arXiv subjects

Chao Zhang

Publications and source records attributed to Chao Zhang.

At least 307 records · Page 17Linked to original sources

arXiv2025

MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence

Audio comprehension-including speech, non-speech sounds, and music-is essential for achieving human-level intelligence. Consequently, AI agents must demonstrate holistic audio understanding to qualify as generally intelligent. However, evaluating auditory intelligence comprehensively remains challenging. To address this gap, we introduce MMAU-Pro, the most comprehensive and rigorously curated benchmark for assessing audio intelligence in AI systems. MMAU-Pro contains 5,305 instances, where each instance has one or more audios paired with human expert-generated question-answer pairs, spanning speech, sound, music, and their combinations. Unlike existing benchmarks, MMAU-Pro evaluates auditory intelligence across 49 unique skills and multiple complex dimensions, including long-form audio comprehension, spatial audio reasoning, multi-audio understanding, among others. All questions are meticulously designed to require deliberate multi-hop reasoning, including both multiple-choice and open-ended response formats. Importantly, audio data is sourced directly ``from the wild" rather than from existing datasets with known distributions. We evaluate 22 leading open-source and proprietary multimodal AI models, revealing significant limitations: even state-of-the-art models such as Gemini 2.5 Flash and Audio Flamingo 3 achieve only 59.2% and 51.7% accuracy, respectively, approaching random performance in multiple categories. Our extensive analysis highlights specific shortcomings and provides novel insights, offering actionable perspectives for the community to enhance future AI systems' progression toward audio general intelligence. The benchmark and code is available at https://sonalkum.github.io/mmau-pro.

eess.AS↗

arXiv2025

Partial regularity of suitable weak solutions to the incompressible magnetohydrodynamic equations

This paper establishes a regularity theory for the magnetohydrodynamics (MHD) equations with external forces through scaling analysis. Inspired by the existing methodology, we utilize linearized approximations and the monotonicity property of harmonic functions to construct iterative sequences capturing scaling properties. This work successfully extends Navier-Stokes techniques to MHD coupling and demonstrates that the one dimensional parabolic Hausdorff measure of the possible singular points for the suitable weak solutions is zero.

math.AP↗

arXiv2025

MoSE: Skill-by-Skill Mixture-of-Experts Learning for Embodied Autonomous Machines

To meet the growing demand for smarter, faster, and more efficient embodied AI solutions, we introduce a novel Mixture-of-Expert (MoE) method that significantly boosts reasoning and learning efficiency for embodied autonomous systems. General MoE models demand extensive training data and complex optimization, which limits their applicability in embodied AI such as autonomous driving (AD) and robotic manipulation. In this work, we propose a skill-oriented MoE called MoSE, which mimics the human learning and reasoning process skill-by-skill, step-by-step. We introduce a skill-oriented routing mechanism that begins with defining and annotating specific skills, enabling experts to identify the necessary competencies for various scenarios and reasoning tasks, thereby facilitating skill-by-skill learning. To better align with multi-step planning in human reasoning and in end-to-end driving models, we build a hierarchical skill dataset and pretrain the router to encourage the model to think step-by-step. Unlike other multi-round dialogues, MoSE integrates valuable auxiliary tasks (e.g. perception-prediction-planning for AD, and high-level and low-level planning for robots) in one single forward process without introducing any extra computational cost. With less than 3B sparsely activated parameters, our model effectively grows more diverse expertise and outperforms models on both AD corner-case reasoning tasks and robot reasoning tasks with less than 40% of the parameters.

cs.AI↗

arXiv2025

HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels

Creating immersive and playable 3D worlds from texts or images remains a fundamental challenge in computer vision and graphics. Existing world generation approaches typically fall into two categories: video-based methods that offer rich diversity but lack 3D consistency and rendering efficiency, and 3D-based methods that provide geometric consistency but struggle with limited training data and memory-inefficient representations. To address these limitations, we present HunyuanWorld 1.0, a novel framework that combines the best of both worlds for generating immersive, explorable, and interactive 3D scenes from text and image conditions. Our approach features three key advantages: 1) 360° immersive experiences via panoramic world proxies; 2) mesh export capabilities for seamless compatibility with existing computer graphics pipelines; 3) disentangled object representations for augmented interactivity. The core of our framework is a semantically layered 3D mesh representation that leverages panoramic images as 360° world proxies for semantic-aware world decomposition and reconstruction, enabling the generation of diverse 3D worlds. Extensive experiments demonstrate that our method achieves state-of-the-art performance in generating coherent, explorable, and interactive 3D worlds while enabling versatile applications in virtual reality, physical simulation, game development, and interactive content creation.

cs.CV↗

arXiv2025

Cowpox: Towards the Immunity of VLM-based Multi-Agent Systems

Vision Language Model (VLM)-based agents are stateful, autonomous entities capable of perceiving and interacting with their environments through vision and language. Multi-agent systems comprise specialized agents who collaborate to solve a (complex) task. A core security property is robustness, stating that the system should maintain its integrity under adversarial attacks. However, the design of existing multi-agent systems lacks the robustness consideration, as a successful exploit against one agent can spread and infect other agents to undermine the entire system's assurance. To address this, we propose a new defense approach, Cowpox, to provably enhance the robustness of multi-agent systems. It incorporates a distributed mechanism, which improves the recovery rate of agents by limiting the expected number of infections to other agents. The core idea is to generate and distribute a special cure sample that immunizes an agent against the attack before exposure and helps recover the already infected agents. We demonstrate the effectiveness of Cowpox empirically and provide theoretical robustness guarantees.

cs.MA↗

arXiv2025

Language Model Uncertainty Quantification with Attention Chain

Accurately quantifying a large language model's (LLM) predictive uncertainty is crucial for judging the reliability of its answers. While most existing research focuses on short, directly answerable questions with closed-form outputs (e.g., multiple-choice), involving intermediate reasoning steps in LLM responses is increasingly important. This added complexity complicates uncertainty quantification (UQ) because the probabilities assigned to answer tokens are conditioned on a vast space of preceding reasoning tokens. Direct marginalization is infeasible, and the dependency inflates probability estimates, causing overconfidence in UQ. To address this, we propose UQAC, an efficient method that narrows the reasoning space to a tractable size for marginalization. UQAC iteratively constructs an "attention chain" of tokens deemed "semantically crucial" to the final answer via a backtracking procedure. Starting from the answer tokens, it uses attention weights to identify the most influential predecessors, then iterates this process until reaching the input tokens. The resulting chain is further refined with similarity filtering and probability thresholding, which reduce the reasoning space, facilitating the approximation of the marginal answer token probabilities. We validate UQAC on multiple reasoning benchmarks with advanced open-source LLMs, demonstrating that it consistently delivers reliable UQ estimates with high computational efficiency.

cs.CL↗

arXiv2025

Multimodal Attention-Aware Fusion for Diagnosing Distal Myopathy: Evaluating Model Interpretability and Clinician Trust

Distal myopathy represents a genetically heterogeneous group of skeletal muscle disorders with broad clinical manifestations, posing diagnostic challenges in radiology. To address this, we propose a novel multimodal attention-aware fusion architecture that combines features extracted from two distinct deep learning models, one capturing global contextual information and the other focusing on local details, representing complementary aspects of the input data. Uniquely, our approach integrates these features through an attention gate mechanism, enhancing both predictive performance and interpretability. Our method achieves a high classification accuracy on the BUSI benchmark and a proprietary distal myopathy dataset, while also generating clinically relevant saliency maps that support transparent decision-making in medical diagnosis. We rigorously evaluated interpretability through (1) functionally grounded metrics, coherence scoring against reference masks and incremental deletion analysis, and (2) application-grounded validation with seven expert radiologists. While our fusion strategy boosts predictive performance relative to single-stream and alternative fusion strategies, both quantitative and qualitative evaluations reveal persistent gaps in anatomical specificity and clinical usefulness of the interpretability. These findings highlight the need for richer, context-aware interpretability methods and human-in-the-loop feedback to meet clinicians' expectations in real-world diagnostic settings.

cs.CV↗

arXiv2025

Why Do Class-Dependent Evaluation Effects Occur with Time Series Feature Attributions? A Synthetic Data Investigation

Evaluating feature attribution methods represents a critical challenge in explainable AI (XAI), as researchers typically rely on perturbation-based metrics when ground truth is unavailable. However, recent work reveals that these evaluation metrics can show different performance across predicted classes within the same dataset. These "class-dependent evaluation effects" raise questions about whether perturbation analysis reliably measures attribution quality, with direct implications for XAI method development and evaluation trustworthiness. We investigate under which conditions these class-dependent effects arise by conducting controlled experiments with synthetic time series data where ground truth feature locations are known. We systematically vary feature types and class contrasts across binary classification tasks, then compare perturbation-based degradation scores with ground truth-based precision-recall metrics using multiple attribution methods. Our experiments demonstrate that class-dependent effects emerge with both evaluation approaches, even in simple scenarios with temporally localized features, triggered by basic variations in feature amplitude or temporal extent between classes. Most critically, we find that perturbation-based and ground truth metrics frequently yield contradictory assessments of attribution quality across classes, with weak correlations between evaluation approaches. These findings suggest that researchers should interpret perturbation-based metrics with care, as they may not always align with whether attributions correctly identify discriminating features. By showing this disconnect, our work points toward reconsidering what attribution evaluation actually measures and developing more rigorous evaluation methods that capture multiple dimensions of attribution quality.

cs.LG↗

arXiv2025

Stacked Intelligent Metasurface Assisted Multiuser Communications: From a Rate Fairness Perspective

Stacked intelligent metasurface (SIM) extends the concept of single-layer reconfigurable holographic surfaces (RHS) by incorporating a multi-layered structure, thereby providing enhanced control over electromagnetic wave propagation and improved signal processing capabilities. This study investigates the potential of SIM in enhancing the rate fairness in multiuser downlink systems by addressing two key optimization problems: maximizing the minimum rate (MR) and maximizing the geometric mean of rates (GMR). {The former strives to enhance the minimum user rate, thereby ensuring fairness among users, while the latter relaxes fairness requirements to strike a better trade-off between user fairness and system sum-rate (SR).} For the MR maximization, we adopt a consensus alternating direction method of multipliers (ADMM)-based approach, which decomposes the approximated problem into sub-problems with closed-form solutions. {For GMR maximization, we develop an alternating optimization (AO)-based algorithm that also yields closed-form solutions and can be seamlessly adapted for SR maximization. Numerical results validate the effectiveness and convergence of the proposed algorithms.} Comparative evaluations show that MR maximization ensures near-perfect fairness, while GMR maximization balances fairness and system SR. Furthermore, the two proposed algorithms respectively outperform existing related works in terms of MR and SR performance. Lastly, SIM with lower power consumption achieves performance comparable to that of multi-antenna digital beamforming.

eess.SP↗

arXiv2025

End-to-end reconstruction of ultra-high energy particle observables from radio detection of extensive air showers

The radio detection of very inclined air showers offers a promising avenue for studying ultra-high-energy cosmic rays (UHECRs) and neutrinos. Accurate reconstruction methods are essential for investigating the properties of primary particles. Recently, we developed an analytical least-squares method to reconstruct the electric field using three polarization components. The reconstruction yields no bias, with a 68\% confidence interval of [-0.02, 0.02], and a standard deviation of 0.04. Using this reconstructed electric field, we perform a realistic reconstruction of the the properties of primary particles. We employ a spherical wave model combined with an angular distribution function (ADF) for arrival direction reconstruction, achieving an angular resolution of 0.04$^\circ$. This paper also presents an energy reconstruction in which we account for the effects of geosynchrotron radiation in inclined air showers, we implement an air density correction in the energy reconstruction, resulting in a 10\% resolution in energy estimation. These findings demonstrate the reliability and effectiveness of our reconstruction methodology, paving the way for future detection experiments using sparse antenna arrays.

astro-ph.IM↗

arXiv2025

Spatial 3D-LLM: Exploring Spatial Awareness in 3D Vision-Language Models

New era has unlocked exciting possibilities for extending Large Language Models (LLMs) to tackle 3D vision-language tasks. However, most existing 3D multimodal LLMs (MLLMs) rely on compressing holistic 3D scene information or segmenting independent objects to perform these tasks, which limits their spatial awareness due to insufficient representation of the richness inherent in 3D scenes. To overcome these limitations, we propose Spatial 3D-LLM, a 3D MLLM specifically designed to enhance spatial awareness for 3D vision-language tasks by enriching the spatial embeddings of 3D scenes. Spatial 3D-LLM integrates an LLM backbone with a progressive spatial awareness scheme that progressively captures spatial information as the perception field expands, generating location-enriched 3D scene embeddings to serve as visual prompts. Furthermore, we introduce two novel tasks: 3D object distance measurement and 3D layout editing, and construct a 3D instruction dataset, MODEL, to evaluate the model's spatial awareness capabilities. Experimental results demonstrate that Spatial 3D-LLM achieves state-of-the-art performance across a wide range of 3D vision-language tasks, revealing the improvements stemmed from our progressive spatial awareness scheme of mining more profound spatial information. Our code is available at https://github.com/bjshuyuan/Spatial-3D-LLM.

cs.CV↗

arXiv2025

Lunar Orbital VLBI Experiment: motivation, scientific purposes and status

The Lunar Orbital VLBI Experiment (LOVEX) is a scientific component of the Chinese Lunar Exploration Project (CLEP) Chang'E-7. The spaceborne component of LOVEX is implemented onboard the relay satellite QueQiao-2, which was launched on 2024 March 20, and later placed into an elliptical selenocentric orbit. The LOVEX-specific payload consists of an X-band cryogenic receiver, a hydrogen maser frequency standard, and VLBI data formatting and acquisition electronics. Several components of the QueQiao-2 nominal onboard instrumentation, such as the 4.2-meter antenna, the data storage device, and the downlink communication system, contribute to the overall spaceborne VLBI instrumentation. This allows us to form a space radio telescope capable of co-observing with Earth-based radio telescopes in VLBI mode. In this space VLBI system, the length of the baseline extends up to approximately 380,000 km. This paper presents the LOVEX scientific objectives, architecture, instrumentation, pre-launch tests, in-flight verification and calibration, and the first in-flight detections of interferometric response (''fringes'') achieved through observations of the quasar AO 0235+164 and the Chang'E-6 orbital module, positioned at the Sun-Earth Lagrange point L2. These initial results demonstrate the successful performance of LOVEX, verifying its capability for both astronomical and spacecraft tracking observations at ultra-long VLBI baselines.

astro-ph.IM↗

arXiv2025

3DKeyAD: High-Resolution 3D Point Cloud Anomaly Detection via Keypoint-Guided Point Clustering

High-resolution 3D point clouds are highly effective for detecting subtle structural anomalies in industrial inspection. However, their dense and irregular nature imposes significant challenges, including high computational cost, sensitivity to spatial misalignment, and difficulty in capturing localized structural differences. This paper introduces a registration-based anomaly detection framework that combines multi-prototype alignment with cluster-wise discrepancy analysis to enable precise 3D anomaly localization. Specifically, each test sample is first registered to multiple normal prototypes to enable direct structural comparison. To evaluate anomalies at a local level, clustering is performed over the point cloud, and similarity is computed between features from the test sample and the prototypes within each cluster. Rather than selecting cluster centroids randomly, a keypoint-guided strategy is employed, where geometrically informative points are chosen as centroids. This ensures that clusters are centered on feature-rich regions, enabling more meaningful and stable distance-based comparisons. Extensive experiments on the Real3D-AD benchmark demonstrate that the proposed method achieves state-of-the-art performance in both object-level and point-level anomaly detection, even using only raw features.

cs.CV↗

arXiv2025

Argus: Leveraging Multiview Images for Improved 3-D Scene Understanding With Large Language Models

Advancements in foundation models have made it possible to conduct applications in various downstream tasks. Especially, the new era has witnessed a remarkable capability to extend Large Language Models (LLMs) for tackling tasks of 3D scene understanding. Current methods rely heavily on 3D point clouds, but the 3D point cloud reconstruction of an indoor scene often results in information loss. Some textureless planes or repetitive patterns are prone to omission and manifest as voids within the reconstructed 3D point clouds. Besides, objects with complex structures tend to introduce distortion of details caused by misalignments between the captured images and the dense reconstructed point clouds. 2D multi-view images present visual consistency with 3D point clouds and provide more detailed representations of scene components, which can naturally compensate for these deficiencies. Based on these insights, we propose Argus, a novel 3D multimodal framework that leverages multi-view images for enhanced 3D scene understanding with LLMs. In general, Argus can be treated as a 3D Large Multimodal Foundation Model (3D-LMM) since it takes various modalities as input(text instructions, 2D multi-view images, and 3D point clouds) and expands the capability of LLMs to tackle 3D tasks. Argus involves fusing and integrating multi-view images and camera poses into view-as-scene features, which interact with the 3D features to create comprehensive and detailed 3D-aware scene embeddings. Our approach compensates for the information loss while reconstructing 3D point clouds and helps LLMs better understand the 3D world. Extensive experiments demonstrate that our method outperforms existing 3D-LMMs in various downstream tasks.

cs.CV↗

arXiv2025

Electric-Field Reconstruction for Radio Detection of Inclined Air Showers in Three Polarizations

Accurate reconstruction of the electric field produced by extensive air showers is essential for the radio-detection technique, as the key parameters of interest of the primary particles that generated the showers are the amplitude, polarization, frequency spectrum, and energy fluence carried by the electric field at each receiving radio antenna. Conventional electric-field reconstruction methods primarily focus on antennas with two horizontal polarizations. In this work, we introduce an analytic $χ^2$ minimization method that is applicable to both two and three polarizations. This solution has been verified for simple and realistic antenna responses, with a particular focus on inclined air showers. Our method achieves standard deviations better than 4\% and 6\% for the estimation of the Hilbert peak envelope amplitude of the electric field and the energy fluence, respectively, with an antenna-response-dependent bias. Additionally, we have studied the dependence of the method with arrival direction showing that it has a good performance in the zenith range from 63$^\circ$ up to 80$^\circ$. This work also demonstrates that incorporating vertically polarized antennas enhances the precision of the reconstruction, leading to a more accurate and reliable electric-field estimation for inclined air showers.

astro-ph.IM↗

arXiv2025

A comprehensive study of bond bipolaron superconductivity in triangular lattice

We employ the diagrammatic Monte Carlo method with a lattice path-integral formulation for both electron and phonon degrees of freedom to investigate the formation and properties of bond polarons and bipolarons on a two-dimensional triangular lattice. In the adiabatic regime ($ω/t < 1.0$), single polarons remain light with a small effective mass, while bipolarons remain compact and lightweight, resulting in a high superfluid transition temperature $T_c$. We systematically study the dependence of $T_c$ on electron-phonon coupling strength and on-site interaction in the bond bipolaron model. Our results show that a moderate on-site repulsion enhances $T_c$ by stabilizing compact yet lightweight bipolarons, leading to high-$T_c$ superconductivity in the dilute limit. Notably, the triangular lattice sustains relatively high $T_c$ across a wide range of phonon frequencies, outperforming square lattice geometry. This enhancement arises from the higher coordination number and the bond-centered nature of the electron-phonon coupling. These findings suggest that triangular lattice geometry offers a promising platform for realizing high-$T_c$ bipolaronic superconductivity.

cond-mat.supr-con↗

arXiv2025

Fast Gaussian Processes under Monotonicity Constraints

Gaussian processes (GPs) are widely used as surrogate models for complicated functions in scientific and engineering applications. In many cases, prior knowledge about the function to be approximated, such as monotonicity, is available and can be leveraged to improve model fidelity. Incorporating such constraints into GP models enhances predictive accuracy and reduces uncertainty, but remains a computationally challenging task for high-dimensional problems. In this work, we present a novel virtual point-based framework for building constrained GP models under monotonicity constraints, based on regularized linear randomize-then-optimize (RLRTO), which enables efficient sampling from a constrained posterior distribution by means of solving randomized optimization problems. We also enhance two existing virtual point-based approaches by replacing Gibbs sampling with the No U-Turn Sampler (NUTS) for improved efficiency. A Python implementation of these methods is provided and can be easily applied to a wide range of problems. This implementation is then used to validate the approaches on approximating a range of synthetic functions, demonstrating comparable predictive performance between all considered methods and significant improvements in computational efficiency with the two NUTS methods and especially with the RLRTO method. The framework is further applied to construct surrogate models for systems of differential equations.

stat.ML↗

arXiv2025

Low-Rank and Sparse Model Merging for Multi-Lingual Speech Recognition and Translation

Language diversity presents a significant challenge in speech-to-text (S2T) tasks, such as automatic speech recognition and translation. Traditional multi-lingual multi-task training approaches aim to address this by jointly optimising multiple speech recognition and translation tasks across various languages. While models like Whisper, built on these strategies, demonstrate strong performance, they still face issues of high computational cost, language interference, suboptimal training configurations, and limited extensibility. To overcome these challenges, we introduce LoRS-Merging (low-rank and sparse model merging), a novel technique designed to efficiently integrate models trained on different languages or tasks while preserving performance and reducing computational overhead. LoRS-Merging combines low-rank and sparse pruning to retain essential structures while eliminating redundant parameters, mitigating language interference, and enhancing extensibility. Experimental results across 10 languages demonstrate that LoRS-Merging significantly outperforms multi-lingual multi-task training, sequential training, and other merging methods, achieving over 20% improvement in normalised performance. Our findings suggest that model merging, particularly LoRS-Merging, is a scalable and effective complement to traditional multi-lingual training strategies for S2T applications.

cs.SD↗