arXiv subjects

Hao Jiang

Publications and source records attributed to Hao Jiang.

At least 145 records · Page 8Linked to original sources

arXiv2025

Joint Activity Detection and Channel Estimation For Fluid Antenna System Exploiting Geographical and Angular Information

The fluid antenna system (FAS) refers to a family of reconfigurable antenna technologies that provide substantial spatial gains within a compact, predefined small space, thereby offering extensive degrees of freedom in the physical layer for future communication networks. The acquisition of channel state information (CSI) is critical, as it determines the placement of ports/antennas, which directly impacts FAS-based optimization. Although various channel estimation methods have been developed, significant flaws persist. For instance, the performance of greedy-based algorithms is heavily influenced by signal assumptions, and current model-free methods are infeasible due to prohibitively high computational complexity issue. Consequently, there is a pressing need for a well-balanced solution that exhibits flexibility, feasibility, and low complexity to support massive connectivity in FAS. In this work, we propose methods based on approximate message passing (AMP) integrated with adaptive expectation maximization (EM). The EM-AMP framework uniquely enables efficient large matrix computations with adaptive learning capabilities, independent of prior knowledge of the model or parameters within potential distributions, making it a robust candidate for FAS networks. We introduce two variants of the EM-AMP framework that leverage geographical and angular features in a FAS network. These proposed algorithms demonstrate improved estimation precision, fast convergence, and low computational complexity in large activity regions. Additionally, we analytically elucidate the reasons behind the inherent performance floor of greedy-based methods and highlight the critical role of angular information in algorithm design. Extensive numerical results validate the promising efficacy of the proposed algorithm designs and the derived analytical findings.

cs.IT↗

arXiv2025

Finite-blocklength Fluid Antenna Systems With Spatial Block-Correlation Channel Model

Massive connectivity with ultra-low latency and high reliability necessitates fundamental advances in future communication networks operating under finite-blocklength (FBL) transmission. Fluid antenna systems (FAS) have emerged as a promising enabler, offering superior spectrum and energy efficiency in short-packet/FBL scenarios. In this work, by leveraging the simplicity and accuracy of block-correlation channel modeling, we rigorously bound the performance limits of FBL-FAS from a statistical perspective, focusing on two key performance metrics: block error rate (BLER) and outage probability (OP). Furthermore, we introduce a novel complex-integral simplification method based on Gauss-Laguerre quadrature, which achieves higher approximation accuracy compared to existing Taylor-expansion-based approaches. Numerical results validate the robustness of the proposed analysis and clearly demonstrate the superiority of FBL-FAS over conventional multiple-antenna systems with fixed antenna placement.

cs.IT↗

arXiv2025

Segmented Waveguide-Enabled Pinching-Antenna Systems (SWANs) for ISAC

A segmented waveguide-enabled pinching-antenna system (SWAN)-assisted integrated sensing and communications (ISAC) framework is proposed. Unlike conventional pinching antenna systems (PASS), which use a single long waveguide, SWAN divides the waveguide into multiple short segments, each with a dedicated feed point. Thanks to the segmented structure, SWAN enhances sensing performance by significantly simplifying the reception model and reducing the in-waveguide propagation loss. To balance performance and complexity, three segment controlling protocols are proposed for the transceivers, namely i) \emph{segment selection} to select a single segment for signal transceiving, ii) \emph{segment aggregation} to aggregate signals from all segments using a single RF chain, and iii) \emph{segment multiplexing} to jointly process the signals from all segments using individual RF chains. The theoretical sensing performance limit is first analyzed for different protocols, unveiling how the sensing performance gain of SWAN scales with the number of segments. Based on this performance limit, the Pareto fronts of sensing and communication performance are characterized for the simple one-user one-target case, which is then extended to the general multi-user single-target case based on time-division multiple access (TDMA). Numerical results are presented to verify the correctness of the derivations and the effectiveness of the proposed algorithms, which jointly confirm the advantages of SWAN-assisted ISAC.

eess.SP↗

arXiv2025

CMMCoT: Enhancing Complex Multi-Image Comprehension via Multi-Modal Chain-of-Thought and Memory Augmentation

While previous multimodal slow-thinking methods have demonstrated remarkable success in single-image understanding scenarios, their effectiveness becomes fundamentally constrained when extended to more complex multi-image comprehension tasks. This limitation stems from their predominant reliance on text-based intermediate reasoning processes. While for human, when engaging in sophisticated multi-image analysis, they typically perform two complementary cognitive operations: (1) continuous cross-image visual comparison through region-of-interest matching, and (2) dynamic memorization of critical visual concepts throughout the reasoning chain. Motivated by these observations, we propose the Complex Multi-Modal Chain-of-Thought (CMMCoT) framework, a multi-step reasoning framework that mimics human-like "slow thinking" for multi-image understanding. Our approach incorporates two key innovations: (1) The construction of interleaved multimodal multi-step reasoning chains, which utilize critical visual region tokens, extracted from intermediate reasoning steps, as supervisory signals. This mechanism not only facilitates comprehensive cross-modal understanding but also enhances model interpretability. (2) The introduction of a test-time memory augmentation module that expands the model's reasoning capacity during inference while preserving parameter efficiency. Furthermore, to facilitate research in this direction, we have curated a novel multi-image slow-thinking dataset. Extensive experiments demonstrate the effectiveness of our model. Code is available at https://github.com/zhangguanghao523/CMMCoT.

cs.CV↗

arXiv2025

Does Hearing Help Seeing? Investigating Audio-Video Joint Denoising for Video Generation

Recent audio-video generative systems suggest that coupling modalities benefits not only audio-video synchrony but also the video modality itself. We pose a fundamental question: Does audio-video joint denoising training improve video generation, even when we only care about video quality? To study this, we introduce a parameter-efficient Audio-Video Full DiT (AVFullDiT) architecture that leverages pre-trained text-to-video (T2V) and text-to-audio (T2A) modules for joint denoising. We train (i) a T2AV model with AVFullDiT and (ii) a T2V-only counterpart under identical settings. Our results provide the first systematic evidence that audio-video joint denoising can deliver more than synchrony. We observe consistent improvements on challenging subsets featuring large and object contact motions. We hypothesize that predicting audio acts as a privileged signal, encouraging the model to internalize causal relationships between visual events and their acoustic consequences (e.g., collision $\times$ impact sound), which in turn regularizes video dynamics. Our findings suggest that cross-modal co-training is a promising approach to developing stronger, more physically grounded world models. Code and dataset will be made publicly available.

cs.CV↗

arXiv2025

Fluid Antenna-Enhanced Flexible Beamforming

Fluid antenna systems encompass a broad class of reconfigurable antenna technologies that offer substantial spatial diversity for various optimization objectives and communication tasks. Their capability to enhance spatial resolution within a fixed physical aperture makes fluid antennas particularly attractive for next-generation wireless deployments. In this work, we focus on the beamforming problem using a two-dimensional planar fluid antenna array. Since both narrow-beam and broad-beam patterns are essential in practical communication networks, enabling flexible beamforming through fluid antennas becomes an important and interesting research direction. We establish a unified and flexible framework that connects arbitrary beam-pattern synthesis with fluid-antenna port selection. The resulting formulation transforms beam-pattern reconstruction into a sparse regression problem, which is addressed using a tailored compressive sensing algorithm designed to operate efficiently with the fast Fourier transform (FFT). Furthermore, to ensure physically consistent phase modeling in the desired beam, we introduce an iterative FFT-based phase retrieval method. Owing to its structure, the proposed phase-refinement procedure exhibits low computational complexity and rapid convergence, requiring only one FFT and one inverse FFT per iteration. Simulation results demonstrate the effectiveness of the proposed flexible beamforming framework. Compared with conventional fixed-array architectures, fluid antennas exhibit significantly improved beam-pattern reconstruction accuracy, highlighting their potential for high-resolution and adaptive beamforming in future wireless systems.

cs.IT↗

arXiv2025

Data Valuation by Fusing Global and Local Statistical Information

Data valuation has garnered increasing attention in recent years, given the critical role of high-quality data in various applications. Among diverse data valuation approaches, Shapley value-based methods are predominant due to their strong theoretical grounding. However, the exact computation of Shapley values is often computationally prohibitive, prompting the development of numerous approximation techniques. Despite notable advancements, existing methods generally neglect the incorporation of value distribution information and fail to account for dynamic data conditions, thereby compromising their performance and application potential. In this paper, we highlight the crucial role of both global and local statistical properties of value distributions in the context of data valuation for machine learning. First, we conduct a comprehensive analysis of these distributions across various simulated and real-world datasets, uncovering valuable insights and key patterns. Second, we propose an enhanced data valuation method that fuses the explored distribution characteristics into two regularization terms to refine Shapley value estimation. The proposed regularizers can be seamlessly incorporated into various existing data valuation methods. Third, we introduce a novel approach for dynamic data valuation that infers updated data values without recomputing Shapley values, thereby significantly improving computational efficiency. Extensive experiments have been conducted across a range of tasks, including Shapley value estimation, value-based data addition and removal, mislabeled data detection, and dynamic data valuation. The results showcase the consistent effectiveness and efficiency of our proposed methodologies, affirming the significant potential of global and local value distributions in data valuation.

cs.LG↗

arXiv2025

SD-MVS: Segmentation-Driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization

In this paper, we introduce Segmentation-Driven Deformation Multi-View Stereo (SD-MVS), a method that can effectively tackle challenges in 3D reconstruction of textureless areas. We are the first to adopt the Segment Anything Model (SAM) to distinguish semantic instances in scenes and further leverage these constraints for pixelwise patch deformation on both matching cost and propagation. Concurrently, we propose a unique refinement strategy that combines spherical coordinates and gradient descent on normals and pixelwise search interval on depths, significantly improving the completeness of reconstructed 3D model. Furthermore, we adopt the Expectation-Maximization (EM) algorithm to alternately optimize the aggregate matching cost and hyperparameters, effectively mitigating the problem of parameters being excessively dependent on empirical tuning. Evaluations on the ETH3D high-resolution multi-view stereo benchmark and the Tanks and Temples dataset demonstrate that our method can achieve state-of-the-art results with less time consumption.

cs.CV↗

arXiv2025

A Universal Block Error Rate Bound for Fluid Antenna Systems

Fluid antenna systems (FASs) offer genuine simplicity for communication network design by eliminating expensive hardware overhead and reducing the complexity of access protocol architectures. Through the discovery of significant spatial diversity within a compact antenna space, FASs enable the implementation of reconfigurable-antenna-based architectures. However, current state-of-the-art studies rarely investigate the impact of finite blocklength constraints on FAS-based designs, leaving a gap in both analytical modeling and the establishment of a solid, universally applicable performance metric for finite blocklength fluid antenna systems (FBL-FAS). In this work, we focus on the study of FBL-FAS and, more importantly, derive a block error rate (BLER) bound that serves as a general and practical performance benchmark across various FAS architectures. The proposed BLER bound is computable both with and without an explicit statistical model, meaning that the BLER performance can be characterized analytically or empirically under model-aware or model-free system scenarios. Moreover, when the statistical model is known, the analytical results derived from the proposed BLER bound exhibit strong alignment with the empirical findings, demonstrating the remarkable simplicity, accuracy, and universality of the proposed BLER bound.

cs.IT↗

arXiv2025

Conceptual Design of the Muonium-to-Antimuonium Conversion Experiment (MACE)

The spontaneous conversion of muonium to antimuonium is one of the interesting charged lepton flavor violation phenomena offering a sensitive probe of potential new physics and serving as a tool to constrain the parameter space beyond the Standard Model. The Muonium-to-Antimuonium Conversion Experiment (MACE) is designed to utilize a high-intensity muon beam, a Michel electron magnetic spectrometer, a positron transport system, and a positron detection system, to either discover or constrain this rare process with a conversion probability of $\mathcal{O}(10^{-13})$. This article presents an overview of the theoretical framework as well as a detailed description of the experimental design for the search for muonium-to-antimuonium conversion.

hep-ex↗

arXiv2025

LLM-Aligned Geographic Item Tokenization for Local-Life Recommendation

Recent advances in Large Language Models (LLMs) have enhanced text-based recommendation by enriching traditional ID-based methods with semantic generalization capabilities. Text-based methods typically encode item textual information via prompt design and generate discrete semantic IDs through item tokenization. However, in domain-specific tasks such as local-life services, simply injecting location information into prompts fails to capture fine-grained spatial characteristics and real-world distance awareness among items. To address this, we propose LGSID, an LLM-Aligned Geographic Item Tokenization Framework for Local-life Recommendation. This framework consists of two key components: (1) RL-based Geographic LLM Alignment, and (2) Hierarchical Geographic Item Tokenization. In the RL-based alignment module, we initially train a list-wise reward model to capture real-world spatial relationships among items. We then introduce a novel G-DPO algorithm that uses pre-trained reward model to inject generalized spatial knowledge and collaborative signals into LLMs while preserving their semantic understanding. Furthermore, we propose a hierarchical geographic item tokenization strategy, where primary tokens are derived from discrete spatial and content attributes, and residual tokens are refined using the aligned LLM's geographic representation vectors. Extensive experiments on real-world Kuaishou industry datasets show that LGSID consistently outperforms state-of-the-art discriminative and generative recommendation models. Ablation studies, visualizations, and case studies further validate its effectiveness.

cs.IR↗

arXiv2025

Neural Networks-Enabled Channel Reconstruction for Fluid Antenna Systems: A Data-Driven Approach

Fluid antenna systems (FASs) offer substantial spatial diversity by exploiting the electromagnetic port correlation within compact array spaces, thereby generating favorable small-scale fading conditions with beneficial channel gain envelope fluctuations. This unique capability opens new opportunities for a wide range of communication applications and emerging technologies. However, accurate channel state information (CSI) must be acquired before a fluid antenna can be effectively utilized. Although several efforts have been made toward channel reconstruction in FASs, a generally applicable solution to both model-based or model-free scenario with both high precision and efficient computational flow remains lacking. In this work, we propose a data-driven channel reconstruction approach enabled by neural networks. The proposed framework not only achieves significantly enhanced reconstruction accuracy but also requires substantially lower computational complexity compared with existing model-free methods. Numerical results further demonstrate the rapid convergence and robust reconstruction capability of the proposed scheme, outperforming current state-of-the-art techniques.

cs.IT↗

arXiv2025

Agentmandering: A Game-Theoretic Framework for Fair Redistricting via Large Language Model Agents

Redistricting plays a central role in shaping how votes are translated into political power. While existing computational methods primarily aim to generate large ensembles of legally valid districting plans, they often neglect the strategic dynamics involved in the selection process. This oversight creates opportunities for partisan actors to cherry-pick maps that, while technically compliant, are politically advantageous. Simply satisfying formal constraints does not ensure fairness when the selection process itself can be manipulated. We propose \textbf{Agentmandering}, a framework that reimagines redistricting as a turn-based negotiation between two agents representing opposing political interests. Drawing inspiration from game-theoretic ideas, particularly the \textit{Choose-and-Freeze} protocol, our method embeds strategic interaction into the redistricting process via large language model (LLM) agents. Agents alternate between selecting and freezing districts from a small set of candidate maps, gradually partitioning the state through constrained and interpretable choices. Evaluation on post-2020 U.S. Census data across all states shows that Agentmandering significantly reduces partisan bias and unfairness, while achieving 2 to 3 orders of magnitude lower variance than standard baselines. These results demonstrate both fairness and stability, especially in swing-state scenarios. Our code is available at https://github.com/Lihaogx/AgentMandering.

cs.AI↗

arXiv2025

Polymap: generating high definition map based on rasterized polygons

The perception of high-definition maps is an integral component of environmental perception in autonomous driving systems. Existing research have often focused on online construction of high-definition maps. For instance, the Maptr[9] series employ a detection-based method to output vectorized map instances parallelly in an end-to-end manner. However, despite their capability for real-time construction, detection-based methods are observed to lack robust generalizability[19], which hampers their applicability in auto-labeling systems. Therefore, aiming to improve the generalizability, we reinterpret road elements as rasterized polygons and design a concise framework based on instance segmentation. Initially, a segmentation-based transformer is employed to deliver instance masks in an end-to-end manner; succeeding this step, a Potrace-based[17] post-processing module is used to ultimately yield vectorized map elements. Quantitative results attained on the Nuscene[1] dataset substantiate the effectiveness and generaliz-ability of our method.

cs.CV↗

arXiv2025

Introducing LongCat-Flash-Thinking: A Technical Report

We present LongCat-Flash-Thinking, an efficient 560-billion-parameter open-source Mixture-of-Experts (MoE) reasoning model. Its advanced capabilities are cultivated through a meticulously crafted training process, beginning with long Chain-of-Thought (CoT) data cold-start and culminating in large-scale Reinforcement Learning (RL). We first employ a well-designed cold-start training strategy, which significantly enhances the reasoning potential and equips the model with specialized skills in both formal and agentic reasoning. Then, a core innovation is our domain-parallel training scheme, which decouples optimization across distinct domains (e.g., STEM, Code, Agentic) and subsequently fuses the resulting expert models into a single, nearly Pareto-optimal model. This entire process is powered by our Dynamic ORchestration for Asynchronous rollout (DORA) system, a large-scale RL framework that delivers a greater than threefold training speedup over synchronous methods on tens of thousands of accelerators. As a result, LongCat-Flash-Thinking achieves state-of-the-art performance among open-source models on a suite of complex reasoning tasks. The model exhibits exceptional efficiency in agentic reasoning, reducing average token consumption by 64.5% (from 19, 653 to 6, 965) on AIME-25, without degrading task accuracy. We release LongCat-Flash-Thinking to promote further advances in reasoning systems and agentic AI research.

cs.AI↗

arXiv2025

DiffVLA++: Bridging Cognitive Reasoning and End-to-End Driving through Metric-Guided Alignment

Conventional end-to-end (E2E) driving models are effective at generating physically plausible trajectories, but often fail to generalize to long-tail scenarios due to the lack of essential world knowledge to understand and reason about surrounding environments. In contrast, Vision-Language-Action (VLA) models leverage world knowledge to handle challenging cases, but their limited 3D reasoning capability can lead to physically infeasible actions. In this work we introduce DiffVLA++, an enhanced autonomous driving framework that explicitly bridges cognitive reasoning and E2E planning through metric-guided alignment. First, we build a VLA module directly generating semantically grounded driving trajectories. Second, we design an E2E module with a dense trajectory vocabulary that ensures physical feasibility. Third, and most critically, we introduce a metric-guided trajectory scorer that guides and aligns the outputs of the VLA and E2E modules, thereby integrating their complementary strengths. The experiment on the ICCV 2025 Autonomous Grand Challenge leaderboard shows that DiffVLA++ achieves EPDMS of 49.12.

cs.RO↗

arXiv2025

Blind MIMO Semantic Communication via Parallel Variational Diffusion: A Completely Pilot-Free Approach

In this paper, we propose a novel blind multi-input multi-output (MIMO) semantic communication (SC) framework named Blind-MIMOSC that consists of a deep joint source-channel coding (DJSCC) transmitter and a diffusion-based blind receiver. The DJSCC transmitter aims to compress and map the source data into the transmitted signal by exploiting the structural characteristics of the source data, while the diffusion-based blind receiver employs a parallel variational diffusion (PVD) model to simultaneously recover the channel and the source data from the received signal without using any pilots. The PVD model leverages two pre-trained score networks to characterize the prior information of the channel and the source data, operating in a plug-and-play manner during inference. This design allows only the affected network to be retrained when channel conditions or source datasets change, avoiding the complicated full-network retraining required by end-to-end methods. This work presents the first fully pilot-free solution for joint channel estimation and source recovery in block-fading MIMO systems. Extensive experiments show that Blind-MIMOSC with PVD achieves superior channel and source recovery accuracy compared to state-of-the-art approaches, with drastically reduced channel bandwidth ratio.

eess.SP↗

arXiv2025

HAIF-GS: Hierarchical and Induced Flow-Guided Gaussian Splatting for Dynamic Scene

Reconstructing dynamic 3D scenes from monocular videos remains a fundamental challenge in 3D vision. While 3D Gaussian Splatting (3DGS) achieves real-time rendering in static settings, extending it to dynamic scenes is challenging due to the difficulty of learning structured and temporally consistent motion representations. This challenge often manifests as three limitations in existing methods: redundant Gaussian updates, insufficient motion supervision, and weak modeling of complex non-rigid deformations. These issues collectively hinder coherent and efficient dynamic reconstruction. To address these limitations, we propose HAIF-GS, a unified framework that enables structured and consistent dynamic modeling through sparse anchor-driven deformation. It first identifies motion-relevant regions via an Anchor Filter to suppress redundant updates in static areas. A self-supervised Induced Flow-Guided Deformation module induces anchor motion using multi-frame feature aggregation, eliminating the need for explicit flow labels. To further handle fine-grained deformations, a Hierarchical Anchor Propagation mechanism increases anchor resolution based on motion complexity and propagates multi-level transformations. Extensive experiments on synthetic and real-world benchmarks validate that HAIF-GS significantly outperforms prior dynamic 3DGS methods in rendering quality, temporal coherence, and reconstruction efficiency.

cs.CV↗