Searcharxiv⌕ Search

arXiv subjects

Yiming Zhao

Publications and source records attributed to Yiming Zhao.

At least 55 records · Page 3Linked to original sources
arXiv2025

UTDesign: A Unified Framework for Stylized Text Editing and Generation in Graphic Design Images

AI-assisted graphic design has emerged as a powerful tool for automating the creation and editing of design elements such as posters, banners, and advertisements. While diffusion-based text-to-image models have demonstrated strong capabilities in visual content generation, their text rendering performance, particularly for small-scale typography and non-Latin scripts, remains limited. In this paper, we propose UTDesign, a unified framework for high-precision stylized text editing and conditional text generation in design images, supporting both English and Chinese scripts. Our framework introduces a novel DiT-based text style transfer model trained from scratch on a synthetic dataset, capable of generating transparent RGBA text foregrounds that preserve the style of reference glyphs. We further extend this model into a conditional text generation framework by training a multi-modal condition encoder on a curated dataset with detailed text annotations, enabling accurate, style-consistent text synthesis conditioned on background images, prompts, and layout specifications. Finally, we integrate our approach into a fully automated text-to-design (T2D) pipeline by incorporating pre-trained text-to-image (T2I) models and an MLLM-based layout planner. Extensive experiments demonstrate that UTDesign achieves state-of-the-art performance among open-source methods in terms of stylistic consistency and text accuracy, and also exhibits unique advantages compared to proprietary commercial approaches. Code and data for this paper are available at https://github.com/ZYM-PKU/UTDesign.

cs.CV↗
arXiv2025

MaP-AVR: A Meta-Action Planner for Agents Leveraging Vision Language Models and Retrieval-Augmented Generation

Embodied robotic AI systems designed to manage complex daily tasks rely on a task planner to understand and decompose high-level tasks. While most research focuses on enhancing the task-understanding abilities of LLMs/VLMs through fine-tuning or chain-of-thought prompting, this paper argues that defining the planned skill set is equally crucial. To handle the complexity of daily environments, the skill set should possess a high degree of generalization ability. Empirically, more abstract expressions tend to be more generalizable. Therefore, we propose to abstract the planned result as a set of meta-actions. Each meta-action comprises three components: {move/rotate, end-effector status change, relationship with the environment}. This abstraction replaces human-centric concepts, such as grasping or pushing, with the robot's intrinsic functionalities. As a result, the planned outcomes align seamlessly with the complete range of actions that the robot is capable of performing. Furthermore, to ensure that the LLM/VLM accurately produces the desired meta-action format, we employ the Retrieval-Augmented Generation (RAG) technique, which leverages a database of human-annotated planning demonstrations to facilitate in-context learning. As the system successfully completes more tasks, the database will self-augment to continue supporting diversity. The meta-action set and its integration with RAG are two novel contributions of our planner, denoted as MaP-AVR, the meta-action planner for agents composed of VLM and RAG. To validate its efficacy, we design experiments using GPT-4o as the pre-trained LLM/VLM model and OmniGibson as our robotic platform. Our approach demonstrates promising performance compared to the current state-of-the-art method. Project page: https://map-avr.github.io/.

cs.RO↗
arXiv2025

How Does Microservice Granularity Impact Energy Consumption and Performance? A Controlled Experiment

Context: Microservice architectures are a widely used software deployment approach, with benefits regarding flexibility and scalability. However, their impact on energy consumption is poorly understood, and often overlooked in favor of performance and other quality attributes (QAs). One understudied concept in this area is microservice granularity, i.e., over how many services the system functionality is distributed. Objective: We therefore aim to analyze the relationship between microservice granularity and two critical QAs in microservice-based systems: energy consumption and performance. Method: We conducted a controlled experiment using two open-source microservice-based systems of different scales: the small Pet Clinic system and the large Train Ticket system. For each system, we created three levels of granularity by merging or splitting services (coarse, medium, and fine) and then exposed them to five levels of request frequency. Results: Our findings revealed that: i) granularity significantly affected both energy consumption and response time, e.g., in the large system, fine granularity consumed on average 461 J more energy (13%) and added 5.2 ms to response time (14%) compared to coarse granularity; ii) higher request loads significantly increased both energy consumption and response times, with moving from 40 to 400 requests / s resulting in 651 J higher energy consumption (23%) and 41.2 ms longer response times (98%); iii) there is a complex relationship between granularity, system scale, energy consumption, and performance that warrants careful consideration in microservice design. We derive generalizable takeaways from our results. Conclusion: Microservices practitioners should take our findings into account when making granularity-related decisions, especially for large-scale systems.

cs.SE↗
arXiv2025

Preparing Spin Squeezed States via Adaptive Genetic Algorithm

We introduce a novel strategy employing an adaptive genetic algorithm (GA) for iterative optimization of control sequences to generate quantum nonclassical states. Its efficacy is demonstrated by preparing spin-squeezed states in an open collective spin model governed by a linear control field. Inspired by Darwinian evolution, the algorithm iteratively refines control sequences using crossover, mutation, and elimination strategies, starting from a coherent spin state within a dissipative and dephasing environment. We rigorously benchmark our method against constant control protocols and reinforcement learning, demonstrating competitive and robust performance. Furthermore, we showcase the GA's versatility by directly optimizing for metrologically relevant squeezing, achieving scalable performance, even in the presence of dissipation and thermal noise. The proposed strategy demonstrates a high state-preparation fidelity, exceeding 0.99, and provides a long time window for maintaining the spin squeezed state, even under dissipative conditions. We discuss feasible experimental implementations and potential extensions to alternative quantum systems, and the adaptability of the GA module. This research establishes the foundation for utilizing GA-like strategies in controlling quantum systems and achieving desired nonclassical states.

quant-ph↗
arXiv2025

Terahertz Channel performance in ULEO Satellite-to-Ground Communications

The exponential growth in satellite data traffic demands communication systems exceeding current microwave capacity limitations, while the terahertz (THz) frequency band (0.1-10 THz) offers unprecedented bandwidth potential with superior weather resilience compared to optical systems, particularly when combined with ultra low Earth orbit (ULEO) satellite deployments below 300 km altitude. This article presents a comprehensive performance evaluation for ULEO-THz satellite to ground communications, analyzing three distinct transmission architectures direct satellite to ground (S2G), satellite relay ground (SRG) forwarding, and satellite-to-high altitude base station (S2H) with fiber backhaul. Our analysis leverages altitude-resolved atmospheric propagation models validated using year long meteorological data from four high-altitude stations in Tibet and Qinghai, China. It incorporates frequency-dependent atmospheric absorption using ITU-R standards, free space path loss with curved atmospheric modeling, and regional atmospheric variations to derive total channel path loss, available bandwidth capacity, and bit error rate (BER) performance under both AWGN and Weibull fading conditions across multiple THz frequencies. Results demonstrate that direct S2G transmission at lower THz frequencies achieves optimal practical performance with maximum available bandwidth under QPSK modulation, while SRG suffers prohibitive cumulative losses from multiple hops, and S2H is rendered impractical for long-haul links by substantial electro-optical conversion and fiber transmission losses.

physics.app-ph↗
arXiv2025

CoS: Towards Optimal Event Scheduling via Chain-of-Scheduling

Recommending event schedules is a key issue in Event-based Social Networks (EBSNs) in order to maintain user activity. An effective recommendation is required to maximize the user's preference, subjecting to both time and geographical constraints. Existing methods face an inherent trade-off among efficiency, effectiveness, and generalization, due to the NP-hard nature of the problem. This paper proposes the Chain-of-Scheduling (CoS) framework, which activates the event scheduling capability of Large Language Models (LLMs) through a guided, efficient scheduling process. CoS enhances LLM by formulating the schedule task into three atomic stages, i.e., exploration, verification and integration. Then we enable the LLMs to generate CoS autonomously via Knowledge Distillation (KD). Experimental results show that CoS achieves near-theoretical optimal effectiveness with high efficiency on three real-world datasets in a interpretable manner. Moreover, it demonstrates strong zero-shot learning ability on out-of-domain data.

cs.AI↗
arXiv2025

SEEA-R1: Tree-Structured Reinforcement Fine-Tuning for Self-Evolving Embodied Agents

Self-evolution, the ability of agents to autonomously improve their reasoning and behavior, is essential for the embodied domain with long-horizon, real-world tasks. Despite current advancements in reinforcement fine-tuning (RFT) showing strong performance in enhancing reasoning in LLMs, its potential to enable self-evolving embodied intelligence with multi-modal interactions remains largely unexplored. Specifically, reinforcement fine-tuning faces two fundamental obstacles in embodied settings: (i) the lack of accessible intermediate rewards in multi-step reasoning tasks limits effective learning signals, and (ii) reliance on hand-crafted reward functions restricts generalization to novel tasks and environments. To address these challenges, we present Self-Evolving Embodied Agents-R1, SEEA-R1, the first RFT framework designed for enabling the self-evolving capabilities of embodied agents. Specifically, to convert sparse delayed rewards into denser intermediate signals that improve multi-step reasoning, we propose Tree-based group relative policy optimization (Tree-GRPO) integrates Monte Carlo Tree Search into GRPO. To generalize reward estimation across tasks and scenes, supporting autonomous adaptation and reward-driven self-evolution, we further introduce Multi-modal Generative Reward Model (MGRM). To holistically evaluate the effectiveness of SEEA-R1, we evaluate on the ALFWorld benchmark, surpassing state-of-the-art methods with scores of 85.07% (textual) and 46.27% (multi-modal), outperforming prior models including GPT-4o. SEEA-R1 also achieves scores of 80.3% (textual) and 44.03% (multi-modal) without ground truth reward, surpassing all open-source baselines and highlighting its scalability as a self-evolving embodied agent. Additional experiments and qualitative analysis further support the potential of SEEA-R1 for future research in scalable embodied intelligence.

cs.AI↗
arXiv2025

Non-Abelian Gauge Enhances Self-Healing for Non-Hermitian Su--Schrieffer--Heeger Chain

We investigate a non-Hermitian extension of the Su--Schrieffer--Heeger model that incorporates spin-dependent SU(2) gauge fields, represented by non-Abelian couplings between lattice sites, as well as independent nonreciprocal hopping amplitudes. This framework gives rise to a rich phase structure characterized by complex-energy braiding and tunable non-Hermitian skin effects. By employing the generalized Brillouin zone approach, we analyze the bulk-boundary correspondence and identify topological transitions protected by chiral symmetry. Notably, we demonstrate that non-Abelian gauge fields significantly enhance the dynamical resilience of the system, enabling robust self-healing under a moving scattering potential. These results clarify the role of SU(2) gauge fields in stabilizing non-Hermitian topological phases and indicate that the proposed model can be realized with currently available photonic, atomic, and superconducting experimental platforms.

cond-mat.mes-hall↗
arXiv2025

Experimental Characterization and Dynamic Modeling of THz Channels Under Fog Conditions

The terahertz (THz) band is a promising candidate for sixth-generation wireless networks, but its deploymen in outdoor environments is challenged by meteorological phenomena, particularly fog, which imposes variable and difficult-to-predict channel degradation. This article introduces dynamic channel model for the THz band explicitly driven by the time-evolving droplet size distribution (DSD) of fog, integrating real-time microphysical sensing to capture variations in the fog microstructure. Experimental measurements were conducted at 220 GHz and 320 GHz in a controlled fog chamber to achieve quasi-stationary states, and a larger room-scale setup to characterize dynamic, non-stationary fog evolution. The results confirm that channel power loss is overwhelmingly dominated by absorption rather than scattering, validating the use of the computationally efficient Rayleigh approximation below 1 THz. Statistical analysis revealed exceptionally high Rician K-factors, demonstrating that THz channels maintain strong line-of-sight stability even in dense fog. System-level performance analysis shows that degradation in bit error rate is driven by the slow, gradual evolution of the DSD, rather than fast multipath fading. This finding enables the reliable simplification of the THz fog channel into a near-Gaussian channel model with time-varying signal-to-noise ratio. This microphysics-aware approach established here provides the necessary foundation for developing adaptive system designs centered on SNR tracking for robust future THz networks.

physics.app-ph↗
arXiv2025

RoboSeek: You Need to Interact with Your Objects

Optimizing and refining action execution through exploration and interaction is a promising way for robotic manipulation. However, practical approaches to interaction-driven robotic learning are still underexplored, particularly for long-horizon tasks where sequential decision-making, physical constraints, and perceptual uncertainties pose significant challenges. Motivated by embodied cognition theory, we propose RoboSeek, a framework for embodied action execution that leverages interactive experience to accomplish manipulation tasks. RoboSeek optimizes prior knowledge from high-level perception models through closed-loop training in simulation and achieves robust real-world execution via a real2sim2real transfer pipeline. Specifically, we first replicate real-world environments in simulation using 3D reconstruction to provide visually and physically consistent environments, then we train policies in simulation using reinforcement learning and the cross-entropy method leveraging visual priors. The learned policies are subsequently deployed on real robotic platforms for execution. RoboSeek is hardware-agnostic and is evaluated on multiple robotic platforms across eight long-horizon manipulation tasks involving sequential interactions, tool use, and object handling. Our approach achieves an average success rate of 79%, significantly outperforming baselines whose success rates remain below 50%, highlighting its generalization and robustness across tasks and platforms. Experimental results validate the effectiveness of our training framework in complex, dynamic real-world settings and demonstrate the stability of the proposed real2sim2real transfer mechanism, paving the way for more generalizable embodied robotic learning. Project Page: https://russderrick.github.io/Roboseek/

cs.RO↗
arXiv2025

Baton: Compensate for Missing Wi-Fi Features for Practical Device-free Tracking

Wi-Fi contact-free sensing systems have attracted widespread attention due to their ubiquity and convenience. The integrated sensing and communication (ISAC) technology utilizes off-the-shelf Wi-Fi communication signals for sensing, which further promotes the deployment of intelligent sensing applications. However, current Wi-Fi sensing systems often require prolonged and unnecessary communication between transceivers, and brief communication interruptions will lead to significant performance degradation. This paper proposes Baton, the first system capable of accurately tracking targets even under severe Wi-Fi feature deficiencies. To be specific, we explore the relevance of the Wi-Fi feature matrix from both horizontal and vertical dimensions. The horizontal dimension reveals feature correlation across different Wi-Fi links, while the vertical dimension reveals feature correlation among different time slots. Based on the above principle, we propose the Simultaneous Tracking And Predicting (STAP) algorithm, which enables the seamless transfer of Wi-Fi features over time and across different links, akin to passing a baton. We implement the system on commercial devices, and the experimental results show that our system outperforms existing solutions with a median tracking error of 0.46m, even when the communication duty cycle is as low as 20.00%. Compared with the state-of-the-art, our system reduces the tracking error by 79.19% in scenarios with severe Wi-Fi feature deficiencies.

cs.NI↗
arXiv2025

Non-Abelian Gauge Effect for 2-D Non-Hermitian Hatano-Nelson Model in Cylinder Type

Non-Abelian gauge offers a powerful route to engineer novel topological phenomena. Here, we systematically investigate a two-dimensional (2D) non-Hermitian Hatano-Nelson model incorporating SU(2) non-Abelian gauge, demonstrating the emergence of Hopf-link bulk braiding topology in the complex energy spectrum solely with x-direction nearest-neighbor couplings. Because of the limitations of exceptional point (EP) topology in fully capturing the rich non-Hermitian skin effect (NHSE) under non-Abelian influence, we introduce a novel polarization parameter derived from the generalized Brillouin zone (GBZ). This parameter quantitatively discerns left-, right-, and notably, bipolar skin modes, with its accuracy corroborated by directly encoding real-space eigenstate. Our findings reveal that non-Abelian gauge provides unprecedented influence over NHSE, compared with Abelian gauge and without gauge cases. Furthermore, we uncover unique characteristics of zero-imaginary-energy eigenstates at these topological boundaries, including pronounced degeneracy and bipolar localization which is unaffected by size effects, investigated via dynamical evolution and Inverse Participation Ratio (IPR). This work establishes a new paradigm for synthesizing and manipulating non-Hermitian topological phases driven by non-Abelian structures, opening avenues for topological engineering and holding promise for experimental realization in synthetic dimensional platforms.

cond-mat.other↗
arXiv2025

Optimization-free Smooth Control Barrier Function for Polygonal Collision Avoidance

Polygonal collision avoidance (PCA) is short for the problem of collision avoidance between two polygons (i.e., polytopes in planar) that own their dynamic equations. This problem suffers the inherent difficulty in dealing with non-smooth boundaries and recently optimization-defined metrics, such as signed distance field (SDF) and its variants, have been proposed as control barrier functions (CBFs) to tackle PCA problems. In contrast, we propose an optimization-free smooth CBF method in this paper, which is computationally efficient and proved to be nonconservative. It is achieved by three main steps: a lower bound of SDF is expressed as a nested Boolean logic composition first, then its smooth approximation is established by applying the latest log-sum-exp method, after which a specified CBF-based safety filter is proposed to address this class of problems. To illustrate its wide applications, the optimization-free smooth CBF method is extended to solve distributed collision avoidance of two underactuated nonholonomic vehicles and drive an underactuated container crane to avoid a moving obstacle respectively, for which numerical simulations are also performed.

math.OC↗
arXiv2025

Comparison Research of Millimeter-Wave/Infrared Co-aperture Reflector Antenna Systems Based on a Specialized Film

This paper presents a novel co-aperture reflector antenna operating in millimeter-wave (MMW) and infrared (IR) for cloud detection radar. The proposed design combines a back-fed dual-reflector antenna, an IR optical reflection system, and a specialize thin film with IR-reflective/MMW-transmissive properties. Simulations demonstrate a gain exceeding 50 dBi within 94 GHz plush or minus 500 MHz bandwidth, with 0.46° beamwidth in both azimuth (E-plane) and elevation (H-plane) and sidelobe levels below -25 dB. This co-aperture architecture addresses the limitations of standalone MMW and IR radars, enabling high-resolution cloud microphysical parameter retrieval while minimizing system footprint. The design lays a foundation for airborne/spaceborne multi-mode detection systems.

eess.SP↗
arXiv2025

SDVPT: Semantic-Driven Visual Prompt Tuning for Open-World Object Counting

Open-world object counting leverages the robust text-image alignment of pre-trained vision-language models (VLMs) to enable counting of arbitrary categories in images specified by textual queries. However, widely adopted naive fine-tuning strategies concentrate exclusively on text-image consistency for categories contained in training, which leads to limited generalizability for unseen categories. In this work, we propose a plug-and-play Semantic-Driven Visual Prompt Tuning framework (SDVPT) that transfers knowledge from the training set to unseen categories with minimal overhead in parameters and inference time. First, we introduce a two-stage visual prompt learning strategy composed of Category-Specific Prompt Initialization (CSPI) and Topology-Guided Prompt Refinement (TGPR). The CSPI generates category-specific visual prompts, and then TGPR distills latent structural patterns from the VLM's text encoder to refine these prompts. During inference, we dynamically synthesize the visual prompts for unseen categories based on the semantic correlation between unseen and training categories, facilitating robust text-image alignment for unseen categories. Extensive experiments integrating SDVPT with all available open-world object counting models demonstrate its effectiveness and adaptability across three widely used datasets: FSC-147, CARPK, and PUCPR+.

cs.CV↗
arXiv2025

VCR-Bench: A Comprehensive Evaluation Framework for Video Chain-of-Thought Reasoning

The advancement of Chain-of-Thought (CoT) reasoning has significantly enhanced the capabilities of large language models (LLMs) and large vision-language models (LVLMs). However, a rigorous evaluation framework for video CoT reasoning remains absent. Current video benchmarks fail to adequately assess the reasoning process and expose whether failures stem from deficiencies in perception or reasoning capabilities. Therefore, we introduce VCR-Bench, a novel benchmark designed to comprehensively evaluate LVLMs' Video Chain-of-Thought Reasoning capabilities. VCR-Bench comprises 859 videos spanning a variety of video content and durations, along with 1,034 high-quality question-answer pairs. Each pair is manually annotated with a stepwise CoT rationale, where every step is tagged to indicate its association with the perception or reasoning capabilities. Furthermore, we design seven distinct task dimensions and propose the CoT score to assess the entire CoT process based on the stepwise tagged CoT rationals. Extensive experiments on VCR-Bench highlight substantial limitations in current LVLMs. Even the top-performing model, o1, only achieves a 62.8% CoT score and an 56.7% accuracy, while most models score below 40%. Experiments show most models score lower on perception than reasoning steps, revealing LVLMs' key bottleneck in temporal-spatial information processing for complex video reasoning. A robust positive correlation between the CoT score and accuracy confirms the validity of our evaluation framework and underscores the critical role of CoT reasoning in solving complex video reasoning tasks. We hope VCR-Bench to serve as a standardized evaluation framework and expose the actual drawbacks in complex video reasoning task.

cs.CV↗
arXiv2025

STMA: A Spatio-Temporal Memory Agent for Long-Horizon Embodied Task Planning

A key objective of embodied intelligence is enabling agents to perform long-horizon tasks in dynamic environments while maintaining robust decision-making and adaptability. To achieve this goal, we propose the Spatio-Temporal Memory Agent (STMA), a novel framework designed to enhance task planning and execution by integrating spatio-temporal memory. STMA is built upon three critical components: (1) a spatio-temporal memory module that captures historical and environmental changes in real time, (2) a dynamic knowledge graph that facilitates adaptive spatial reasoning, and (3) a planner-critic mechanism that iteratively refines task strategies. We evaluate STMA in the TextWorld environment on 32 tasks, involving multi-step planning and exploration under varying levels of complexity. Experimental results demonstrate that STMA achieves a 31.25% improvement in success rate and a 24.7% increase in average score compared to the state-of-the-art model. The results highlight the effectiveness of spatio-temporal memory in advancing the memory capabilities of embodied agents.

cs.AI↗