arXiv subjects

Min Wei

Publications and source records attributed to Min Wei.

At least 19 recordsLinked to original sources

arXiv2026

TGRHuman: Text-Guided Realistic 3D Human Generation via Diffusion Renderer

Realistic 3D human generation plays a crucial role in many graphics applications. However, current methods still struggle to generate high-quality human geometry and texture while maintaining 3D consistency and inference efficiency. In this work, we address these limitations by introducing TGRHuman, a novel approach for generating realistic 3D humans from text. Our method decouples geometry and texture generation to alleviate the issues commonly encountered in NeRF-based methods. Instead of relying on slow, implicit score-distillation-based optimization, we directly use explicit multi-view observation generation and optimization for efficient 3D synthesis. For geometry generation, we propose a high-resolution generative module for multi-view normals together with a geometry-carving strategy that preserves view consistency and supports loose clothing. For texture generation, we produce spatially consistent RGB observations from densely sampled surrounding views using a carefully designed texture-prior acquisition strategy and a diffusion renderer, enabling detailed human texture synthesis. Experiments show that our method can generate high-quality and consistent 3D human geometry and texture efficiently. TGRHuman outperforms existing text-to-3D human methods in both geometry and texture quality.

cs.CV↗

arXiv2026

ContextMaster: Interactive Multi-Shot Video Creation via Fixed-Budget Sparse Context Routing

Recent video models increasingly support generation, reference conditioning, and editing within a single model, yet typically expose them as separate operations over fixed inputs. Practical creation unfolds across multiple shots, requiring one model to generate from text, follow a reference, or edit source footage while maintaining shared history. We formalize this setting as interactive multi-shot video creation (IMVC) and introduce ContextMaster, a unified model with a role-aware context representation for these operations. An interactive model must retain access to an expanding history without allowing the context read cost at each denoising step to grow. ContextMaster combines reusable clean context states with fixed budget sparse context routing and uses ConstraintSink to keep task constraints visible. To address the dual challenges of sparse context access and inference with few denoising steps, we propose a two-stage privileged context distillation framework, which transfers full context behavior from a dense teacher through consistency distillation and then refines deployment rollouts with distribution matching. Experiments on the three primitive tasks demonstrate improved task fulfillment and consistency across shots over specialized baselines. User studies further validate flexibly composed workflows, while the model reaches 16 FPS on a single GPU.

cs.CV↗

arXiv2026

Towards 3D-Aware Video Diffusion Models: Render-Free Human Motion Control with Mesh Tokenization

Diffusion models have shown remarkable success in video generation. However, whether such models are truly aware of the 3D structure underlying visual observations, rather than simply reproducing plausible 2D projections, remains an open question. In this work, we investigate this question through human motion control, a task that requires precise modelling of 3D human geometry, motion, camera viewpoint, and scene context. Unlike prior methods that rely on rendered 2D motion guidance videos, we propose a render-free framework that conditions video generation directly on compressed 3D human mesh tokens. This representation preserves full 3D geometric information while enabling a unified token-based generation pipeline that processes video tokens jointly with motion tokens in a DiT-based architecture. This design requires the model to reason jointly about appearance, 3D structure, and camera viewpoint during video generation. Experimental results demonstrate strong performance on human motion control benchmarks, while reducing artifacts induced by view-dependent 2D guidance and trajectory-pose mismatches during editing. These findings suggest that video diffusion models, when equipped with mesh tokenization, can better capture complex 3D human structures and their interactions with the surrounding environment.

cs.CV↗

arXiv2026

Geometry-Aware Implicit Memory for Video World Models

Video world models aim to simulate controllable visual environments, but long-horizon rollouts depend on what the model remembers after observations leave its native context window. Explicit memories retain frames or online 3D reconstructions, which can suffer from heuristic retrieval errors, redundant appearance storage, or reconstruction artifacts. Implicit memories compress history into a compact state, but existing designs are not explicitly constrained to encode cross-view scene geometry. We propose GIM-World, a geometry-aware implicit memory framework for video world models. A lightweight transformer encoder compresses variable-length history into fixed-size memory tokens, a camera-queryable geometry head distills 3D scene structure from a frozen foundation model into the memory during training, and an information-guided pruning rule keeps encoding cost bounded as history grows. The geometry teacher is discarded at inference, leaving a lightweight memory module. Experiments on MIND show that GIM-World better preserves long-horizon geometric and visual consistency than both explicit- and implicit-memory baselines.

cs.CV↗

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

Deterministic non-local parity control and supercurrent-based detection in an Andreev molecule

The ability to manipulate and detect the parity of quantum states in superconductor-semiconductor hybrid systems is pivotal to realizing the promise of topological quantum computation. However, as these architectures scale toward artificial Kitaev chains with phase-control loops, local accessibility becomes restricted, constraining conventional local parity control and detection. While Andreev molecules offer a platform for non-local intervention, deterministic protocols for parity manipulation have yet to be experimentally established. Here, we demonstrate deterministic non-local control over the parity configuration of a quantum dot (QD) by electrically modulating the coherent hybridization with a spatially adjacent QD within an Andreev molecule. By systematically investigating three distinct joint parity configuration regimes in the elastic co-tunneling limit, we experimentally uncover the operational conditions for this non-local control. In conjunction with theoretical simulations establishing a global phase diagram, we identify a set of universal selection rules governing parity transitions, dictated by the symmetry-imposed interplay between the joint parity configuration and the dominant inter-dot coupling mechanism (elastic co-tunneling vs. crossed Andreev reflection). Furthermore, we establish the supercurrent, directly signaled by zero-bias conductance peaks, as an intrinsic, sensor-free probe of the parity configuration, obviating the need for auxiliary charge sensors. Our results provide a validated physical framework for parity engineering, offering a key building block for scalable, multi-QD superconducting architectures.

cond-mat.mes-hall↗

arXiv2025

Kling-Omni Technical Report

We present Kling-Omni, a generalist generative framework designed to synthesize high-fidelity videos directly from multimodal visual language inputs. Adopting an end-to-end perspective, Kling-Omni bridges the functional separation among diverse video generation, editing, and intelligent reasoning tasks, integrating them into a holistic system. Unlike disjointed pipeline approaches, Kling-Omni supports a diverse range of user inputs, including text instructions, reference images, and video contexts, processing them into a unified multimodal representation to deliver cinematic-quality and highly-intelligent video content creation. To support these capabilities, we constructed a comprehensive data system that serves as the foundation for multimodal video creation. The framework is further empowered by efficient large-scale pre-training strategies and infrastructure optimizations for inference. Comprehensive evaluations reveal that Kling-Omni demonstrates exceptional capabilities in in-context generation, reasoning-based editing, and multimodal instruction following. Moving beyond a content creation tool, we believe Kling-Omni is a pivotal advancement toward multimodal world simulators capable of perceiving, reasoning, generating and interacting with the dynamic and complex worlds.

cs.CV↗

arXiv2025

GOGS: High-Fidelity Geometry and Relighting for Glossy Objects via Gaussian Surfels

Inverse rendering of glossy objects from RGB imagery remains fundamentally limited by inherent ambiguity. Although NeRF-based methods achieve high-fidelity reconstruction via dense-ray sampling, their computational cost is prohibitive. Recent 3D Gaussian Splatting achieves high reconstruction efficiency but exhibits limitations under specular reflections. Multi-view inconsistencies introduce high-frequency surface noise and structural artifacts, while simplified rendering equations obscure material properties, leading to implausible relighting results. To address these issues, we propose GOGS, a novel two-stage framework based on 2D Gaussian surfels. First, we establish robust surface reconstruction through physics-based rendering with split-sum approximation, enhanced by geometric priors from foundation models. Second, we perform material decomposition by leveraging Monte Carlo importance sampling of the full rendering equation, modeling indirect illumination via differentiable 2D Gaussian ray tracing and refining high-frequency specular details through spherical mipmap-based directional encoding that captures anisotropic highlights. Extensive experiments demonstrate state-of-the-art performance in geometry reconstruction, material separation, and photorealistic relighting under novel illuminations, outperforming existing inverse rendering approaches.

cs.CV↗

arXiv2025

Josephson diode effect in nanowire-based Andreev molecules

Superconducting systems exhibit non-reciprocal current transport under certain conditions of symmetry breaking, a phenomenon known as the superconducting diode effect. This effect allows for perfect rectification of supercurrent, and has received considerable research interest. We report the observation of the Josephson diode effect (JDE) in nanowire-based Andreev molecules, where the time-reversal and spatial-inversion symmetries of a Josephson junction (JJ) can be nonlocally broken by coherently coupling to another JJ. The JDE can be controlled using both non-local phase and gate voltages. Notably, the non-local phase can induce a sign reversal of the diode efficiency, a manifestation of regulating the probabilities of double elastic cotunneling and double-crossed Andreev reflection. Additionally, the diode efficiency can be further modulated by local and non-local gate voltages, exhibiting a central-peak feature in the gate-voltage space. Our theoretical calculations of the energy spectrum and the Josephson currents align well with the experimental results. These results demonstrate the non-local regulation of the JDE in Andreev molecules, offering significant implications for the control of multi-JJ devices and the development of advanced superconducting devices.

cond-mat.mes-hall↗

arXiv2025

3DV-TON: Textured 3D-Guided Consistent Video Try-on via Diffusion Models

Video try-on replaces clothing in videos with target garments. Existing methods struggle to generate high-quality and temporally consistent results when handling complex clothing patterns and diverse body poses. We present 3DV-TON, a novel diffusion-based framework for generating high-fidelity and temporally consistent video try-on results. Our approach employs generated animatable textured 3D meshes as explicit frame-level guidance, alleviating the issue of models over-focusing on appearance fidelity at the expanse of motion coherence. This is achieved by enabling direct reference to consistent garment texture movements throughout video sequences. The proposed method features an adaptive pipeline for generating dynamic 3D guidance: (1) selecting a keyframe for initial 2D image try-on, followed by (2) reconstructing and animating a textured 3D mesh synchronized with original video poses. We further introduce a robust rectangular masking strategy that successfully mitigates artifact propagation caused by leaking clothing information during dynamic human and garment movements. To advance video try-on research, we introduce HR-VVT, a high-resolution benchmark dataset containing 130 videos with diverse clothing types and scenarios. Quantitative and qualitative results demonstrate our superior performance over existing methods. The project page is at this link https://2y7c3.github.io/3DV-TON/

cs.CV↗

arXiv2025

RealisDance-DiT: Simple yet Strong Baseline towards Controllable Character Animation in the Wild

Controllable character animation remains a challenging problem, particularly in handling rare poses, stylized characters, character-object interactions, complex illumination, and dynamic scenes. To tackle these issues, prior work has largely focused on injecting pose and appearance guidance via elaborate bypass networks, but often struggles to generalize to open-world scenarios. In this paper, we propose a new perspective that, as long as the foundation model is powerful enough, straightforward model modifications with flexible fine-tuning strategies can largely address the above challenges, taking a step towards controllable character animation in the wild. Specifically, we introduce RealisDance-DiT, built upon the Wan-2.1 video foundation model. Our sufficient analysis reveals that the widely adopted Reference Net design is suboptimal for large-scale DiT models. Instead, we demonstrate that minimal modifications to the foundation model architecture yield a surprisingly strong baseline. We further propose the low-noise warmup and "large batches and small iterations" strategies to accelerate model convergence during fine-tuning while maximally preserving the priors of the foundation model. In addition, we introduce a new test dataset that captures diverse real-world challenges, complementing existing benchmarks such as TikTok dataset and UBC fashion video dataset, to comprehensively evaluate the proposed method. Extensive experiments show that RealisDance-DiT outperforms existing methods by a large margin.

cs.CV↗

arXiv2024

Incentive-Driven Task Offloading and Collaborative Computing in Device-Assisted MEC Networks

Edge computing (EC), positioned near end devices, holds significant potential for delivering low-latency, energy-efficient, and secure services. This makes it a crucial component of the Internet of Things (IoT). However, the increasing number of IoT devices and emerging services place tremendous pressure on edge servers (ESs). To better handle dynamically arriving heterogeneous tasks, ESs and IoT devices with idle resources can collaborate in processing tasks. Considering the selfishness and heterogeneity of IoT devices and ESs, we propose an incentive-driven multi-level task allocation framework. Specifically, we categorize IoT devices into task IoT devices (TDs), which generate tasks, and auxiliary IoT devices (ADs), which have idle resources. We use a bargaining game to determine the initial offloading decision and the payment fee for each TD, as well as a double auction to incentivize ADs to participate in task processing. Additionally, we develop a priority-based inter-cell task scheduling algorithm to address the uneven distribution of user tasks across different cells. Finally, we theoretically analyze the performance of the proposed framework. Simulation results demonstrate that our proposed framework outperforms benchmark methods.

cs.GT↗

arXiv2024

Global and Local Attention-based Inception U-Net for Static IR Drop Prediction

Static IR drop analysis is a fundamental and critical task in chip design since the IR drop will significantly affect the design's functionality, performance, and reliability. However, the process of IR drop analysis can be time-consuming, potentially taking several hours. Therefore, a fast and accurate IR drop prediction is paramount for reducing the overall time invested in chip design. In this paper, we propose a global and local attention-based Inception U-Net for static IR drop prediction. Our U-Net incorporates the Transformer, CBAM, and Inception architectures to enhance its feature capture capability at different scales and improve the accuracy of predicted IR drop. Moreover, we propose 4 new features, which enhance our model with richer information. Finally, to balance the sampling probabilities across different regions in one design, we propose a series of novel data spatial adjustment techniques, with each batch randomly selecting one of them during training. Experimental results demonstrate that our proposed algorithm can achieve the best results among the winning teams of the ICCAD 2023 contest and the state-of-the-art algorithms.

cs.AR↗

arXiv2024

Computation Rate Maximization for Wireless Powered Edge Computing With Multi-User Cooperation

The combination of mobile edge computing (MEC) and radio frequency-based wireless power transfer (WPT) presents a promising technique for providing sustainable energy supply and computing services at the network edge. This study considers a wireless-powered mobile edge computing system that includes a hybrid access point (HAP) equipped with a computing unit and multiple Internet of Things (IoT) devices. In particular, we propose a novel muti-user cooperation scheme to improve computation performance, where collaborative clusters are dynamically formed. Each collaborative cluster comprises a source device (SD) and an auxiliary device (AD), where the SD can partition the computation task into various segments for local processing, offloading to the HAP, and remote execution by the AD with the assistance of the HAP. Specifically, we aims to maximize the weighted sum computation rate (WSCR) of all the IoT devices in the network. This involves jointly optimizing collaboration, time and data allocation among multiple IoT devices and the HAP, while considering the energy causality property and the minimum data processing requirement of each device. Initially, an optimization algorithm based on the interior-point method is designed for time and data allocation. Subsequently, a priority-based iterative algorithm is developed to search for a near-optimal solution to the multi-user collaboration scheme. Finally, a deep learning-based approach is devised to further accelerate the algorithm's operation, building upon the initial two algorithms. Simulation results show that the performance of the proposed algorithms is comparable to that of the exhaustive search method, and the deep learning-based algorithm significantly reduces the execution time of the algorithm.

cs.IT↗

arXiv2023

Adversarial Score Distillation: When score distillation meets GAN

Existing score distillation methods are sensitive to classifier-free guidance (CFG) scale: manifested as over-smoothness or instability at small CFG scales, while over-saturation at large ones. To explain and analyze these issues, we revisit the derivation of Score Distillation Sampling (SDS) and decipher existing score distillation with the Wasserstein Generative Adversarial Network (WGAN) paradigm. With the WGAN paradigm, we find that existing score distillation either employs a fixed sub-optimal discriminator or conducts incomplete discriminator optimization, resulting in the scale-sensitive issue. We propose the Adversarial Score Distillation (ASD), which maintains an optimizable discriminator and updates it using the complete optimization objective. Experiments show that the proposed ASD performs favorably in 2D distillation and text-to-3D tasks against existing methods. Furthermore, to explore the generalization ability of our WGAN paradigm, we extend ASD to the image editing task, which achieves competitive results. The project page and code are at https://github.com/2y7c3/ASD.

cs.CV↗

arXiv2023

Communication Efficiency Optimization of Federated Learning for Computing and Network Convergence of 6G Networks

Federated learning effectively addresses issues such as data privacy by collaborating across participating devices to train global models. However, factors such as network topology and device computing power can affect its training or communication process in complex network environments. A new network architecture and paradigm with computing-measurable, perceptible, distributable, dispatchable, and manageable capabilities, computing and network convergence (CNC) of 6G networks can effectively support federated learning training and improve its communication efficiency. By guiding the participating devices' training in federated learning based on business requirements, resource load, network conditions, and arithmetic power of devices, CNC can reach this goal. In this paper, to improve the communication efficiency of federated learning in complex networks, we study the communication efficiency optimization of federated learning for computing and network convergence of 6G networks, methods that gives decisions on its training process for different network conditions and arithmetic power of participating devices in federated learning. The experiments address two architectures that exist for devices in federated learning and arrange devices to participate in training based on arithmetic power while achieving optimization of communication efficiency in the process of transferring model parameters. The results show that the method we proposed can (1) cope well with complex network situations (2) effectively balance the delay distribution of participating devices for local training (3) improve the communication efficiency during the transfer of model parameters (4) improve the resource utilization in the network.

cs.LG↗

arXiv2023

Super-Resolution Neural Operator

We propose Super-resolution Neural Operator (SRNO), a deep operator learning framework that can resolve high-resolution (HR) images at arbitrary scales from the low-resolution (LR) counterparts. Treating the LR-HR image pairs as continuous functions approximated with different grid sizes, SRNO learns the mapping between the corresponding function spaces. From the perspective of approximation theory, SRNO first embeds the LR input into a higher-dimensional latent representation space, trying to capture sufficient basis functions, and then iteratively approximates the implicit image function with a kernel integral mechanism, followed by a final dimensionality reduction step to generate the RGB representation at the target coordinates. The key characteristics distinguishing SRNO from prior continuous SR works are: 1) the kernel integral in each layer is efficiently implemented via the Galerkin-type attention, which possesses non-local properties in the spatial domain and therefore benefits the grid-free continuum; and 2) the multilayer attention architecture allows for the dynamic latent basis update, which is crucial for SR problems to "hallucinate" high-frequency information from the LR image. Experiments show that SRNO outperforms existing continuous SR methods in terms of both accuracy and running time. Our code is at https://github.com/2y7c3/Super-Resolution-Neural-Operator

cs.CV↗

arXiv2018

Mixed-timescale Per-group Hybrid Precoding for Multiuser Massive MIMO Systems

Considering the expensive radio frequency (RF) chain, huge training overhead and feedback burden issues in massive MIMO, in this letter, we propose a mixed-timescale per-group hybrid precoding (MPHP) scheme under an adaptive partially-connected RF precoding structure (PRPS), where the RF precoder is implemented using an adaptive connection network (ACN) and M analog phase shifters (APSs), where M is the number of antennas at the base station (BS). Exploiting the mixed-time stage channel state information (CSI) structure, the joint-design of ACN and APSs is formulated as a statistical signal-to-leakage-and-noise ratio (SSLNR) maximization problem, and a heuristic group RF precoding (GRFP) algorithm is proposed to provide a near-optimal solution. Simulation results show that the proposed design advances at better energy efficiency (EE) and lower hardware cost, CSI signaling overhead and computational complexity than the conventional hybrid precoding (HP) schemes.

eess.SP↗