arXiv subjects

Zheng Chang

Publications and source records attributed to Zheng Chang.

At least 19 recordsLinked to original sources

arXiv2026

DeSeG: Decoupling Semantic Intent and Geometric Constraints for Physically Plausible Human-Scene Interaction

Synthesizing physically plausible human-scene interactions (HSI) remains a critical challenge in computer vision and the development of human avatars. Although recent generative models enable diverse motion synthesis, they suffer from an inductive bias referred to as semantic-geometric entanglement. Because spatial constraints often strongly correlate with specific actions in training data, monolithic models will learn the shortcut bias, aggressively overriding the semantic intent when faced with strict geometric cues. Furthermore, this entanglement exacerbates physical hallucinations, such as body-scene penetrations. To address these limitations, we propose DeSeG, a hierarchical framework that explicitly decouples semantic intent from geometric constraints. First, we introduce a Residual Semantic Planner that encodes textual instructions and canonicalized goal voxels into a compact latent space, enabling fine-grained semantic control independent of spatial trajectories. Second, we propose a physics regularized diffusion executor that incorporates differentiable repulsive potential fields directly into the diffusion objective, enforcing collision-aware motion generation. Extensive experiments on the Lingo dataset demonstrate that DeSeG achieves state-of-the-art performance, reducing mean scene penetration by 47% and improving semantic alignment by 29% over the SOTA baselines.

cs.CV↗

arXiv2026

Ultrafast Demagnetization Governed by Spin Fluctuations in CaRuO$_{3}$/SrTiO$_{3}$ Superlattice

For ultrafast magnetization switching devices, critical slowing down in conventional ferromagnets near their Curie temperature constitutes a key challenge that must be overcome. In contrast to this typical behavior, we observe an anomalous acceleration of demagnetization in CaRuO$_{3}$/SrTiO$_{3}$ superlattices, a moderately correlated weak itinerant ferromagnet. The demagnetization rate increases with rising temperature, pump fluence, and applied magnetic field. To explain these anomalous phenomena, we develop a phenomenological model integrating the three-temperature model with self-consistent renormalization theory. Because the intrinsic gradient magnetism of the superlattice suppresses the typical divergence of specific heat, the conventional thermodynamic bottleneck is bypassed. Our model reveals that this decoupling enables the ultrafast dynamics to be predominantly governed by the spin-fluctuation-driven enhancement of the electron-spin scattering vertex. Our work demonstrates how spatial inhomogeneity can decouple macroscopic thermodynamic singularities from microscopic scattering processes, offering a new paradigm for manipulating ultrafast spin dynamics in correlated quantum materials. The pronounced sensitivity of the demagnetization rate to external parameters further suggests the potential for designing highly tunable ultrafast spintronic devices that leverage enhanced fluctuations near the magnetic instability.

cond-mat.mtrl-sci↗

arXiv2026

Ultrafast Magneto-optical Fingerprints of Altermagnetism in MnTe

Recently identified altermagnets exhibit a distinctive dual-space nature: they possess spin-split electronic bands akin to ferromagnets in momentum space while maintaining the fully compensated magnetization of antiferromagnets in real space. This inherent duality, originating from the same crystal symmetry, gives rise to various intriguing physical phenomena unique to altermagnets. Consequently, a robust and efficient experimental signature capable of revealing this dual character is critically needed. The magneto-optical Kerr and Voigt effects, given their high sensitivity to ferromagnetism and antiferromagnetism, respectively, are ideally suited to probe this duality. Here, using time-resolved pump-probe magneto-optical measurements, we report the coexistence of pronounced Kerr and Voigt effects in the altermagnet MnTe. Combining the magnetization measurement and first-principles calculations, we demonstrate that the Kerr effect originates from the intrinsic Berry curvature of altermagnetism distribution in momentum space, while the Voigt effect arises from an anisotropic permittivity induced by the in-plane N\'eel order in real space, directly revealing the dual-space nature of altermagnets. Furthermore, the transient Kerr signal exhibits faster relaxation dynamics than the transient Voigt signal, underscoring their distinct origins in Berry curvature and N\'eel order, respectively. These findings establish transient magneto-optical responses as distinctive fingerprints of altermagnetism and position altermagnets as promising platforms for manipulating magneto-optical phenomena in ultrafast spin optoelectronics.

cond-mat.mtrl-sci↗

arXiv2026

TSFLora: Token-Compressed Split Fine-Tuning for Wireless Edge Networks

Adapting large AI models (LAMs) to personalized edge data is challenging because wireless devices have limited memory, computation, and uplink capacity. Federated fine-tuning preserves data privacy but still requires each device to host the full model, while split learning reduces device memory at the cost of heavy activation transmission. This paper proposes TSFLora, a token-compressed split fine-tuning framework for communication-efficient LAM adaptation at the edge. TSFLora combines attention-guided token selection, token merging, low-bit activation quantization, and LoRA-based adaptation within a split federated training pipeline. The key idea is to compress the intermediate token sequence before transmission so that the system reduces both uplink traffic and server-side processing without changing the frozen backbone. Experiments on ViT models over CIFAR-10, CIFAR-100, and TinyImageNet show that TSFLora achieves up to \textbf{6.8$\times$} communication reduction and \textbf{41\%} memory saving while maintaining competitive accuracy.

cs.DC↗

arXiv2026

Semantic-aware Token Selection and Resource Optimization for Communication-efficient Split Federated Fine-tuning in Edge Intelligence

Deploying large Transformer-based vision models on resource-limited mobile devices at network edge is severely constrained by hardware limitations and dynamic wireless environments. While federated learning (FL) enables collaborative training without sharing raw data, strictly local fine-tuning of such massive models remains computationally prohibitive for edge devices. Split federated learning (SFL) alleviates this burden by offloading deep layers to the edge server, yet it suffers from heavy communication overhead when transmitting high-dimensional activation tokens. To address this bottleneck, we propose ST-SFLora, a semantic token-based split federated LoRA fine-tuning framework. We introduce a new metric, \emph{Semantic Transmission Efficiency} (STE), to balance semantic retention and transmission cost. Based on STE, we formulate a joint resource optimization problem that dynamically determines token selection, uplink bandwidth allocation, and transmit power under latency and energy constraints. The resulting mixed-integer nonconvex problem is efficiently solved via an alternating algorithm. Experiments on multiple benchmarks demonstrate that ST-SFLora achieves the lowest client-side resource consumption among baselines while delivering a favorable trade-off between communication efficiency and model performance.

cs.DC↗

arXiv2026

Lighting-grounded Video Generation with Renderer-based Agent Reasoning

Diffusion models have achieved remarkable progress in video generation, but their controllability remains a major limitation. Key scene factors such as layout, lighting, and camera trajectory are often entangled or only weakly modeled, restricting their applicability in domains like filmmaking and virtual production where explicit scene control is essential. We present LiVER, a diffusion-based framework for scene-controllable video generation. To achieve this, we introduce a novel framework that conditions video synthesis on explicit 3D scene properties, supported by a new large-scale dataset with dense annotations of object layout, lighting, and camera parameters. Our method disentangles these properties by rendering control signals from a unified 3D representation. We propose a lightweight conditioning module and a progressive training strategy to integrate these signals into a foundational video diffusion model, ensuring stable convergence and high fidelity. Our framework enables a wide range of applications, including image-to-video and video-to-video synthesis where the underlying 3D scene is fully editable. To further enhance usability, we develop a scene agent that automatically translates high-level user instructions into the required 3D control signals. Experiments show that LiVER achieves state-of-the-art photorealism and temporal consistency while enabling precise, disentangled control over scene factors, setting a new standard for controllable video generation.

cs.CV↗

arXiv2026

Semantic Communication-Enhanced Split Federated Learning for Vehicular Networks: Architecture, Challenges, and Case Study

Vehicular edge intelligence (VEI) is vital for future intelligent transportation systems. However, traditional centralized learning in dynamic vehicular networks faces significant communication overhead and privacy risks. Split federated learning (SFL) offers a distributed solution but is often hindered by substantial communication bottlenecks from transmitting high-dimensional intermediate features and can present label privacy concerns. Semantic communication offers a transformative approach to alleviate these communication challenges in SFL by focusing on transmitting only task-relevant information. This paper leverages the advantages of semantic communication in the design of SFL, and presents a case study the semantic communication-enhanced U-Shaped split federated learning (SC-USFL) framework that inherently enhances label privacy by localizing sensitive computations with reduced overhead. It features a dedicated semantic communication module (SCM), with pre-trained and parameter-frozen encoding/decoding units, to efficiently compress and transmit only the task-relevant semantic information over the critical uplink path from vehicular users to the edge server (ES). Furthermore, a network status monitor (NSM) module enables adaptive adjustment of the semantic compression rate in real-time response to fluctuating wireless channel conditions. The SC-USFL framework demonstrates a promising approach for efficiently balancing communication load, preserving privacy, and maintaining learning performance in resource-constrained vehicular environments. Finally, this paper highlights key open research directions to further advance the synergy between semantic communication and SFL in the vehicular network.

cs.LG↗

arXiv2026

Generative Visual Chain-of-Thought for Image Editing

Existing image editing methods struggle to perceive where to edit, especially under complex scenes and nuanced spatial instructions. To address this issue, we propose Generative Visual Chain-of-Thought (GVCoT), a unified framework that performs native visual reasoning by first generating spatial cues to localize the target region and then executing the edit. Unlike prior text-only CoT or tool-dependent visual CoT paradigms, GVCoT jointly optimizes visual tokens generated during the reasoning and editing phases in an end-to-end manner. This way fosters the emergence of innate spatial reasoning ability and enables more effective utilization of visual-domain cues. The main challenge of training GCVoT lies in the scarcity of large-scale editing data with precise edit region annotations; to this end, we construct GVCoT-Edit-Instruct, a dataset of 1.8M high-quality samples spanning 19 tasks. We adopt a progressive training strategy: supervised fine-tuning to build foundational localization ability in reasoning trace before final editing, followed by reinforcement learning to further improve reasoning and editing quality. Finally, we introduce SREdit-Bench, a new benchmark designed to comprehensively stress-test models under sophisticated scenes and fine-grained referring expressions. Experiments demonstrate that GVCoT consistently outperforms state-of-the-art models on SREdit-Bench and ImgEdit. We hope our GVCoT will inspire future research toward interpretable and precise image editing.

cs.CV↗

arXiv2025

CO-QLink: Cryogenic Optical Link for Scalable Quantum Computing Systems and High-Performance Cryogenic Computing Systems

Cryogenic systems necessitate extensive data transmission between room-temperature and cryogenic environments, as well as within the cryogenic temperature domain. High-speed, low-power data transmission is pivotal to enabling the deployment of larger-scale cryogenic systems, including the scalable quantum computing systems and the high-performance cryogenic computing systems fully immersed in liquid nitrogen. In contrast to wireline and microwave links, optical communication links are emerging as a solution characterized by high data rates, high energy efficiency, low signal attenuation, absence of thermal conduction, and superior scalability. In this work, a 4K heat-insulated high-speed (56Gbps) low-power (1.6pJ/b) transceiver (TRX) that achieves a complete link between 4K systems and room temperature (RT) equipment is presented. Copackaged with a PIN photodiode (PD), the RX uses an inverter-based analog front-end and an analog half-rate clock data recovery loop. Connecting to a Mach-Zehnder modulator (MZM), the TX contains a voltage-mode driver with current-mode injection for low-power output-swing-boosting and 3-tap feed-forward equalization (FFE). This link has been demonstrated in the control and readout of a complete superconducting quantum computing system.

quant-ph↗

arXiv2025

Age of Information Minimization in UAV-Enabled Integrated Sensing and Communication Systems

Unmanned aerial vehicles (UAVs) equipped with integrated sensing and communication (ISAC) capabilities are envisioned to play a pivotal role in future wireless networks due to their enhanced flexibility and efficiency. However, jointly optimizing UAV trajectory planning, multi-user communication, and target sensing under stringent resource constraints and time-critical conditions remains a significant challenge. To address this, we propose an Age of Information (AoI)-centric UAV-ISAC system that simultaneously performs target sensing and serves multiple ground users, emphasizing information freshness as the core performance metric. We formulate a long-term average AoI minimization problem that jointly optimizes the UAV's flight trajectory and beamforming. To tackle the high-dimensional, non-convexity of this problem, we develop a deep reinforcement learning (DRL)-based algorithm capable of providing real-time decisions on UAV movement and beamforming for both radar sensing and multi-user communication. Specifically, a Kalman filter is employed for accurate target state prediction, regularized zero-forcing is utilized to mitigate inter-user interference, and the Soft Actor-Critic algorithm is applied for training the DRL agent on continuous actions. The proposed framework adaptively balances the trade-offs between sensing accuracy and communication quality. Extensive simulation results demonstrate that our proposed method consistently achieves lower average AoI compared to baseline approaches.

eess.SP↗

arXiv2025

Split Federated Learning Empowered Vehicular Edge Intelligence: Concept, Adaptive Design and Future Directions

To achieve ubiquitous intelligence in future vehicular networks, artificial intelligence (AI) is essential for extracting valuable insights from vehicular data to enhance AI-driven services. By integrating AI technologies into Vehicular Edge Computing (VEC) platforms, which provides essential storage, computing, and network resources, Vehicular Edge Intelligence (VEI) can be fully realized. Traditional centralized learning, as one of the enabling technologies for VEI, places significant strain on network bandwidth while also increasing latency and privacy concerns. Nowadays, distributed machine learning methods, such as Federated Learning (FL), Split Learning (SL), and Split Federated Learning (SFL), are widely applied in vehicular networks to support VEI. However, these methods still face significant challenges due to the mobility and constrained resources inherent in vehicular networks. In this article, we first provide an overview of the system architecture, performance metrics, and challenges associated with VEI design. Then, the adaptive design of SFL, namely Adaptive Split Federated Learning (ASFL) is introduced. The proposed ASFL scheme dynamically adapts the cut layer selection process and operates in parallel, optimizing both communication and computation efficiency while improving model performance under non-IID data distribution. Finally, we highlight future research directions to shed the light on the efficient design of SFL.

cs.DC↗

arXiv2025

Audio-Sync Video Generation with Multi-Stream Temporal Control

Audio is inherently temporal and closely synchronized with the visual world, making it a naturally aligned and expressive control signal for controllable video generation (e.g., movies). Beyond control, directly translating audio into video is essential for understanding and visualizing rich audio narratives (e.g., Podcasts or historical recordings). However, existing approaches fall short in generating high-quality videos with precise audio-visual synchronization, especially across diverse and complex audio types. In this work, we introduce MTV, a versatile framework for audio-sync video generation. MTV explicitly separates audios into speech, effects, and music tracks, enabling disentangled control over lip motion, event timing, and visual mood, respectively -- resulting in fine-grained and semantically aligned video generation. To support the framework, we additionally present DEMIX, a dataset comprising high-quality cinematic videos and demixed audio tracks. DEMIX is structured into five overlapped subsets, enabling scalable multi-stage training for diverse generation scenarios. Extensive experiments demonstrate that MTV achieves state-of-the-art performance across six standard metrics spanning video quality, text-video consistency, and audio-video alignment. Project page: https://hjzheng.net/projects/MTV/.

cs.CV↗

arXiv2025

Ineffectiveness of Formamidine in Suppressing Ultralow Thermal Conductivity in Cubic Hybrid Perovskite FAPbI3

Fundamentally understanding the lattice dynamics and microscopic mechanisms of thermal transport in cubic hybrid organic-inorganic perovskites remains elusive, primarily due to their strong anharmonicity and frequent phase transitions. In this work, we comprehensively investigate the thermal transport behavior in cubic hybrid perovskite FAPbI3, integrating first principles-based anharmonic lattice dynamics with a linearized Wigner transport formula. The Temperature Dependent Effective Potential (TDEP) technique allows us to stabilize the negative soft modes, primarily dominated by organic cations, at finite temperatures in cubic FAPbI3. We then predict an ultra-low thermal conductivity of ~0.63 Wm^(-1) K^(-1) in cubic FAPbI3 at 300 K, with a temperature dependence of T^(-0.740), suggesting a good crystalline nature of phonon transport. Notably, the ultra-low thermal conductivity in cubic FAPbI3 is primarily attributed to the [PbI3]1- units, challenging the conventional focus on organic FA+ cations. This shift in focus is due to the presence of Pb(s)-I(p) anti-bonding sates within the [PbI3]1- units. Furthermore, thermal transport in cubic FAPbI3 is predominantly governed by the particle-like phonon propagation channel across the entire temperature range of 300-500 K, a result of diminished suppression of low-frequency phonons by FA+ cations and large inter-branch spacings. Finally, our findings underscore that the anharmonic force constants are highly temperature-sensitive, leading to underestimations of thermal conductivity when relying on 0-K anharmonic force constants. Our study not only elucidates the microscopic mechanisms of thermal transport in cubic FAPbI3 but also provides a crucial framework for the discovery, design, and understanding of hybrid organic-inorganic compounds with ultra-low thermal conductivity.

cond-mat.mtrl-sci↗

arXiv2025

Deploying Large AI Models on Resource-Limited Devices with Split Federated Learning

Large Artificial Intelligence Models (LAMs) powered by massive datasets, extensive parameter scales, and extensive computational resources, leading to significant transformations across various industries. Yet, their practical deployment on resource-limited mobile edge devices is hindered by critical challenges such as data privacy, constrained resources, and high overhead costs. Addressing this gap, this paper proposes a novel framework, named Quantized Split Federated Fine-Tuning Large AI Model (SFLAM). By partitioning the training load between edge devices and servers using a split learning paradigm, SFLAM can facilitate the operation of large models on devices and significantly lowers the memory requirements on edge devices. Additionally, SFLAM incorporates quantization management, power control, and bandwidth allocation strategies to enhance training efficiency while concurrently reducing energy consumption and communication latency. A theoretical analysis exploring the latency-energy trade-off is presented, and the framework's efficacy is validated via comprehensive simulations. The findings indicate that SFLAM achieves superior performance in terms of learning efficiency and scalability compared to conventional methods, thereby providing a valuable approach for enabling advanced AI services in resource-constrained scenarios.

cs.LG↗

arXiv2025

AIGC-assisted Federated Learning for Edge Intelligence: Architecture Design, Research Challenges and Future Directions

Federated learning (FL) can fully leverage large-scale terminal data while ensuring privacy and security, and is considered as a distributed alternative for the centralized machine learning. However, the issue of data heterogeneity poses limitations on FL's performance. To address this challenge, artificial intelligence-generated content (AIGC) which is an innovative data synthesis technique emerges as one potential solution. In this article, we first provide an overview of the system architecture, performance metrics, and challenges associated with AIGC-assistant FL system design. We then propose the Generative federated learning (GenFL) architecture and present its workflow, including the design of aggregation and weight policy. Finally, using the CIFAR10 and CIFAR100 datasets, we employ diffusion models to generate dataset and improve FL performance. Experiments conducted under various non-independent and identically distributed (non-IID) data distributions demonstrate the effectiveness of GenFL on overcoming the bottlenecks in FL caused by data heterogeneity. Open research directions in the research of AIGC-assisted FL are also discussed.

cs.LG↗

arXiv2025

AIGC-assisted Federated Learning for Vehicular Edge Intelligence: Vehicle Selection, Resource Allocation and Model Augmentation

To leverage the vast amounts of onboard data while ensuring privacy and security, federated learning (FL) is emerging as a promising technology for supporting a wide range of vehicular applications. Although FL has great potential to improve the architecture of intelligent vehicular networks, challenges arise due to vehicle mobility, wireless channel instability, and data heterogeneity. To mitigate the issue of heterogeneous data across vehicles, artificial intelligence-generated content (AIGC) can be employed as an innovative data synthesis technique to enhance FL model performance. In this paper, we propose AIGC-assisted Federated Learning for Vehicular Edge Intelligence (GenFV). We further propose a weighted policy using the Earth Mover's Distance (EMD) to quantify data distribution heterogeneity and introduce a convergence analysis for GenFV. Subsequently, we analyze system delay and formulate a mixed-integer nonlinear programming (MINLP) problem to minimize system delay. To solve this MINLP NP-hard problem, we propose a two-scale algorithm. At large communication scale, we implement label sharing and vehicle selection based on velocity and data heterogeneity. At the small computation scale, we optimally allocate bandwidth, transmission power and amount of generated data. Extensive experiments show that GenFV significantly improves the performance and robustness of FL in dynamic, resource-constrained environments, outperforming other schemes and confirming the effectiveness of our approach.

cs.DC↗

arXiv2025

IIMedGPT: Promoting Large Language Model Capabilities of Medical Tasks by Efficient Human Preference Alignment

Recent researches of large language models(LLM), which is pre-trained on massive general-purpose corpora, have achieved breakthroughs in responding human queries. However, these methods face challenges including limited data insufficiency to support extensive pre-training and can not align responses with users' instructions. To address these issues, we introduce a medical instruction dataset, CMedINS, containing six medical instructions derived from actual medical tasks, which effectively fine-tunes LLM in conjunction with other data. Subsequently, We launch our medical model, IIMedGPT, employing an efficient preference alignment method, Direct preference Optimization(DPO). The results show that our final model outperforms existing medical models in medical dialogue.Datsets, Code and model checkpoints will be released upon acceptance.

cs.CL↗

arXiv2025

Age-Based Device Selection and Transmit Power Optimization in Over-the-Air Federated Learning

Recently, over-the-air federated learning (FL) has attracted significant attention for its ability to enhance communication efficiency. However, the performance of over-the-air FL is often constrained by device selection strategies and signal aggregation errors. In particular, neglecting straggler devices in FL can lead to a decline in the fairness of model updates and amplify the global model's bias toward certain devices' data, ultimately impacting the overall system performance. To address this issue, we propose a joint device selection and transmit power optimization framework that ensures the appropriate participation of straggler devices, maintains efficient training performance, and guarantees timely updates. First, we conduct a theoretical analysis to quantify the convergence upper bound of over-the-air FL under age-of-information (AoI)-based device selection. Our analysis further reveals that both the number of selected devices and the signal aggregation errors significantly influence the convergence upper bound. To minimize the expected weighted sum peak age of information, we calculate device priorities for each communication round using Lyapunov optimization and select the highest-priority devices via a greedy algorithm. Then, we formulate and solve a transmit power and normalizing factor optimization problem for selected devices to minimize the time-average mean squared error (MSE). Experimental results demonstrate that our proposed method offers two significant advantages: (1) it reduces MSE and improves model performance compared to baseline methods, and (2) it strikes a balance between fairness and training efficiency while maintaining satisfactory timeliness, ensuring stable model performance.

cs.NI↗