arXiv subjects

Pu Wang

Publications and source records attributed to Pu Wang.

At least 55 records · Page 3Linked to original sources

arXiv2025

mmCooper: A Multi-agent Multi-stage Communication-efficient and Collaboration-robust Cooperative Perception Framework

Collaborative perception significantly enhances individual vehicle perception performance through the exchange of sensory information among agents. However, real-world deployment faces challenges due to bandwidth constraints and inevitable calibration errors during information exchange. To address these issues, we propose mmCooper, a novel multi-agent, multi-stage, communication-efficient, and collaboration-robust cooperative perception framework. Our framework leverages a multi-stage collaboration strategy that dynamically and adaptively balances intermediate- and late-stage information to share among agents, enhancing perceptual performance while maintaining communication efficiency. To support robust collaboration despite potential misalignments and calibration errors, our framework prevents misleading low-confidence sensing information from transmission and refines the received detection results from collaborators to improve accuracy. The extensive evaluation results on both real-world and simulated datasets demonstrate the effectiveness of the mmCooper framework and its components.

cs.CV↗

arXiv2025

LiDAR Remote Sensing Meets Weak Supervision: Concepts, Methods, and Perspectives

Light detection and ranging (LiDAR) remote sensing encompasses two major directions: data interpretation and parameter inversion. However, both directions rely heavily on costly and labor-intensive labeled data and field measurements, which constrains their scalability and spatiotemporal adaptability. Weakly Supervised Learning (WSL) provides a unified framework to address these limitations. This paper departs from the traditional view that treats interpretation and inversion as separate tasks and offers a systematic review of recent advances in LiDAR remote sensing from a unified WSL perspective. We cover typical WSL settings including incomplete supervision(e.g., sparse point labels), inexact supervision (e.g., scene-level tags), inaccurate supervision (e.g., noisy labels), and cross-domain supervision (e.g., domain adaptation/generalization) and corresponding techniques such as pseudo-labeling, consistency regularization, self-training, and label refinement, which collectively enable robust learning from limited and weak annotations.We further analyze LiDAR-specific challenges (e.g., irregular geometry, data sparsity, domain heterogeneity) that require tailored weak supervision, and examine how sparse LiDAR observations can guide joint learning with other remote-sensing data for continuous surface-parameter retrieval. Finally, we highlight future directions where WSL acts as a bridge between LiDAR and foundation models to leverage large-scale multimodal datasets and reduce labeling costs, while also enabling broader WSL-driven advances in generalization, open-world adaptation, and scalable LiDAR remote sensing.

cs.CV↗

arXiv2025

How to Auto-optimize Prompts for Domain Tasks? Adaptive Prompting and Reasoning through Evolutionary Domain Knowledge Adaptation

Designing optimal prompts and reasoning processes for large language models (LLMs) on domain-specific tasks is both necessary and challenging in real-world applications. Determining how to integrate domain knowledge, enhance reasoning efficiency, and even provide domain experts with refined knowledge integration hints are particularly crucial yet unresolved tasks. In this research, we propose Evolutionary Graph Optimization for Prompting (EGO-Prompt), an automated framework to designing better prompts, efficient reasoning processes and providing enhanced causal-informed process. EGO-Prompt begins with a general prompt and fault-tolerant initial Semantic Causal Graph (SCG) descriptions, constructed by human experts, which is then automatically refined and optimized to guide LLM reasoning. Recognizing that expert-defined SCGs may be partial or imperfect and that their optimal integration varies across LLMs, EGO-Prompt integrates a novel causal-guided textual gradient process in two steps: first, generating nearly deterministic reasoning guidance from the SCG for each instance, and second, adapting the LLM to effectively utilize the guidance alongside the original input. The iterative optimization algorithm further refines both the SCG and the reasoning mechanism using textual gradients with ground-truth. We tested the framework on real-world public health, transportation and human behavior tasks. EGO-Prompt achieves 7.32%-12.61% higher F1 than cutting-edge methods, and allows small models to reach the performence of larger models at under 20% of the original cost. It also outputs a refined, domain-specific SCG that improves interpretability.

cs.AI↗

arXiv2025

Towards Physics-informed Spatial Intelligence with Human Priors: An Autonomous Driving Pilot Study

How to integrate and verify spatial intelligence in foundation models remains an open challenge. Current practice often proxies Visual-Spatial Intelligence (VSI) with purely textual prompts and VQA-style scoring, which obscures geometry, invites linguistic shortcuts, and weakens attribution to genuinely spatial skills. We introduce Spatial Intelligence Grid (SIG): a structured, grid-based schema that explicitly encodes object layouts, inter-object relations, and physically grounded priors. As a complementary channel to text, SIG provides a faithful, compositional representation of scene structure for foundation-model reasoning. Building on SIG, we derive SIG-informed evaluation metrics that quantify a model's intrinsic VSI, which separates spatial capability from language priors. In few-shot in-context learning with state-of-the-art multimodal LLMs (e.g. GPT- and Gemini-family models), SIG yields consistently larger, more stable, and more comprehensive gains across all VSI metrics compared to VQA-only representations, indicating its promise as a data-labeling and training schema for learning VSI. We also release SIGBench, a benchmark of 1.4K driving frames annotated with ground-truth SIG labels and human gaze traces, supporting both grid-based machine VSI tasks and attention-driven, human-like VSI tasks in autonomous-driving scenarios.

cs.CV↗

arXiv2025

MaskControl: Spatio-Temporal Control for Masked Motion Synthesis

Recent advances in motion diffusion models have enabled spatially controllable text-to-motion generation. However, these models struggle to achieve high-precision control while maintaining high-quality motion generation. To address these challenges, we propose MaskControl, the first approach to introduce controllability to the generative masked motion model. Our approach introduces two key innovations. First, \textit{Logits Regularizer} implicitly perturbs logits at training time to align the distribution of motion tokens with the controlled joint positions, while regularizing the categorical token prediction to ensure high-fidelity generation. Second, \textit{Logit Optimization} explicitly optimizes the predicted logits during inference time, directly reshaping the token distribution that forces the generated motion to accurately align with the controlled joint positions. Moreover, we introduce \textit{Differentiable Expectation Sampling (DES)} to combat the non-differential distribution sampling process encountered by logits regularizer and optimization. Extensive experiments demonstrate that MaskControl outperforms state-of-the-art methods, achieving superior motion quality (FID decreases by ~77\%) and higher control precision (average error 0.91 vs. 1.08). Additionally, MaskControl enables diverse applications, including any-joint-any-frame control, body-part timeline control, and zero-shot objective control. Video visualization can be found at https://www.ekkasit.com/ControlMM-page/

cs.CV↗

arXiv2025

A PDE-Based Image Dehazing Method via Atmospheric Scattering Theory

This paper introduces a novel partial differential equation (PDE) framework for single-image dehazing. We embed the atmospheric scattering model into a PDE featuring edge-preserving diffusion and a nonlocal operator to maintain both local details and global structures. A key innovation is an adaptive regularization mechanism guided by the dark channel prior, which adjusts smoothing strength based on haze density. The framework's mathematical well-posedness is rigorously established by proving the existence and uniqueness of its weak solution in $H_0^1(Ω)$. An efficient, GPU-accelerated fixed-point solver is used for implementation. Experiments confirm our method achieves effective haze removal while preserving high image fidelity, offering a principled alternative to purely data-driven techniques.

cs.CV↗

arXiv2025

SSVD: Structured SVD for Parameter-Efficient Fine-Tuning and Benchmarking under Domain Shift in ASR

Parameter-efficient fine-tuning (PEFT) has emerged as a scalable solution for adapting large foundation models. While low-rank adaptation (LoRA) is widely used in speech applications, its state-of-the-art variants, e.g., VeRA, DoRA, PiSSA, and SVFT, are developed mainly for language and vision tasks, with limited validation in speech. This work presents the first comprehensive integration and benchmarking of these PEFT methods within ESPnet. We further introduce structured SVD-guided (SSVD) fine-tuning, which selectively rotates input-associated right singular vectors while keeping output-associated vectors fixed to preserve semantic mappings. This design enables robust domain adaptation with minimal trainable parameters and improved efficiency. We evaluate all methods on domain-shifted speech recognition tasks, including child speech and dialectal variation, across model scales from 0.1B to 2B. All implementations are released in ESPnet to support reproducibility and future work.

cs.CL↗

arXiv2025

Benchmarking Training Paradigms, Dataset Composition, and Model Scaling for Child ASR in ESPnet

Despite advancements in ASR, child speech recognition remains challenging due to acoustic variability and limited annotated data. While fine-tuning adult ASR models on child speech is common, comparisons with flat-start training remain underexplored. We compare flat-start training across multiple datasets, SSL representations (WavLM, XEUS), and decoder architectures. Our results show that SSL representations are biased toward adult speech, with flat-start training on child speech mitigating these biases. We also analyze model scaling, finding consistent improvements up to 1B parameters, beyond which performance plateaus. Additionally, age-related ASR and speaker verification analysis highlights the limitations of proprietary models like Whisper, emphasizing the need for open-data models for reliable child speech research. All investigations are conducted using ESPnet, and our publicly available benchmark provides insights into training strategies for robust child speech processing.

cs.LG↗

arXiv2025

DiffMesh: A Motion-aware Diffusion Framework for Human Mesh Recovery from Videos

Human mesh recovery (HMR) provides rich human body information for various real-world applications. While image-based HMR methods have achieved impressive results, they often struggle to recover humans in dynamic scenarios, leading to temporal inconsistencies and non-smooth 3D motion predictions due to the absence of human motion. In contrast, video-based approaches leverage temporal information to mitigate this issue. In this paper, we present DiffMesh, an innovative motion-aware Diffusion-like framework for video-based HMR. DiffMesh establishes a bridge between diffusion models and human motion, efficiently generating accurate and smooth output mesh sequences by incorporating human motion within the forward process and reverse process in the diffusion model. Extensive experiments are conducted on the widely used datasets (Human3.6M \cite{h36m_pami} and 3DPW \cite{pw3d2018}), which demonstrate the effectiveness and efficiency of our DiffMesh. Visual comparisons in real-world scenarios further highlight DiffMesh's suitability for practical applications.

cs.CV↗

arXiv2025

Continuous-variable quantum key distribution over 50.4 km fiber using integrated silicon photonic transmitter and receiver

Quantum key distribution (QKD) is the fastest-growing and relatively mature technology in the field of quantum information, enabling information-theoretically secure key distribution between two remote users. Although QKD based on off-the-shelf telecom components has been validated in both laboratory and field tests, its high cost and large volume remain major obstacles to large-scale deployment. Photonic integration, featured by its compact size and low cost, offers an effective approach to addressing the above challenges faced by QKD. Here, we implement a high-performance, integrated local local oscillator continuous-variable (CV) QKD system based on an integrated silicon photonic transmitter and receiver. By employing a high-speed silicon photonic integrated in-phase and quadrature modulator, a low-noise and high bandwidth silicon photonic integrated heterodyne detector, and digital signal processing, our CV-QKD system achieves a symbol rate of up to 1.5625 GBaud. Furthermore, the system achieves asymptotic secret key rates of 31.05 and 5.05 Mbps over 25.8 and 50.4 km standard single-mode fiber, respectively, using an 8-phase-shift keying discrete modulation. Our integrated CV-QKD system with high symbol rate and long transmission distance pays the way for the quantum secure communication network at metropolitan area.

quant-ph↗

arXiv2025

Synthetic Tabular Data Generation: A Comparative Survey for Modern Techniques

As privacy regulations become more stringent and access to real-world data becomes increasingly constrained, synthetic data generation has emerged as a vital solution, especially for tabular datasets, which are central to domains like finance, healthcare and the social sciences. This survey presents a comprehensive and focused review of recent advances in synthetic tabular data generation, emphasizing methods that preserve complex feature relationships, maintain statistical fidelity, and satisfy privacy requirements. A key contribution of this work is the introduction of a novel taxonomy based on practical generation objectives, including intended downstream applications, privacy guarantees, and data utility, directly informing methodological design and evaluation strategies. Therefore, this review prioritizes the actionable goals that drive synthetic data creation, including conditional generation and risk-sensitive modeling. Additionally, the survey proposes a benchmark framework to align technical innovation with real-world demands. By bridging theoretical foundations with practical deployment, this work serves as both a roadmap for future research and a guide for implementing synthetic tabular data in privacy-critical environments.

cs.LG↗

arXiv2025

Towards Reliable and Interpretable Traffic Crash Pattern Prediction and Safety Interventions Using Customized Large Language Models

Predicting crash events is crucial for understanding crash distributions and their contributing factors, thereby enabling the design of proactive traffic safety policy interventions. However, existing methods struggle to interpret the complex interplay among various sources of traffic crash data, including numeric characteristics, textual reports, crash imagery, environmental conditions, and driver behavior records. As a result, they often fail to capture the rich semantic information and intricate interrelationships embedded in these diverse data sources, limiting their ability to identify critical crash risk factors. In this research, we propose TrafficSafe, a framework that adapts LLMs to reframe crash prediction and feature attribution as text-based reasoning. A multi-modal crash dataset including 58,903 real-world reports together with belonged infrastructure, environmental, driver, and vehicle information is collected and textualized into TrafficSafe Event Dataset. By customizing and fine-tuning LLMs on this dataset, the TrafficSafe LLM achieves a 42% average improvement in F1-score over baselines. To interpret these predictions and uncover contributing factors, we introduce TrafficSafe Attribution, a sentence-level feature attribution framework enabling conditional risk analysis. Findings show that alcohol-impaired driving is the leading factor in severe crashes, with aggressive and impairment-related behaviors having nearly twice the contribution for severe crashes compared to other driver behaviors. Furthermore, TrafficSafe Attribution highlights pivotal features during model training, guiding strategic crash data collection for iterative performance improvements. The proposed TrafficSafe offers a transformative leap in traffic safety research, providing a blueprint for translating advanced AI technologies into responsible, actionable, and life-saving outcomes.

cs.CL↗

arXiv2025

UHD Image Dehazing via anDehazeFormer with Atmospheric-aware KV Cache

In this paper, we propose an efficient visual transformer framework for ultra-high-definition (UHD) image dehazing that addresses the key challenges of slow training speed and high memory consumption for existing methods. Our approach introduces two key innovations: 1) an \textbf{a}daptive \textbf{n}ormalization mechanism inspired by the nGPT architecture that enables ultra-fast and stable training with a network with a restricted range of parameter expressions; and 2) we devise an atmospheric scattering-aware KV caching mechanism that dynamically optimizes feature preservation based on the physical haze formation model. The proposed architecture improves the training convergence speed by \textbf{5 $\times$} while reducing memory overhead, enabling real-time processing of 50 high-resolution images per second on an RTX4090 GPU. Experimental results show that our approach maintains state-of-the-art dehazing quality while significantly improving computational efficiency for 4K/8K image restoration tasks. Furthermore, we provide a new dehazing image interpretable method with the help of an integrated gradient attribution map. Our code can be found here: https://anonymous.4open.science/r/anDehazeFormer-632E/README.md.

cs.CV↗

arXiv2025

AgentPolyp: Accurate Polyp Segmentation via Image Enhancement Agent

Since human and environmental factors interfere, captured polyp images usually suffer from issues such as dim lighting, blur, and overexposure, which pose challenges for downstream polyp segmentation tasks. To address the challenges of noise-induced degradation in polyp images, we present AgentPolyp, a novel framework integrating CLIP-based semantic guidance and dynamic image enhancement with a lightweight neural network for segmentation. The agent first evaluates image quality using CLIP-driven semantic analysis (e.g., identifying ``low-contrast polyps with vascular textures") and adapts reinforcement learning strategies to dynamically apply multi-modal enhancement operations (e.g., denoising, contrast adjustment). A quality assessment feedback loop optimizes pixel-level enhancement and segmentation focus in a collaborative manner, ensuring robust preprocessing before neural network segmentation. This modular architecture supports plug-and-play extensions for various enhancement algorithms and segmentation networks, meeting deployment requirements for endoscopic devices.

eess.IV↗

arXiv2025

UAKNN: Label Distribution Learning via Uncertainty-Aware KNN

Label Distribution Learning (LDL) aims to characterize the polysemy of an instance by building a set of descriptive degrees corresponding to the instance. In recent years, researchers seek to model to obtain an accurate label distribution by using low-rank, label relations, expert experiences, and label uncertainty estimation. In general, these methods are based on algorithms with parameter learning in a linear (including kernel functions) or deep learning framework. However, these methods are difficult to deploy and update online due to high training costs, limited scalability, and outlier sensitivity. To address this problem, we design a novel LDL method called UAKNN, which has the advantages of the KNN algorithm with the benefits of uncertainty modeling. In addition, we provide solutions to the dilemma of existing work on extremely label distribution spaces. Extensive experiments demonstrate that our method is significantly competitive on 12 benchmarks and that the inference speed of the model is well-suited for industrial-level applications.

cs.LG↗

arXiv2025

LLAVIDAL: A Large LAnguage VIsion Model for Daily Activities of Living

Current Large Language Vision Models (LLVMs) trained on web videos perform well in general video understanding but struggle with fine-grained details, complex human-object interactions (HOI), and view-invariant representation learning essential for Activities of Daily Living (ADL). This limitation stems from a lack of specialized ADL video instruction-tuning datasets and insufficient modality integration to capture discriminative action representations. To address this, we propose a semi-automated framework for curating ADL datasets, creating ADL-X, a multiview, multimodal RGBS instruction-tuning dataset. Additionally, we introduce LLAVIDAL, an LLVM integrating videos, 3D skeletons, and HOIs to model ADL's complex spatiotemporal relationships. For training LLAVIDAL a simple joint alignment of all modalities yields suboptimal results; thus, we propose a Multimodal Progressive (MMPro) training strategy, incorporating modalities in stages following a curriculum. We also establish ADL MCQ and video description benchmarks to assess LLVM performance in ADL tasks. Trained on ADL-X, LLAVIDAL achieves state-of-the-art performance across ADL benchmarks. Code and data will be made publicly available at: https://adl-x.github.io/.

cs.CV↗

arXiv2025

MaskHand: Generative Masked Modeling for Robust Hand Mesh Reconstruction in the Wild

Reconstructing a 3D hand mesh from a single RGB image is challenging due to complex articulations, self-occlusions, and depth ambiguities. Traditional discriminative methods, which learn a deterministic mapping from a 2D image to a single 3D mesh, often struggle with the inherent ambiguities in 2D-to-3D mapping. To address this challenge, we propose MaskHand, a novel generative masked model for hand mesh recovery that synthesizes plausible 3D hand meshes by learning and sampling from the probabilistic distribution of the ambiguous 2D-to-3D mapping process. MaskHand consists of two key components: (1) a VQ-MANO, which encodes 3D hand articulations as discrete pose tokens in a latent space, and (2) a Context-Guided Masked Transformer that randomly masks out pose tokens and learns their joint distribution, conditioned on corrupted token sequence, image context, and 2D pose cues. This learned distribution facilitates confidence-guided sampling during inference, producing mesh reconstructions with low uncertainty and high precision. Extensive evaluations on benchmark and real-world datasets demonstrate that MaskHand achieves state-of-the-art accuracy, robustness, and realism in 3D hand mesh reconstruction. Project website: https://m-usamasaleem.github.io/publication/MaskHand/MaskHand.html.

cs.CV↗

arXiv2025

Machine Learning for Detecting Steering in Qutrit-Pair States

Only a few states in high-dimensional systems can be identified as (un)steerable using existing theoretical or experimental methods. We utilize semidefinite programming (SDP) to construct a dataset for steerability detection in qutrit-qutrit systems. For the full-information feature $F_1$, artificial neural networks achieve high classification accuracy and generalization, and preform better than the support vector machine. As feature engineering playing a pivotal role, we introduce a steering ellipsoid-like feature $F_2$, which significantly enhances the performance of each of our models. Given the SDP method provides only a sufficient condition for steerability detection, we establish the first rigorously constructed, accurately labeled dataset based on theoretical foundations. This dataset enables models to exhibit outstanding accuracy and generalization capabilities, independent of the choice of features. As applications, we investigate the steerability boundaries of isotropic states and partially entangled states, and find new steerable states. This work not only advances the application of machine learning for probing quantum steerability in high-dimensional systems but also deepens the theoretical understanding of quantum steerability itself.

quant-ph↗