obtained by directly diagonalizing the ab initio no-core shell model Hamiltonian is achievable numerically. Specifically, we calculate the $^{4}$He electric dipole ($E1$) polarizability, that is an inverse energy weighted sum rule, employing the Daejeon16 $NN$ interaction. We demonstrate that the calculations are numerically tractable as the dimension of the basis increases and are convergent. Our results for the $^{4}$He electric dipole polarizability are consistent with the most recent experimental data and are compared with those of other theoretical studies employing different techniques and various interactions.

nucl-th↗