arXiv subjects

Jin Wang

Publications and source records attributed to Jin Wang.

At least 145 records · Page 8Linked to original sources

arXiv2025

AI Governance InternationaL Evaluation Index (AGILE Index) 2025

The year 2024 witnessed accelerated global AI governance advancements, marked by strengthened multilateral frameworks and proliferating national regulatory initiatives. This acceleration underscores an unprecedented need to systematically track governance progress--an imperative that drove the launch of the AI Governance InternationaL Evaluation Index (AGILE Index) project since 2023. The inaugural AGILE Index, released in February 2024 after assessing 14 countries, established an operational and comparable baseline framework. Building on pilot insights, AGILE Index 2025 incorporates systematic refinements to better balance scientific rigor with practical adaptability. The updated methodology expands data diversity while enhancing metric validity and cross-national comparability. Reflecting both research advancements and practical policy evolution, AGILE Index 2025 evaluates 40 countries across income levels, regions, and technological development stages, with 4 Pillars, 17 Dimensions and 43 Indicators. In compiling the data, the team integrates multi-source evidence including policy documents, governance practices, research outputs, and risk exposure to construct a unified comparison framework. This approach maps global disparities while enabling countries to identify governance strengths, gaps, and systemic constraints. Through ongoing refinement and iterations, we hope the AGILE Index will fundamentally advance transparency and measurability in global AI governance, delivering data-driven assessments that depict national AI governance capacity, assist governments in recognizing their maturation stages and critical governance issues, and ultimately provide actionable insights for enhancing AI governance systems nationally and globally.

cs.CY↗

arXiv2025

FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocities

The rapid progress of large language models (LLMs) has catalyzed the emergence of multimodal large language models (MLLMs) that unify visual understanding and image generation within a single framework. However, most existing MLLMs rely on autoregressive (AR) architectures, which impose inherent limitations on future development, such as the raster-scan order in image generation and restricted reasoning abilities in causal context modeling. In this work, we challenge the dominance of AR-based approaches by introducing FUDOKI, a unified multimodal model purely based on discrete flow matching, as an alternative to conventional AR paradigms. By leveraging metric-induced probability paths with kinetic optimal velocities, our framework goes beyond the previous masking-based corruption process, enabling iterative refinement with self-correction capability and richer bidirectional context integration during generation. To mitigate the high cost of training from scratch, we initialize FUDOKI from pre-trained AR-based MLLMs and adaptively transition to the discrete flow matching paradigm. Experimental results show that FUDOKI achieves performance comparable to state-of-the-art AR-based MLLMs across both visual understanding and image generation tasks, highlighting its potential as a foundation for next-generation unified multimodal models. Furthermore, we show that applying test-time scaling techniques to FUDOKI yields significant performance gains, further underscoring its promise for future enhancement through reinforcement learning.

cs.CV↗

arXiv2025

RALAD: Bridging the Real-to-Sim Domain Gap in Autonomous Driving with Retrieval-Augmented Learning

In the pursuit of robust autonomous driving systems, models trained on real-world datasets often struggle to adapt to new environments, particularly when confronted with corner cases such as extreme weather conditions. Collecting these corner cases in the real world is non-trivial, which necessitates the use of simulators for validation. However,the high computational cost and the domain gap in data distribution have hindered the seamless transition between real and simulated driving scenarios. To tackle this challenge, we propose Retrieval-Augmented Learning for Autonomous Driving (RALAD), a novel framework designed to bridge the real-to-sim gap at a low cost. RALAD features three primary designs, including (1) domain adaptation via an enhanced Optimal Transport (OT) method that accounts for both individual and grouped image distances, (2) a simple and unified framework that can be applied to various models, and (3) efficient fine-tuning techniques that freeze the computationally expensive layers while maintaining robustness. Experimental results demonstrate that RALAD compensates for the performance degradation in simulated environments while maintaining accuracy in real-world scenarios across three different models. Taking Cross View as an example, the mIOU and mAP metrics in real-world scenarios remain stable before and after RALAD fine-tuning, while in simulated environments,the mIOU and mAP metrics are improved by 10.30% and 12.29%, respectively. Moreover, the re-training cost of our approach is reduced by approximately 88.1%. Our code is available at https://github.com/JiachengZuo/RALAD.git.

cs.CV↗

arXiv2025

INTER: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Sampling

Hallucinations in large vision-language models (LVLMs) pose significant challenges for real-world applications, as LVLMs may generate responses that appear plausible yet remain inconsistent with the associated visual content. This issue rarely occurs in human cognition. We argue that this discrepancy arises from humans' ability to effectively leverage multimodal interaction information in data samples. Specifically, humans typically first gather multimodal information, analyze the interactions across modalities for understanding, and then express their understanding through language. Motivated by this observation, we conduct extensive experiments on popular LVLMs and obtained insights that surprisingly reveal human-like, though less pronounced, cognitive behavior of LVLMs on multimodal samples. Building on these findings, we further propose \textbf{INTER}: \textbf{Inter}action Guidance Sampling, a novel training-free algorithm that mitigate hallucinations without requiring additional data. Specifically, INTER explicitly guides LVLMs to effectively reapply their understanding of multimodal interaction information when generating responses, thereby reducing potential hallucinations. On six benchmarks including VQA and image captioning tasks, INTER achieves an average improvement of up to 3.4\% on five LVLMs compared to the state-of-the-art decoding strategy. The code will be released when the paper is accepted.

cs.CV↗

arXiv2025

In-flight Characteristics and Modelling of the Instrumental Background of EP/FXT

The in-flight instrumental background of the Follow-up X-ray Telescope (FXT) onboard Einstein Probe (EP) mission is analysed in this work by utilizing observations collected during Performance Verification phase and subsequent dedicated filter wheel closed observations. The instrumental backgrounds of the two FXT modules are consistent with each other, with an average rate of $\sim 4\times10^{-2}$\,counts/s/keV in the 0.5--10\,keV band for each module. The background is nearly uniformly distributed across the detector area, with a minor increase ($<8\%$) observed along rows. The spatial distribution shows significant modulation by the geomagnetic field. The spectral shapes remain unchanged in 0.5--10\,keV at different rates. The long-term temporal variation indicates a periodic change associated with the orbital precession ($\sim 57$ days). The innovative design of FXT full-frame readout mode enables simultaneous recording of events in both the imaging area (IMG) and the frame store area (FSA) of the pnCCD. FSA event rates show a strong linear correlation with the IMG, based on which the IMG instrumental background modelling is established.

astro-ph.IM↗

arXiv2025

AI Governance InternationaL Evaluation Index (AGILE Index) 2024

The rapid advancement of Artificial Intelligence (AI) technology is profoundly transforming human society and concurrently presenting a series of ethical, legal, and social issues. The effective governance of AI has become a crucial global concern. Since 2022, the extensive deployment of generative AI, particularly large language models, marked a new phase in AI governance. Continuous efforts are being made by the international community in actively addressing the novel challenges posed by these AI developments. As consensus on international governance continues to be established and put into action, the practical importance of conducting a global assessment of the state of AI governance is progressively coming to light. In this context, we initiated the development of the AI Governance InternationaL Evaluation Index (AGILE Index). Adhering to the design principle, "the level of governance should match the level of development," the inaugural evaluation of the AGILE Index commences with an exploration of four foundational pillars: the development level of AI, the AI governance environment, the AI governance instruments, and the AI governance effectiveness. It covers 39 indicators across 18 dimensions to comprehensively assess the AI governance level of 14 representative countries globally. The index is utilized to delve into the status of AI governance to date in 14 countries for the first batch of evaluation. The aim is to depict the current state of AI governance in these countries through data scoring, assist them in identifying their governance stage and uncovering governance issues, and ultimately offer insights for the enhancement of their AI governance systems.

cs.CY↗

arXiv2025

Information-Assisted Carnot Engine Surpasses Standard Thermodynamic Bounds

Information can improve heat engine performance, but the underlying principles are still not so clear. Here we introduce a Carnot information machine (CIE) and obtain a quantitative relationship between the engine performance and information. We demonstrate that the presence of information changes allows the CIE to operate as a heat engine in the regime where the standard Carnot cycle is prohibited, ensures that the efficiency of the CIE is greater than or equal to the standard Carnot efficiency, and significantly enables it to achieve 100\% efficiency with positive work extraction for arbitrary two-level systems. We explicitly demonstrate these features using a spin-1/2 system and propose an experimental implementation scheme based on a trapped $^{40}\mathrm{Ca}^+$ ion.

cond-mat.stat-mech↗

arXiv2025

On-Device Control of Electronic Friction

Friction causes mechanical energy dissipation and material degradation in machinery and devices. While phononic friction is well understood via anharmonic lattice dynamics, the physics of electronic friction remains unclear due to challenges in separating electronic degrees of freedom from phononic ones in experiments and analyzing the non-equilibrium interactions between ionic movement and electronic dynamics in theory. To tackle this problem, we construct a sliding device featuring 2D crystalline interfaces that possess ultra-smooth and minimally interacting surfaces, achieving the state of structural superlubricity with no wear and minimal friction. Using electrical and mechanical controls, we tuned the nature of interfacial electronic coupling and charge densities in materials in an on-device setting, which allows us to disentangle the electron and phonon contributions to friction. Our experimental data and theoretical analysis supported by first-principles calculations demonstrate that electronic friction can well surpass phononic contributions and dominate energy dissipation at structural superlubricity contacts. These findings offer fresh insights into the mechanism of electronic friction and promising opportunities for friction control in device applications.

cond-mat.mes-hall↗

arXiv2025

Compact and robust design of the optical system for cold atom interferometer in space

The optical system is a complex and precise subsystem for the atom interferometer (AI), especially for those used in field or space applications. Here, we introduce the design of the optical system of the China Space Station atom interferometer (CSSAI). The scheme is optimized to reduce the complexity while maintaining the capability to achieve the dual-species AI. It features a fused silica optical bench with bonding technology, ensuring compactness and smaller thermal deformation. Spatial structures are designed to isolate the vibration and transfer the heat. After assembling, the optical system has a size of 250 mm * 240 mm * 104 mm and weighs 5.2 kg. After installing in the CSSAI, it passed the thermal and mechanical tests and then launched to the China Space Station (CSS). The output laser power changes are less than 15% from ground to space, and its long-term fluctuations are less than 2.5% for months in space. Cold atom preparation and interference are also realized in space. This optical system is extremely integrated and robust, which provides a foundation for the design of future cold atom payloads in space.

physics.atom-ph↗

arXiv2025

Efficient Event-Based Semantic Segmentation via Exploiting Frame-Event Fusion: A Hybrid Neural Network Approach

Event cameras have recently been introduced into image semantic segmentation, owing to their high temporal resolution and other advantageous properties. However, existing event-based semantic segmentation methods often fail to fully exploit the complementary information provided by frames and events, resulting in complex training strategies and increased computational costs. To address these challenges, we propose an efficient hybrid framework for image semantic segmentation, comprising a Spiking Neural Network branch for events and an Artificial Neural Network branch for frames. Specifically, we introduce three specialized modules to facilitate the interaction between these two branches: the Adaptive Temporal Weighting (ATW) Injector, the Event-Driven Sparse (EDS) Injector, and the Channel Selection Fusion (CSF) module. The ATW Injector dynamically integrates temporal features from event data into frame features, enhancing segmentation accuracy by leveraging critical dynamic temporal information. The EDS Injector effectively combines sparse event data with rich frame features, ensuring precise temporal and spatial information alignment. The CSF module selectively merges these features to optimize segmentation performance. Experimental results demonstrate that our framework not only achieves state-of-the-art accuracy across the DDD17-Seg, DSEC-Semantic, and M3ED-Semantic datasets but also significantly reduces energy consumption, achieving a 65\% reduction on the DSEC-Semantic dataset.

cs.CV↗

arXiv2025

Privacy-preserving Preselection for Face Identification Based on Packing

Face identification systems operating in the ciphertext domain have garnered significant attention due to increasing privacy concerns and the potential recovery of original facial data. However, as the size of ciphertext template libraries grows, the face retrieval process becomes progressively more time-intensive. To address this challenge, we propose a novel and efficient scheme for face retrieval in the ciphertext domain, termed Privacy-Preserving Preselection for Face Identification Based on Packing (PFIP). PFIP incorporates an innovative preselection mechanism to reduce computational overhead and a packing module to enhance the flexibility of biometric systems during the enrollment stage. Extensive experiments conducted on the LFW and CASIA datasets demonstrate that PFIP preserves the accuracy of the original face recognition model, achieving a 100% hit rate while retrieving 1,000 ciphertext face templates within 300 milliseconds. Compared to existing approaches, PFIP achieves a nearly 50x improvement in retrieval efficiency.

cs.CV↗

arXiv2025

Brain-inspired and Self-based Artificial Intelligence

The question "Can machines think?" and the Turing Test to assess whether machines could achieve human-level intelligence is one of the roots of AI. With the philosophical argument "I think, therefore I am", this paper challenge the idea of a "thinking machine" supported by current AIs since there is no sense of self in them. Current artificial intelligence is only seemingly intelligent information processing and does not truly understand or be subjectively aware of oneself and perceive the world with the self as human intelligence does. In this paper, we introduce a Brain-inspired and Self-based Artificial Intelligence (BriSe AI) paradigm. This BriSe AI paradigm is dedicated to coordinating various cognitive functions and learning strategies in a self-organized manner to build human-level AI models and robotic applications. Specifically, BriSe AI emphasizes the crucial role of the Self in shaping the future AI, rooted with a practical hierarchical Self framework, including Perception and Learning, Bodily Self, Autonomous Self, Social Self, and Conceptual Self. The hierarchical framework of the Self highlights self-based environment perception, self-bodily modeling, autonomous interaction with the environment, social interaction and collaboration with others, and even more abstract understanding of the Self. Furthermore, the positive mutual promotion and support among multiple levels of Self, as well as between Self and learning, enhance the BriSe AI's conscious understanding of information and flexible adaptation to complex environments, serving as a driving force propelling BriSe AI towards real Artificial General Intelligence.

cs.AI↗

arXiv2025

Detection of subsurface structures with a vehicle-based atom gravity gradiometer

High-precision mobile gravity gradiometers are very useful in geodesy and geophysics. Atom gravity gradiometers (AGGs) could be among the most accurate mobile gravity gradiometers but are currently constrained by the trade-off between portability and sensitivity. Here, we present a high-sensitivity mobile AGG featuring an ultra-compact sensor head with a volume of only 94 L. In the laboratory, it achieves a sensitivity of 77 E/$\sqrt{Hz}$ (1 E=1$\times10^{-9}$/s$^2$) and a long-term stability of better than 0.5 E. We integrated the instrument in a minivan, enabling efficient mobile field surveys with excellent maneuverability in confined spaces. Using this vehicular system, we surveyed the gravitational field over a set of subsurface structures within a small wooded area, successfully resolving their structural signatures with a signal-to-noise ratio of 57 and quantifying the water depth in a reservoir with an accuracy of $\pm$0.23 m. Compared with previous observations using a CG-5 gravimeter, the superior spatial resolution inherent in gradiometry is clearly demonstrated. This work paves the way for bring AGGs to practical field applications.

physics.ins-det↗

arXiv2025

Tailless Flapping-Wing Robot With Bio-Inspired Elastic Passive Legs for Multi-Modal Locomotion

Flapping-wing robots offer significant versatility; however, achieving efficient multi-modal locomotion remains challenging. This paper presents the design, modeling, and experimentation of a novel tailless flapping-wing robot with three independently actuated pairs of wings. Inspired by the leg morphology of juvenile water striders, the robot incorporates bio-inspired elastic passive legs that convert flapping-induced vibrations into directional ground movement, enabling locomotion without additional actuators. This vibration-driven mechanism facilitates lightweight, mechanically simplified multi-modal mobility. An SE(3)-based controller coordinates flight and mode transitions with minimal actuation. To validate the robot's feasibility, a functional prototype was developed, and experiments were conducted to evaluate its flight, ground locomotion, and mode-switching capabilities. Results show satisfactory performance under constrained actuation, highlighting the potential of multi-modal flapping-wing designs for future aerial-ground robotic applications. These findings provide a foundation for future studies on frequency-based terrestrial control and passive yaw stabilization in hybrid locomotion systems.

cs.RO↗

arXiv2025

MoNetV2: Enhanced Motion Network for Freehand 3D Ultrasound Reconstruction

Three-dimensional (3D) ultrasound (US) aims to provide sonographers with the spatial relationships of anatomical structures, playing a crucial role in clinical diagnosis. Recently, deep-learning-based freehand 3D US has made significant advancements. It reconstructs volumes by estimating transformations between images without external tracking. However, image-only reconstruction poses difficulties in reducing cumulative drift and further improving reconstruction accuracy, particularly in scenarios involving complex motion trajectories. In this context, we propose an enhanced motion network (MoNetV2) to enhance the accuracy and generalizability of reconstruction under diverse scanning velocities and tactics. First, we propose a sensor-based temporal and multi-branch structure that fuses image and motion information from a velocity perspective to improve image-only reconstruction accuracy. Second, we devise an online multi-level consistency constraint that exploits the inherent consistency of scans to handle various scanning velocities and tactics. This constraint exploits both scan-level velocity consistency, path-level appearance consistency, and patch-level motion consistency to supervise inter-frame transformation estimation. Third, we distill an online multi-modal self-supervised strategy that leverages the correlation between network estimation and motion information to further reduce cumulative errors. Extensive experiments clearly demonstrate that MoNetV2 surpasses existing methods in both reconstruction quality and generalizability performance across three large datasets.

eess.IV↗

arXiv2025

Driven-dissipative quantum battery with nonequilibrium reservoirs

We investigate a quantum battery system under both external driving and dissipation. The system consists of a coupled two-level charger and battery immersed in nonequilibrium fermionic reservoirs. By considering the changes in the energy spectrum induced by external driving and charger-battery coupling in a non-perturbative manner, we go beyond the secular approximation to derive the Redfield master equation. In the nonequilibrium scenario, both charging efficiency and power of the quantum battery can be optimized through a compensation mechanism. When the charger and battery are off-resonance, a significant chemical potential difference between the reservoirs, which characterizes the degree of nonequilibrium, plays a crucial role. Specifically, the charger's frequency should be higher (lower) than that of the battery when the average chemical potential is negative (positive) to achieve enhanced charging efficiency and power under strong nonequilibrium conditions. Remarkably, the efficiency in the nonequilibrium case can surpass that in the equilibrium setup. Moreover, we find no positive correlation between entanglement and efficiency, challenging the prevailing assumption that entanglement necessarily enhances the performance of quantum devices. Our results provide insights into the design and optimization of quantum batteries in nonequilibrium open systems.

quant-ph↗

arXiv2025

Critical slowing down of black hole phase transition and kinetic crossover in supercritical regime

Reissner-Nordström-Anti-de Sitter (RNAdS) black holes in the extended phase space exhibit critical behavior analogous to the liquid-gas system, with critical exponents matching those of van der Waals-type phase transitions. However, the kinetics of these transitions near spinodal and critical points remain poorly understood. We demonstrate that both the autocorrelation time and the variance of trajectories increase significantly as the system approaches these special points, signaling critical slowing down. This behavior is driven by the flattening of the free energy landscape, as further confirmed by the lowest eigenvalue of the Fokker-Planck equation. Moreover, we uncover a clear dynamical crossover separating gas-like and liquid-like regimes in the supercritical region. This kinetic crossover defines the Widom line that closely matches the thermodynamic one obtained from the maxima of the isobaric heat capacity. These findings contribute to a deeper understanding of the kinetics of RNAdS black holes in the vicinity of spinodal and critical points.

gr-qc↗

arXiv2025

Decoherence of quantum superpositions in near-extremal Reissner-Nordström black holes with quantum gravity corrections

We study the quantum gravity corrected decoherence of quantum superpositions in the near-extremal Reissner-Nordström black holes. By employing the effective field theory approach, we model the black hole as a quantum system coupled to an external source via a scalar field, and derive the relation between the decoherence rate and the two-point correlation function of the operators acting on the black quantum system. By utilizing the low-energy Schwarzian effective theory, which captures the boundary dynamics of the $AdS_2$ near-horizon geometry of the near-extremal Reissner-Nordström black holes, we compute the decoherence rate both in the microcanonical and canonical ensembles. We find that in the microcanonical ensemble, where the black hole energy is fixed, quantum gravity corrections do not modify the decoherence rate compared to the semiclassical prediction. However, in the canonical ensemble, where the black hole is in a thermal equilibrium state, quantum gravitational effects significantly enhance the decoherence rate at low temperatures. Our results demonstrate that even in the near-extremal limit where Hawking radiation is suppressed, quantum gravitational fluctuations can strongly influence the coherence of nearby quantum systems.

hep-th↗