Searcharxiv⌕ Search

arXiv subjects

Zhiqiang Yuan

Publications and source records attributed to Zhiqiang Yuan.

At least 19 recordsLinked to original sources
arXiv2026

Realistic Characterization and Modeling of Vehicle-Mounted Antenna Radiation Patterns Based on Large-Scale Full-Vehicle Measurements

Vehicle-mounted antenna radiation patterns can be significantly altered after installation due to interactions with the vehicle body. However, existing studies mainly focus on simulations or isolated antenna characterization, while large-scale experimental investigations remain limited. This paper presents a comprehensive experimental analysis of vehicle-mounted antenna radiation patterns based on full-vehicle spherical near-field measurements. A large-scale dataset covering ten commercial vehicle platforms, multiple antenna mounting locations, and various wireless functions, including 4G, 5G, V2X, and GNSS, is established under a unified measurement framework. Based on the measured results, representative case studies and statistical characterization are performed to investigate the impacts of vehicle installation on antenna radiation behavior. The results reveal substantial variations across mounting locations and wireless functions, highlighting the strong influence of vehicle integration on realistic antenna performance. Furthermore, a novel statistical model is proposed to generate realistic vehicle-mounted antenna patterns using a small set of physically interpretable parameters. The obtained dataset, characterization results, and modeling approach provide a foundation for realistic antenna evaluation and wireless system simulations in vehicular communication applications.

eess.SP↗
arXiv2026

Trustworthy synthetic visual media: Evidence across the media lifecycle

Images and videos have long helped people understand what happened and how a work came into being. Generative systems complicate that role. Realistic media can now be produced and revised without leaving a stable history, so appearance no longer reveals whether a scene was captured, synthesized, or altered along the way. Trust must instead come from evidence that explains the path an asset has taken and the circumstances in which it was used. Some of this evidence can be recovered from the media, while some must be recorded during production and preserved as the asset circulates. This review brings those approaches together and asks when their claims remain meaningful after ordinary processing or deliberate manipulation. We argue that trustworthy media do not depend on one universal marker of authenticity. The evidence must suit the question at hand, reach the person making the judgment, and remain open to correction when better information emerges. The larger goal is to keep the history of media intelligible even as the media itself continues to change.

cs.CV↗
arXiv2026

RAVA: Retrieval-Augmented Viewpoint Alignment for Subject-Driven Image Generation

Reference-driven image generation has made rapid progress on identity preservation, but reliable viewpoint control across different subjects remains poorly understood. The difficulty is not merely generating a new image of the target subject: the model must infer the implicit viewpoint of one subject and transfer it to another subject using only image-level evidence, without camera poses, depth, or ray-based conditions. In this setting, existing generators conditioned on multiple image references often rely on spurious semantic correlations, which lead to viewpoint drift, part-level structural mismatches, and missing or unsupported target-specific content. We formulate this challenge as cross-subject viewpoint alignment and propose RAVA, a retrieval-augmented framework that supplies explicit geometric evidence before generation. RAVA first learns a cross-instance viewpoint embedding that retrieves target-subject images aligned with the anchor viewpoint, then applies a LogDet-based subset selection strategy to retain a compact reference set that is both view-consistent and structurally complementary. The selected references are finally consumed by a fine-tuned multi-reference image generator. Experiments show that generic semantic embeddings are nearly random for this task, while the proposed retriever substantially improves viewpoint retrieval quality. On cross-subject generation, RAVA consistently outperforms zero-shot baselines and stronger retrieval alternatives under the same generation backbone. These results indicate that cross-subject viewpoint alignment benefits from retrieval-augmented geometric grounding rather than relying on end-to-end generation alone.

cs.CV↗
arXiv2026

PAL-Bench: Evidence-Grounded Profile Reconstruction from Longitudinal Personal Albums

Longitudinal personal albums are weak-schema multimodal databases: noisy perceptual records whose key facts require joins across faces, text, timestamps, locations, and repeated events. Existing visual, video, document, and lifelog benchmarks test sub-problems, but not album-scale profile reconstruction with social identity binding and evidence citation. Benchmarking this task is difficult because the ground truth needed for evaluation--owner profiles, social graphs, face-name maps, and evidence provenance--is private state that real albums cannot safely release. We introduce PAL-Bench, a controlled benchmark for evidence-grounded reconstruction under a public-record contract. Its Evidence Compiler builds latent private worlds, programs target-level evidence paths, renders album pixels, re-measures them through perception pipelines, and exports audited public/private views. Agents receive only perception-derived public records; targets, identifier maps, and evidence paths remain hidden. PAL-Bench contains 50 synthetic users, 36,659 public photo records, and 2,799 targets over owner facts, identities, and relations. A privacy-preserving audit with 10 participants confirms that PAL-Bench evidence structures match real private albums, though equivalent releases remain privacy-prohibitive. Across seven systems and two compute-matched diagnostics, a seven-metric protocol reveals a gap between plausible profile summarization and faithful social reconstruction: systems recover some owner facts but struggle with recurring identities and evidence citation. PAL-TRACE, a reference framework that freezes identity bindings before owner-fact mining, performs best but leaves hard identity resolution far from solved. PAL-Bench provides a testbed for perceptual entity resolution, multimodal data integration, temporal evidence aggregation, and provenance-aware structured prediction.

cs.AI↗
arXiv2026

Fine-grained Fragment Retrieval in Multi-modal Long-form Dialogues

With the widespread adoption of multi-modal communication platforms, long-form dialogues interleaving text and images have become increasingly common. Users often need to retrieve coherent dialogue fragments related to specific topics, rather than isolated utterances. We propose Fine-grained Fragment Retrieval (FFR), which locates semantically relevant multi-utterance, multi-image fragments in multi-modal long-form dialogues. We explore two settings: (1) FFR within Single-Dialogue, retrieving fragments from a given dialogue; and (2) FFR within Dialogue Corpus, retrieving from a large-scale corpus for open-domain scenarios. For (1), we introduce F2RVLM, a generation-based retrieval model trained with reinforcement learning, using multi-objective rewards and difficulty-aware curriculum sampling to enhance fragment coherence. For (2), we develop FFRS, a two-stage system combining offline fragment-level indexing with online retrieval. Specifically, each dialogue is decomposed into minimal semantic fragments encoded by a Fragment Embedding Model (FEM) into a vector database; at inference, FEM rapidly recalls Top-K candidates, and F2RVLM performs fine-grained reasoning to identify the most relevant sub-content. To support FFR, we construct MLDR, the longest multi-modal dialogue retrieval dataset to date, and a WeChat-based real-world test set. Experiments on both benchmarks demonstrate that F2RVLM and FFRS consistently achieve superior performance across single-dialogue and corpus-level FFR.

cs.CL↗
arXiv2026

PhotoCraft: Agentic Reasoning with Hierarchical Self-Evolving Memory for Deep Image Search

Deep Image Search requires multi-step reasoning over rich contextual cues, such as time, location, and event relations. However, most existing LLM-based agents are stateless and reactive, lacking persistent memory to maintain long-horizon context or transfer experience across tasks, which often leads to execution drift and experience isolation. To address these limitations, we propose PhotoCraft, a training-free, hierarchical memory system for photo-search agents. Inspired by human cognition, PhotoCraft equips MLLMs with working, episodic, and semantic memory, which are dynamically invoked during reasoning to preserve logical consistency and knowledge transferability throughout multi-step reasoning and answer generation. Extensive experiments on DISBench demonstrate that PhotoCraft consistently improves context-aware retrieval across diverse MLLM backbones, achieving gains of up to 18.5\% and effectively mitigating key bottlenecks in memoryless deep image search, offering a practical path toward reliable and generalizable multimodal search agents.

cs.CL↗
arXiv2026

Artificial-Intelligence-Assisted Multi-Modal Terahertz Sensing and Environment Reconstruction

Multi-modal sensing is an important enabler for future environment-aware wireless systems, since a single sensing modality is generally insufficient to provide accurate metric geometry, material awareness, and semantic interpretability in complex environments. This paper presents a measurement-based multi-modal THz sensing and vision framework for indoor environment reconstruction. A three-dimensional monostatic THz channel sounding system operating at 290-310 GHz is integrated with an omnidirectional fisheye camera to acquire radio-frequency and visual observations from a common sensing viewpoint. From the measured THz data, a signal processing pipeline extracts multipath components and infers geometryand material-consistent structural primitives through trajectory tracking-assisted parameter estimation, graph-based structure discovery, planar reconstruction, and reflection-loss analysis. In parallel, AI-based visual perception modules extract object-level semantic masks and depth priors from panoramic images. To associate these heterogeneous representations, an agentic-AI-based task-driven THz-agent module is developed to select appropriate integration tools according to the attributes of the modality-specific outputs. Through angular alignment and consistency analysis, THz-derived metric geometry and material information are associated with vision-derived semantic regions and depth priors, enabling geometry-consistent and semantically interpretable environment reconstruction directly from measurements. Experimental validation in the indoor L-shaped hallway demonstrates that the proposed framework reconstructs dominant structural elements with centimeter-level accuracy while identifying semantic categories and material attributes of representative indoor objects.

eess.SP↗
arXiv2026

On Spatial Degree-of-Freedom Analysis of Near-Field Multipath Channels for Ultra-massive MIMO Systems

The transition to near-field (NF) communications in ultra-massive multiple-input multiple-output (UM-MIMO) systems fundamentally alters the spatial degrees of freedom (DoF) of wireless channels. While the NF DoF of line-of-sight (LoS) transmission channels is well-characterized in the literature, the DoF in NF multipath scenarios remains underexplored. This paper investigates the spatial DoF of NF UM-MIMO channels under practical multipath conditions. A generic DoF metric is derived by modeling multipath propagation and analyzing the resulting eigenvalue distribution based on the Green' s function representation of the channel. The DoF contribution of each path is determined by the product of the effective electrical aperture and the subtended solid angle, and the total DoF is obtained through the effective union of spatially resolvable path contributions. A mapping between the eigenvalue distribution and multipath powers is further established. Numerical simulations and real-world NF channel measurements at 28-30 GHz with 720 array elements are conducted for validation in both LoS multipath and non-LoS scenarios. The results show that multipath propagation can significantly increase the spatial DoF and that the proposed metric accurately predicts the DoF of practical NF channels. The proposed framework provides a practical tool for DoF prediction and supports capacity analysis and spatial multiplexing design in future NF UM-MIMO systems.

eess.SP↗
arXiv2026

CoDA: Color Distribution Probing for Efficient and Generalizable AI-Generated Image Detection

AI-generated image detection faces a persistent trade-off between generalization and efficiency: lightweight artifact-based methods often degrade on unseen generators or domains, whereas more robust large-scale models are computationally expensive. Meanwhile, existing benchmarks mainly focus on cross-model evaluation in photorealistic settings, leaving cross-domain robustness underexplored. To address this gap, we introduce FakeForm, a large-scale benchmark with approximately 370,000 images across 62 diverse domains for both cross-model and cross-domain evaluation. Motivated by this broader setting, we revisit color-distribution probing as an efficient complementary cue for AI-generated image detection. We observe that, especially for photographic content, real photographs tend to exhibit smoother and more stable color patterns, whereas synthetic images often show characteristic color imbalances introduced by neural generation. Based on this observation, we propose CoDA, a compact 1.48M-parameter detector built on a Noise-Quantization Probe, together with a theoretical analysis linking probe responses to color non-uniformity. Experiments show that CoDA achieves state-of-the-art performance on standard benchmarks and the best results on the challenging cross-domain evaluation of FakeForm, while remaining highly competitive in cross-model photorealistic settings. These results suggest that persistent generative artifacts can provide a practical foundation for efficient and robust AI-generated image detection. The models and FakeForm benchmark will be made publicly available.

cs.CV↗
arXiv2026

Less Redundancy: Boosting Practicality of Vision Language Model in Walking Assistants

Approximately 283 million people worldwide live with visual impairments, motivating increasing research into leveraging Visual Language Models (VLMs) to develop effective walking assistance systems for blind and low vision individuals. However, existing VLMs in walking assistant task often have outputs that contain considerable redundancy and extraneous details, adversely affecting users' ability to accurately assess their surroundings. Moreover, these models typically lack the capability to proactively assess environmental risks and adaptively trigger reminders based on the appropriate scene, leading to excessive temporal redundancy. To mitigate output and temporal redundancy, we propose WalkVLM-LR, a walking assistance model with less redundancy. To reduce output redundancy, we introduce four human-preference-based custom reward functions within the GRPO-based reasoning framework to optimize the output in terms of conciseness, fluency, keyword density, and accuracy, thereby producing more informative and streamlined outputs. To minimize temporal redundancy, we incorporate an environment awareness discriminator, which shares the visual encoder with the VLMs to reduce redundant computations and enhance discriminative efficiency, to make WalkVLM-LR assess scene risk levels and minimize unnecessary reminders. Experimental results demonstrate that our method achieves state-of-the-art performance across all evaluation metrics compared with other models, particularly in output conciseness and less temporal redundancy.

cs.CL↗
arXiv2026

Project-Level C-to-Rust Translation via Pointer Knowledge Graphs

Translating C code into safe Rust is an effective way to ensure memory safety. Compared to rule-based approaches, which often produce largely unsafe Rust code, LLM-based methods generate more idiomatic and safer Rust by leveraging extensive training on human-written code. Despite their promise, existing LLM-based approaches still struggle with project-level C-to-Rust translation. They typically partition a C project into smaller units (e.g., functions) based on call graphs and translate them in a bottom-up manner to resolve dependencies. However, this unit-by-unit paradigm often fails to handle pointers due to the lack of a global view of their usage. To address this limitation, we propose a novel C-to-Rust Pointer Knowledge Graph (KG) that augments code dependency graphs with two types of pointer semantics: (i) pointer usage information, which captures global behaviors such as points-to flows and lifts low-level struct interactions to higher-level abstractions; and (ii) Rust-oriented annotations, which encode ownership, mutability, nullability, and lifetime. Building on this KG, we further propose PtrTrans, a project-level C-to-Rust translation approach. In PtrTrans, the KG provides LLMs with comprehensive global pointer semantics, guiding them to generate safe and idiomatic Rust code. Experimental results show that PtrTrans reduces unsafe usages in translated Rust by 99.9% compared to both rule-based and conventional LLM-based methods, while achieving 29.3% higher functional correctness than fuzzing-enhanced LLM approaches.

cs.SE↗
arXiv2026

TransAgent: Enhancing LLM-Based Code Translation via Fine-Grained Execution Alignment

Code translation transforms code between programming languages while preserving functionality, which is critical in software development and maintenance. While traditional learning-based code translation methods have limited effectiveness due to the lack of sufficient parallel training data, Large Language Models (LLMs) have recently advanced this field with their strong code generation and comprehension capabilities. However, code translated by LLMs still suffers from diverse quality issues, such as syntax and semantic errors. In this work, we propose TransAGENT, a novel multi-agent system that eliminates the errors during LLM-based code translation. The main insight of TransAGENT is to localize error-prone code blocks via fine-grained execution alignment between source and target code. We evaluate TransAGENT on a newly constructed benchmark of recent programming tasks to mitigate data leakage. TransAGENT outperforms the latest UniTrans by up to 33.3% in translation accuracy and achieves an average improvement of 56.7% over Agentless in program repair performance. We also conduct an ablation study and evaluate TransAGENT across different LLMs, demonstrating its effectiveness and strong generalizability.

cs.SE↗
arXiv2026

Does Pass Rate Tell the Whole Story? Evaluating Design Constraint Compliance in LLM-based Issue Resolution

Repository-level issue resolution benchmarks have become a standard testbed for evaluating LLM-based agents, yet success is still predominantly measured by test pass rates. In practice, however, acceptable patches must also comply with project-specific design constraints, such as architectural conventions, error-handling policies, and maintainability requirements, which are rarely encoded in tests and are often documented only implicitly in code review discussions. This paper introduces \textit{design-aware issue resolution} and presents \bench{}, a benchmark that makes such implicit design constraints explicit and measurable. \bench{} is constructed by mining and validating design constraints from real-world pull requests, linking them to issue instances, and automatically checking patch compliance using an LLM-based verifier, yielding 495 issues and 1,787 validated constraints across six repositories, aligned with SWE-bench-Verified and SWE-bench-Pro. Experiments with state-of-the-art agents show that test-based correctness substantially overestimates patch quality: fewer than half of resolved issues are fully design-satisfying, design violations are widespread, and functional correctness exhibits negligible statistical association with design satisfaction. While providing issue-specific design guidance reduces violations, substantial non-compliance remains, highlighting a fundamental gap in current agent capabilities and motivating design-aware evaluation beyond functional correctness.

cs.SE↗
arXiv2025

RDTF: Resource-efficient Dual-mask Training Framework for Multi-frame Animated Sticker Generation

Recently, significant advancements have been achieved in video generation technology, but applying it to resource-constrained downstream tasks like multi-frame animated sticker generation (ASG) characterized by low frame rates, abstract semantics, and long tail frame length distribution-remains challenging. Parameter-efficient fine-tuning (PEFT) techniques (e.g., Adapter, LoRA) for large pre-trained models suffer from insufficient fitting ability and source-domain knowledge interference. In this paper, we propose Resource-Efficient Dual-Mask Training Framework (RDTF), a dedicated solution for multi-frame ASG task under resource constraints. We argue that training a compact model from scratch with million-level samples outperforms PEFT on large models, with RDTF realizing this via three core designs: 1) a Discrete Frame Generation Network (DFGN) optimized for low-frame-rate ASG, ensuring parameter efficiency; 2) a dual-mask based data utilization strategy to enhance the availability and diversity of limited data; 3) a difficulty-adaptive curriculum learning method that decomposes sample entropy into static and adaptive components, enabling easy-to-difficult training convergence. To provide high-quality data support for RDTFs training from scratch, we construct VSD2M-a million-level multi-modal animated sticker dataset with rich annotations (static and animated stickers, action-focused text descriptions)-filling the gap of dedicated animated data for ASG task. Experiments demonstrate that RDTF is quantitatively and qualitatively superior to state-of-the-art PEFT methods (e.g., I2V-Adapter, SimDA) on ASG tasks, verifying the feasibility of our framework under resource constraints.

cs.MM↗
arXiv2025

F2RVLM: Boosting Fine-grained Fragment Retrieval for Multi-Modal Long-form Dialogue with Vision Language Model

Traditional dialogue retrieval aims to select the most appropriate utterance or image from recent dialogue history. However, they often fail to meet users' actual needs for revisiting semantically coherent content scattered across long-form conversations. To fill this gap, we define the Fine-grained Fragment Retrieval (FFR) task, requiring models to locate query-relevant fragments, comprising both utterances and images, from multimodal long-form dialogues. As a foundation for FFR, we construct MLDR, the longest-turn multimodal dialogue retrieval dataset to date, averaging 25.45 turns per dialogue, with each naturally spanning three distinct topics. To evaluate generalization in real-world scenarios, we curate and annotate a WeChat-based test set comprising real-world multimodal dialogues with an average of 75.38 turns. Building on these resources, we explore existing generation-based Vision-Language Models (VLMs) on FFR and observe that they often retrieve incoherent utterance-image fragments. While optimized for generating responses from visual-textual inputs, these models lack explicit supervision to ensure semantic coherence within retrieved fragments. To this end, we propose F2RVLM, a generative retrieval model trained in a two-stage paradigm: (1) supervised fine-tuning to inject fragment-level retrieval knowledge, and (2) GRPO-based reinforcement learning with multi-objective rewards promoting semantic precision, relevance, and contextual coherence. To handle varying intra-fragment complexity, from locally dense to sparsely distributed, we introduce difficulty-aware curriculum sampling that ranks training instances by model-predicted difficulty and gradually exposes the model to harder samples. This boosts reasoning ability in long, multi-turn contexts. F2RVLM outperforms popular VLMs in both in-domain and real-domain settings, demonstrating superior retrieval performance.

cs.CV↗
arXiv2025

A Novel Multi-Reference-Point Modeling Framework for Monostatic Background Channel: Toward 3GPP ISAC Standardization

Integrated Sensing and Communication (ISAC) has been identified as a key 6G application by ITU and 3GPP. A realistic, standard-compatible channel model is essential for ISAC system design. To characterize the impact of Sensing Targets (STs), 3GPP defines ISAC channel as a combination of target and background channels, comprising multipath components related to STs and those originating solely from the environment, respectively. Although the background channel does not carry direct ST information, its accurate modeling is critical for evaluating sensing performance, especially in complex environments. Existing communication standards characterize propagation between separated transmitter (Tx) and receiver (Rx). However, modeling background channels in the ISAC monostatic mode, where the Tx and Rx are co-located, remains a pressing challenge. In this paper, we firstly conduct ISAC monostatic background channel measurements for an indoor scenario at 28 GHz. Realistic channel parameters are extracted, revealing pronounced single-hop propagation and discrete multipath distribution. Inspired by these properties, a novel stochastic model is proposed to characterizing the ISAC monostatic background channel as the superposition of sub-channels between the monostatic Tx&Rx and multiple communication Rx-like Reference Points (RPs). This model is compatible with standardizations, and a 3GPP-extended implementation framework is introduced. Finally, a genetic algorithm-based method is proposed to extract the optimal number and placement of multi-RPs. The optimization approach and modeling framework are validated by comparing measured and simulated channel parameters. Results demonstrate that the proposed model effectively captures monostatic background channel characteristics, addresses a critical gap in ISAC channel modeling, and supports 6G standardization.

eess.SP↗
arXiv2025

Multi-Target Flexible Angular Emulation for ISAC Base Station Testing Using a Conductive Amplitude and Phase Matrix Setup: Framework and Experimental Validation

Comprehensive evaluation of the functionalities, algorithms, hardware components, and performance characteristics of future integrated sensing and communication (ISAC) base stations (BSs) under realistic deployment scenarios in controlled laboratory environments represents a critical requirement for ISAC technology advancement. A primary challenge in achieving this objective involves the emulation of multiple targets with arbitrary radar cross-section (RCS), range, angle, and Doppler profiles for ISAC BS equipped with large-scale antenna arrays using radar target simulator (RTS) with limited interface ports. In this work, we introduce a simple yet highly effective and practical conductive amplitude and phase matrix framework to address this fundamental challenge. The core concept involves introducing a tunable conductive amplitude and phase modulation network in the test configuration between the ISAC BS under test and a RTS. Based on this structure, we subsequently investigate the corresponding configurations for different sensing operational modes of ISAC BSs, specifically the array duplex transmission and reception (ADTR) mode and the split-array transmission and reception (SATR) mode. For experimental validation, we design two distinct monostatic sensing scenarios to demonstrate the framework capabilities across both operational modes. The first scenario involves dynamic multi-drone sensing validation for ADTR mode operation, while the second scenario addresses static single-drone sensing for SATR mode validation. The experimental results demonstrate that the proposed framework can accurately emulate the joint RCS, range, velocity, and angular characteristics of multiple sensing targets within the conductive test environment, highlighting its significant potential for testing applications in sub-6 GHz ISAC BS development and validation.

eess.SP↗
arXiv2025

6G Channel Modeling: Requirement, Measurement, Methodology and Simulator

Sixth-generation (6G) mobile communications have attracted substantial attention in the global research community of information and communication technologies (ICTs). 6G systems are expected to support not only extended 5G usage scenarios but also new usage scenarios, such as integrated sensing and communication (ISAC), integrated artificial intelligence (AI) and communication, and communication and ubiquitous connectivity. To achieve this goal, channel characteristics must be comprehensively studied and properly exploited to promote the design, standardization, and optimization of 6G systems. In this paper, we first summarize the requirements and challenges in 6G channel research. Our focus is on channels for six promising technologies enabling 6G, including ISAC, extremely large-scale MIMO (XL-MIMO), mid-band and terahertz (THz) technologies, reconfigurable intelligent surfaces (RISs), and space-air-ground integrated networks (SAGINs). A survey of the progress in 6G channel research regarding the above six promising technologies is presented in terms of the latest measurement campaigns, new characteristics, modeling methods, and research prospects. To support testing, optimization and evaluation, existing 6G channel simulators are summarized. Then, BUPTCMCCCMG-IMT2030 is introduced as an example of a simulator that was developed on the basis of the ITU/3GPP 3D geometry-based stochastic model (GBSM) methodology. We also address open issues covering standardization activities, AI-enabled methods, and system performance analysis in the context of 6G channel research. This paper offers in-depth, hands-on insights into the best practices of channel measurements, modeling, and simulations for the evaluation of 6G technologies, the development of 6G standards, and the implementation and optimization of 6G systems.

eess.SP↗