arXiv subjects

Dian Sheng

Publications and source records attributed to Dian Sheng.

7 recordsLinked to original sources

arXiv2026

SoulX-FlashHead: Oracle-guided Generation of Infinite Real-time Streaming Talking Heads

Achieving a balance between high-fidelity visual quality and low-latency streaming remains a formidable challenge in audio-driven portrait generation. Existing large-scale models often suffer from prohibitive computational costs, while lightweight alternatives typically compromise on holistic facial representations and temporal stability. In this paper, we propose SoulX-FlashHead, a unified 1.3B-parameter framework designed for real-time, infinite-length, and high-fidelity streaming video generation. To address the instability of audio features in streaming scenarios, we introduce Streaming-Aware Spatiotemporal Pre-training equipped with a Temporal Audio Context Cache mechanism, which ensures robust feature extraction from short audio fragments. Furthermore, to mitigate the error accumulation and identity drift inherent in long-sequence autoregressive generation, we propose Oracle-Guided Bidirectional Distillation, leveraging ground-truth motion priors to provide precise physical guidance. We also present VividHead, a large-scale, high-quality dataset containing 782 hours of strictly aligned footage to support robust training. Extensive experiments demonstrate that SoulX-FlashHead achieves state-of-the-art performance on HDTF and VFHQ benchmarks. Notably, our Lite variant achieves an inference speed of 96 FPS on a single NVIDIA RTX 4090, facilitating ultra-fast interaction without sacrificing visual coherence.

cs.CV↗

arXiv2026

BrainSegNet: A Novel Framework for Whole-Brain MRI Parcellation Enhanced by Large Models

Whole-brain parcellation from MRI is a critical yet challenging task due to the complexity of subdividing the brain into numerous small, irregular shaped regions. Traditionally, template-registration methods were used, but recent advances have shifted to deep learning for faster workflows. While large models like the Segment Anything Model (SAM) offer transferable feature representations, they are not tailored for the high precision required in brain parcellation. To address this, we propose BrainSegNet, a novel framework that adapts SAM for accurate whole-brain parcellation into 95 regions. We enhance SAM by integrating U-Net skip connections and specialized modules into its encoder and decoder, enabling fine-grained anatomical precision. Key components include a hybrid encoder combining U-Net skip connections with SAM's transformer blocks, a multi-scale attention decoder with pyramid pooling for varying-sized structures, and a boundary refinement module to sharpen edges. Experimental results on the Human Connectome Project (HCP) dataset demonstrate that BrainSegNet outperforms several state-of-the-art methods, achieving higher accuracy and robustness in complex, multi-label parcellation.

cs.CV↗

arXiv2025

Dynamic Switching Models for Truck-only Delivery and Drone-assisted Truck Delivery under Demand Uncertainty

Integrating drones into truck delivery systems can improve customer accessibility, reduce operational costs, and increase delivery efficiency. However, drone deployment incurs costs, including procurement, maintenance, and energy consumption, and its benefits depend on service demand. In low-demand areas, drone-assisted trucks may underutilize resources due to high upfront costs. Accurately predicting demand is challenging due to uncertainties from unforeseen events or infrastructure disruptions. To address this, a market entry and exit real option approach is used to optimize switching between truck-only and drone-assisted delivery under stochastic demand. Results show that deploying multiple drones per truck offers significant cost advantages in high-demand regions. Using the proposed dynamic switching model, deterministic and stochastic approaches reduce costs by 17.4% and 31.3%, respectively, compared to immediate cost-saving switching. Sensitivity analysis reveals asymmetric effects of stochastic parameters on entry and exit timings. A stochastic multiple-options model is further developed to dynamically switch between truck-only and drone-assisted delivery with varying drone numbers. Applying these models to Miami-Dade County, we evaluate dynamic switching costs for three major logistics operators. This study highlights the potential benefits of dynamic delivery switching and provides insights for optimizing logistics operations.

eess.SY↗

arXiv2025

Optimized dynamic scheduling of an exclusive bus lane or high occupancy vehicle lane in a bimodal traffic corridor

Efficient management of traffic corridors is critical for sustaining urban mobility. Exclusive bus lane (EBL) and high occupancy vehicle lane (HOVL) are two prominent strategies for enhancing public transit services and alleviating congestion. EBLs prioritize bus transit by providing dedicated lanes for faster travel times, while HOVLs encourage carpooling by reserving lanes for high-occupancy vehicles. However, static implementations of these policies may underutilize road resources and disrupt general-purpose lanes. Dynamic implementation, based on real-time demand, can potentially maximize road efficiency and minimize negative impacts. This study first compares the mixed traffic policy (MTP), exclusive bus lane policy (EBLP), and high occupancy vehicle lane policy (HOVLP) by formulating the total system costs in the context of a bimodal traffic corridor involving private cars and public buses. Under each lane policy, the bus frequency is optimized together with the modal split equilibrium derived separately. Based on dynamic demand simulated using an Ornstein-Uhlenbeck (O-U) process, switching thresholds are then derived to identify optimal periods for implementing each policy. Results reveal significant reductions in total system costs with the proposed dynamic policy schedules. Compared to static implementations, the dynamic policy schedules achieve cost reductions of 11.9%, 6.70%, and 43.64% relative to MTP-only, EBLP-only, and HOVLP-only scenarios, respectively. Additionally, in two real case studies of existing EBL and HOVL operations in Seattle, the proposed dynamic policy reduces total costs by 32.5% and 28.6%, respectively. The findings provide valuable insights for policymakers and transit planners, offering a robust framework for dynamically scheduling and integrating EBL and HOVL policies to optimize urban corridor efficiency and reduce overall system costs.

math.OC↗

arXiv2019

Convolutional neural networks with fractional order gradient method

This paper proposes a fractional order gradient method for the backward propagation of convolutional neural networks. To overcome the problem that fractional order gradient method cannot converge to real extreme point, a simplified fractional order gradient method is designed based on Caputo's definition. The parameters within layers are updated by the designed gradient method, but the propagations between layers still use integer order gradients, and thus the complicated derivatives of composite functions are avoided and the chain rule will be kept. By connecting every layers in series and adding loss functions, the proposed convolutional neural networks can be trained smoothly according to various tasks. Some practical experiments are carried out in order to demonstrate fast convergence, high accuracy and ability to escape local optimal point at last.

math.OC↗

arXiv2019

Adaptive backstepping control for FOS with nonsmooth nonlinearities

This paper proposes an original solution to input saturation and dead zone of fractional order system. To overcome these nonsmooth nonlinearities, the control input is decomposed into two independent parts by introducing an intermediate variable, and thus the problem of dead zone and saturation transforms into the problem of disturbance and saturation afterwards. With the procedure of fractional order adaptive backstepping controller design, the bound of disturbance is estimated, and saturation is compensated by the virtual signal of an auxiliary system as well. In spite of the existence of nonsmooth nonlinearities, the output is guaranteed to track the reference signal asymptotically on the basis of our proposed method. Some simulation studies are carried out in order to demonstrate the effectiveness of method at last.

math.OC↗

arXiv2017

Topological transport in Dirac electronic systems: A concise review

Various novel physical properties have emerged in Dirac electronic systems, especially the topological characters protected by symmetry. Current studies on these systems have been greatly promoted by the intuitive concepts of Berry phase and Berry curvature, which provide precise definitions of the topological orders. In this topical review, transport properties of topological insulator (Bi2Se3), topological Dirac semimetal (Cd3As2) and topological insulator-graphene heterojunction are presented and discussed. Perspectives about transport properties of two-dimensional topological nontrivial systems, including topological edge transport, topological valley transport and topological Weyl semimetals, are provided.

cond-mat.mtrl-sci↗