arXiv subjects

Kunpeng Wang

Publications and source records attributed to Kunpeng Wang.

At least 19 recordsLinked to original sources

arXiv2026

AV-SyncBench: Decoupled Benchmarking of Temporal and Semantic Audio-Visual Synchronization

Audio-visual feature extraction is a fundamental component of multimodal understanding and generation tasks. However, existing evaluation protocols for feature extraction models exhibit dimensional bias, typically focusing on either semantic matching or temporal offset detection. Moreover, their data construction remains coupled, preventing independent assessment of temporal and semantic consistency. We propose AV-SyncBench, the first benchmark to fully separate temporal and semantic evaluation for audio-visual synchronization. Built from in-the-wild videos, it spans Voice, Music, and Sound across 10 scenarios and 5 challenge tasks. Data are automatically filtered and manually verified to ensure on-screen sound sources. The benchmark contains 3,269 videos and 38,390 samples, and we evaluate five representative models to quantify feature quality for alignment and downstream tasks. The code and dataset are available at: https://fgt7t6g.github.io/AV-SyncBench.

cs.CV↗

arXiv2026

VoiceGiraffe: A Benchmark for Extreme Long-Context Audio-Language Understanding

While large audio language models (LALMs) have achieved remarkable progress in audio processing at the second- or minute-level scale, understanding hour-level audio remains a fundamental bottleneck. Existing benchmarks predominantly rely on short clips or artificially concatenated segments, failing to faithfully assess LALM capacity for long-range information comprehension in real-world scenarios such as podcasts and lengthy speeches. To address this gap, we introduce VoiceGiraffe, a novel benchmark designed to rigorously evaluate LALMs across diverse real-world scenarios, modalities, and languages under long-context settings. It comprises 1500 curated triplets structured into a dual-level taxonomy of single-hop perception and multi-hop reasoning. We evaluate a broad suite of open-source and proprietary LALMs against human performance. Results underscore three fundamental findings. First, VoiceGiraffe remains highly challenging and far from saturation. Second, we show that no single inference paradigm universally dominates. The E2E inference benefits models with native long-context audio understanding, cascaded caption aggregation stabilizes small models overwhelmed by hour-scale audio, and reasoning-enhanced cascading with external LLM helps weaker models but can bottleneck stronger proprietary systems. Third, we reveal long-range memory persistence as a key bottleneck. LALMs are better at answering questions that require connecting salient causal cues than those requiring sustained tracking of sparse events across long audio, whereas humans show the opposite pattern. These findings position VoiceGiraffe as a challenging and diagnostic testbed for long-form audio understanding, highlighting the need for LALMs with persistent memory and robust long-range aggregation.

cs.SD↗

arXiv2026

Governance of Technological Transition: A Predator-Prey Analysis of AI Capital in China's Economy and Its Policy Implications

The rapid integration of Artificial Intelligence (AI) into China's economy presents a classic governance challenge: how to harness its growth potential while managing its disruptive effects on traditional capital and labor markets. This study addresses this policy dilemma by modeling the dynamic interactions between AI capital, physical capital, and labor within a Lotka-Volterra predator-prey framework. Using annual Chinese data (2016-2023), we quantify the interaction strengths, identify stable equilibria, and perform a global sensitivity analysis. Our results reveal a consistent pattern where AI capital acts as the 'prey', stimulating both physical capital accumulation and labor compensation (wage bill), while facing only weak constraining feedback. The equilibrium points are stable nodes, indicating a policy-mediated convergence path rather than volatile cycles. Critically, the sensitivity analysis shows that the labor market equilibrium is overwhelmingly driven by AI-related parameters, whereas the physical capital equilibrium is also influenced by its own saturation dynamics. These findings provide a systemic, quantitative basis for policymakers: (1) to calibrate AI promotion policies by recognizing the asymmetric leverage points in capital vs. labor markets; (2) to anticipate and mitigate structural rigidities that may arise from current regulatory settings; and (3) to prioritize interventions that foster complementary growth between AI and traditional economic structures while ensuring broad-base distribution of technological gains.

econ.GN↗

arXiv2025

The Cobb-Douglas Production Function and the Old Bowley's Law

Bowley's law, also referred to as the law of the constant wage share, was a noteworthy empirical finding in economics, suggesting that a nation's wage share tended to remain stable over time, as observed through most of the 20th century. The wage share represents the proportion of a country's economic output that is distributed to employees as compensation for their labor, usually in the form of wages. The term ''Bowley's law'' was coined in 1964 by Paul Samuelson, the first American laureate of the Nobel memorial prize in economic sciences. He attributed this principle to Sir Arthur Bowley, an English economist, mathematician, and statistician. In this paper, we introduce a mathematical model derived from data for the American economy, originally employed by Cobb and Douglas in 1928 to validate the renowned Cobb-Douglas production function. We utilize symmetry methods, particularly those developed by Peter Olver, to elucidate the validity of Bowley's law within our model's framework. By employing these advanced mathematical techniques, our objective is to elucidate the factors contributing to the stability of the wage share over time. We demonstrate that the validity of both Bowley's law and the Cobb-Douglas production function arises from the robust growth of an economy, characterized by expansion in capital, labor, and production, which can be approximated by an exponential function. Through our analysis, we aim to offer valuable insights into the underlying mechanisms that support Bowley's law and its implications for comprehending income distribution patterns in economies.

math.DS↗

arXiv2025

3-D Magnetotelluric Deep Learning Inversion Guided by Pseudo-Physical Information

Magnetotelluric deep learning (DL) inversion methods based on joint data-driven and physics-driven have become a hot topic in recent years. When mapping observation data (or forward modeling data) to the resistivity model using neural networks (NNs), incorporating the error (loss) term of the inversion resistivity's forward modeling response--which introduces physical information about electromagnetic field propagation--can significantly enhance the inversion accuracy. To efficiently achieve data-physical dual-driven MT deep learning inversion for large-scale 3-D MT data, we propose using DL forward modeling networks to compute this portion of the loss. This approach introduces pseudo-physical information through the forward modeling of NN simulation, further guiding the inversion network fitting. Specifically, we first pre-train the forward modeling networks as fixed forward modeling operators, then transfer and integrate them into the inversion network training, and finally optimize the inversion network by minimizing the multinomial loss. Theoretical experimental results indicate that despite some simulation errors in DL forward modeling, the introduced pseudo-physical information still enhances inversion accuracy and significantly mitigates the overfitting problem during training. Additionally, we propose a new input mode that involves masking and adding noise to the data, simulating the field data environment of 3-D MT inversion, thereby making the method more flexible and effective for practical applications.

physics.geo-ph↗

arXiv2025

Mixture of Scale Experts for Alignment-free RGBT Video Object Detection and A Unified Benchmark

Existing RGB-Thermal Video Object Detection (RGBT VOD) methods predominantly rely on the manual alignment of image pairs, that is both labor-intensive and time-consuming. This dependency significantly restricts the scalability and practical applicability of these methods in real-world scenarios. To address this critical limitation, we propose a novel framework termed the Mixture of Scale Experts Network (MSENet). MSENet integrates multiple experts trained at different perceptual scales, enabling the capture of scale discrepancies between RGB and thermal image pairs without the need for explicit alignment. Specifically, to address the issue of unaligned scales, MSENet introduces a set of experts designed to perceive the correlation between RGBT image pairs across various scales. These experts are capable of identifying and quantifying the scale differences inherent in the image pairs. Subsequently, a dynamic routing mechanism is incorporated to assign adaptive weights to each expert, allowing the network to dynamically select the most appropriate experts based on the specific characteristics of the input data. Furthermore, to address the issue of weakly unaligned positions, we integrate deformable convolution into the network. Deformable convolution is employed to learn position displacements between the RGB and thermal modalities, thereby mitigating the impact of spatial misalignment. To provide a comprehensive evaluation platform for alignment-free RGBT VOD, we introduce a new benchmark dataset. This dataset includes eleven common object categories, with a total of 60,988 images and 271,835 object instances. The dataset encompasses a wide range of scenes from both daily life and natural environments, ensuring high content diversity and complexity.

cs.CV↗

arXiv2024

Alignment-Free RGB-T Salient Object Detection: A Large-scale Dataset and Progressive Correlation Network

Alignment-free RGB-Thermal (RGB-T) salient object detection (SOD) aims to achieve robust performance in complex scenes by directly leveraging the complementary information from unaligned visible-thermal image pairs, without requiring manual alignment. However, the labor-intensive process of collecting and annotating image pairs limits the scale of existing benchmarks, hindering the advancement of alignment-free RGB-T SOD. In this paper, we construct a large-scale and high-diversity unaligned RGB-T SOD dataset named UVT20K, comprising 20,000 image pairs, 407 scenes, and 1256 object categories. All samples are collected from real-world scenarios with various challenges, such as low illumination, image clutter, complex salient objects, and so on. To support the exploration for further research, each sample in UVT20K is annotated with a comprehensive set of ground truths, including saliency masks, scribbles, boundaries, and challenge attributes. In addition, we propose a Progressive Correlation Network (PCNet), which models inter- and intra-modal correlations on the basis of explicit alignment to achieve accurate predictions in unaligned image pairs. Extensive experiments conducted on unaligned and aligned datasets demonstrate the effectiveness of our method.Code and dataset are available at https://github.com/Angknpng/PCNet.

cs.CV↗

arXiv2024

Adapting Segment Anything Model to Multi-modal Salient Object Detection with Semantic Feature Fusion Guidance

Although most existing multi-modal salient object detection (SOD) methods demonstrate effectiveness through training models from scratch, the limited multi-modal data hinders these methods from reaching optimality. In this paper, we propose a novel framework to explore and exploit the powerful feature representation and zero-shot generalization ability of the pre-trained Segment Anything Model (SAM) for multi-modal SOD. Despite serving as a recent vision fundamental model, driving the class-agnostic SAM to comprehend and detect salient objects accurately is non-trivial, especially in challenging scenes. To this end, we develop \underline{SAM} with se\underline{m}antic f\underline{e}ature fu\underline{s}ion guidanc\underline{e} (Sammese), which incorporates multi-modal saliency-specific knowledge into SAM to adapt SAM to multi-modal SOD tasks. However, it is difficult for SAM trained on single-modal data to directly mine the complementary benefits of multi-modal inputs and comprehensively utilize them to achieve accurate saliency prediction. To address these issues, we first design a multi-modal complementary fusion module to extract robust multi-modal semantic features by integrating information from visible and thermal or depth image pairs. Then, we feed the extracted multi-modal semantic features into both the SAM image encoder and mask decoder for fine-tuning and prompting, respectively. Specifically, in the image encoder, a multi-modal adapter is proposed to adapt the single-modal SAM to multi-modal information. In the mask decoder, a semantic-geometric prompt generation strategy is proposed to produce corresponding embeddings with various saliency cues. Extensive experiments on both RGB-D and RGB-T SOD benchmarks show the effectiveness of the proposed framework. The code will be available at \url{https://github.com/Angknpng/Sammese}.

cs.CV↗

arXiv2024

Unified-modal Salient Object Detection via Adaptive Prompt Learning

Existing single-modal and multi-modal salient object detection (SOD) methods focus on designing specific architectures tailored for their respective tasks. However, developing completely different models for different tasks leads to labor and time consumption, as well as high computational and practical deployment costs. In this paper, we attempt to address both single-modal and multi-modal SOD in a unified framework called UniSOD, which fully exploits the overlapping prior knowledge between different tasks. Nevertheless, assigning appropriate strategies to modality variable inputs is challenging. To this end, UniSOD learns modality-aware prompts with task-specific hints through adaptive prompt learning, which are plugged into the proposed pre-trained baseline SOD model to handle corresponding tasks, while only requiring few learnable parameters compared to training the entire model. Each modality-aware prompt is generated from a switchable prompt generation block, which adaptively performs structural switching based on single-modal and multi-modal inputs without human intervention. Through end-to-end joint training, UniSOD achieves overall performance improvement on 14 benchmark datasets for RGB, RGB-D, and RGB-T SOD, which demonstrates that our method effectively and efficiently unifies single-modal and multi-modal SOD tasks.The code and results are available at https://github.com/Angknpng/UniSOD.

cs.CV↗

arXiv2024

Alignment-Free RGBT Salient Object Detection: Semantics-guided Asymmetric Correlation Network and A Unified Benchmark

RGB and Thermal (RGBT) Salient Object Detection (SOD) aims to achieve high-quality saliency prediction by exploiting the complementary information of visible and thermal image pairs, which are initially captured in an unaligned manner. However, existing methods are tailored for manually aligned image pairs, which are labor-intensive, and directly applying these methods to original unaligned image pairs could significantly degrade their performance. In this paper, we make the first attempt to address RGBT SOD for initially captured RGB and thermal image pairs without manual alignment. Specifically, we propose a Semantics-guided Asymmetric Correlation Network (SACNet) that consists of two novel components: 1) an asymmetric correlation module utilizing semantics-guided attention to model cross-modal correlations specific to unaligned salient regions; 2) an associated feature sampling module to sample relevant thermal features according to the corresponding RGB features for multi-modal feature integration. In addition, we construct a unified benchmark dataset called UVT2000, containing 2000 RGB and thermal image pairs directly captured from various real-world scenes without any alignment, to facilitate research on alignment-free RGBT SOD. Extensive experiments on both aligned and unaligned datasets demonstrate the effectiveness and superior performance of our method. The dataset and code are available at https://github.com/Angknpng/SACNet.

cs.CV↗

arXiv2024

Learning Adaptive Fusion Bank for Multi-modal Salient Object Detection

Multi-modal salient object detection (MSOD) aims to boost saliency detection performance by integrating visible sources with depth or thermal infrared ones. Existing methods generally design different fusion schemes to handle certain issues or challenges. Although these fusion schemes are effective at addressing specific issues or challenges, they may struggle to handle multiple complex challenges simultaneously. To solve this problem, we propose a novel adaptive fusion bank that makes full use of the complementary benefits from a set of basic fusion schemes to handle different challenges simultaneously for robust MSOD. We focus on handling five major challenges in MSOD, namely center bias, scale variation, image clutter, low illumination, and thermal crossover or depth ambiguity. The fusion bank proposed consists of five representative fusion schemes, which are specifically designed based on the characteristics of each challenge, respectively. The bank is scalable, and more fusion schemes could be incorporated into the bank for more challenges. To adaptively select the appropriate fusion scheme for multi-modal input, we introduce an adaptive ensemble module that forms the adaptive fusion bank, which is embedded into hierarchical layers for sufficient fusion of different source data. Moreover, we design an indirect interactive guidance module to accurately detect salient hollow objects via the skip integration of high-level semantic information and low-level spatial details. Extensive experiments on three RGBT datasets and seven RGBD datasets demonstrate that the proposed method achieves the outstanding performance compared to the state-of-the-art methods. The code and results are available at https://github.com/Angknpng/LAFB.

cs.CV↗

arXiv2024

RecycleGPT: An Autoregressive Language Model with Recyclable Module

Existing large language models have to run K times to generate a sequence of K tokens. In this paper, we present RecycleGPT, a generative language model with fast decoding speed by recycling pre-generated model states without running the whole model in multiple steps. Our approach relies on the observation that adjacent tokens in a sequence usually have strong correlations and the next token in a sequence can be reasonably guessed or inferred based on the preceding ones. Experiments and analysis demonstrate the effectiveness of our approach in lowering inference latency, achieving up to 1.4x speedup while preserving high performance.

cs.CL↗

arXiv2024

Mitigating noise of residual electric fields for single Rydberg atoms with electron photodesorption

Rydberg atoms as versatile tools for quantum applications are extremely sensitive to electric fields. When utilizing these atoms, it becomes imperative to comprehensively characterize and mitigate any residual electric fields present in the environment. Particularly for single Rydberg atoms trapped in optical tweezers in a compact quartz vacuum cell, we have identified that a significant source of background electric fields originates from electrons bound to the cell surface. These electrons are generated by the 297-nm light used for single-photon Rydberg excitation. Furthermore, once the electrons are desorbed from the surface through exposure to ultraviolet light, the incoherent ground-Rydberg transition undergoes a transformation into coherent excitation, since the noise of residual electric fields are effectively mitigated. Our studies promote enhanced control and reliable performance of Rydberg atom-based systems, thereby paving the way for advancements in quantum information processing, the realization of high-fidelity quantum gates, and the development of precise quantum sensors.

physics.atom-ph↗

arXiv2023

Erasure-based Interaction Network for RGBT Video Object Detection and A Unified Benchmark

Recently, many breakthroughs are made in the field of Video Object Detection (VOD), but the performance is still limited due to the imaging limitations of RGB sensors in adverse illumination conditions. To alleviate this issue, this work introduces a new computer vision task called RGB-thermal (RGBT) VOD by introducing the thermal modality that is insensitive to adverse illumination conditions. To promote the research and development of RGBT VOD, we design a novel Erasure-based Interaction Network (EINet) and establish a comprehensive benchmark dataset (VT-VOD50) for this task. Traditional VOD methods often leverage temporal information by using many auxiliary frames, and thus have large computational burden. Considering that thermal images exhibit less noise than RGB ones, we develop a negative activation function that is used to erase the noise of RGB features with the help of thermal image features. Furthermore, with the benefits from thermal images, we rely only on a small temporal window to model the spatio-temporal information to greatly improve efficiency while maintaining detection accuracy. VT-VOD50 dataset consists of 50 pairs of challenging RGBT video sequences with complex backgrounds, various objects and different illuminations, which are collected in real traffic scenarios. Extensive experiments on VT-VOD50 dataset demonstrate the effectiveness and efficiency of our proposed method against existing mainstream VOD methods. The code of EINet and the dataset will be released to the public for free academic usage.

cs.CV↗

arXiv2022

A CT-Based Airway Segmentation Using U$^2$-net Trained by the Dice Loss Function

Airway segmentation from chest computed tomography scans has played an essential role in the pulmonary disease diagnosis. The computer-assisted airway segmentation based on the U-net architecture is more efficient and accurate compared to the manual segmentation. In this paper we employ the U$^2$-net trained by the Dice loss function to model the airway tree from the multi-site CT scans based on 299 training CT scans provided by the ATM'22. The derived saliency probability map from the training is applied to the validation data to extract the corresponding airway trees. The observation shows that the majority of the segmented airway trees behave well from the perspective of accuracy and connectivity. Refinements such as non-airway regions labeling and removing are applied to certain obtained airway tree models to display the largest component of the binary results.

eess.IV↗

arXiv2021

Defect-free arbitrary-geometry assembly of mixed-species atom arrays

Optically trapped mixed-species single atom arrays with arbitrary geometries are an attractive and promising platform for various applications, because tunable quantum systems with multiple components provide extra degrees of freedom for experimental control. Here, we report the first demonstration of two-dimensional $6\times4$ dual-species atom assembly with a filling fraction of 0.88 (0.89) for $^{85}$Rb ($^{87}$Rb) atoms. This mixed-species atomic synthetic is achieved via rearranging initially randomly distributed atoms using a sorting algorithm (heuristic heteronuclear algorithm) which is proposed for bottom-up atom assembly with both user-defined geometries and two-species atom number ratios. Our fully tunable hybrid-atom system of scalable advantages is a good starting point for high-fidelity quantum logic, many-body quantum simulation and forming defect-free single molecule arrays.

physics.atom-ph↗

arXiv2020

Efficient preparation of 2D defect-free atom arrays with near-fewest sorting-atom moves

Sorting atoms stochastically loaded in optical tweezer arrays via an auxiliary mobile tweezer is an efficient approach to preparing intermediate-scale defect-free atom arrays in arbitrary geometries. However, high filling fraction of atom-by-atom assemblers is impeded by redundant sorting moves with imperfect atom transport, especially for scaling the system size to larger atom numbers. Here, we propose a new sorting algorithm (heuristic cluster algorithm, HCA) which provides near-fewest moves in our tailored atom assembler scheme and experimentally demonstrate a $5\times6$ defect-free atom array with 98.4(7)$\%$ filling fraction for one rearrangement cycle. The feature of HCA that the number of moves $N_{m}\approx N$ ($N$ is the number of defect sites to be filled) makes the filling fraction uniform as the size of atom assembler enlarged. Our method is essential to scale hundreds of assembled atoms for bottom-up quantum computation, quantum simulation and precision measurement.

quant-ph↗

arXiv2019

Preparation of a Heteronuclear Two-atom System in the 3D Motional Ground State in an Optical Tweezer

We report the realization of a heteronuclear two-atom of $^{87}$Rb-$^{85}$Rb in the ground state of an optical tweezer (OT). Starting by trapping two different isotopic single atoms, a $^{87}$Rb and a $^{85}$Rb in two strongly focused and linearly polarized OT with 4 $μ$m apart, we perform simultaneously three dimensional Raman sideband cooling for both atoms and the obtained 3D ground state probabilities of $^{87}$Rb and $^{85}$Rb are 0.91(5) and 0.91(10) respectively. There is no obvious crosstalk observed during the cooling process. We then merge them into one tweezer via a species-dependent transport, where the species-dependent potentials are made by changing the polarization of the OTs for each species from linear polarization to the desired circular polarization. The measurable increment of vibrational quantum due to merging is $0.013(1)$ for the axial dimension. This two-atom system can be used to investigate cold collisional physics, to form quantum logic gates, and to build a single heteronuclear molecule. It can also be scaled up to few-atom regime and extended to other atomic species and molecules, and thus to ultracold chemistry.

physics.atom-ph↗