arXiv subjects

Hao Wang

Publications and source records attributed to Hao Wang.

At least 775 records · Page 43Linked to original sources

arXiv2025

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

Large language models (LLMs) have demonstrated remarkable proficiency in mainstream academic disciplines such as mathematics, physics, and computer science. However, human knowledge encompasses over 200 specialized disciplines, far exceeding the scope of existing benchmarks. The capabilities of LLMs in many of these specialized fields-particularly in light industry, agriculture, and service-oriented disciplines-remain inadequately evaluated. To address this gap, we present SuperGPQA, a comprehensive benchmark that evaluates graduate-level knowledge and reasoning capabilities across 285 disciplines. Our benchmark employs a novel Human-LLM collaborative filtering mechanism to eliminate trivial or ambiguous questions through iterative refinement based on both LLM responses and expert feedback. Our experimental results reveal significant room for improvement in the performance of current state-of-the-art LLMs across diverse knowledge domains (e.g., the reasoning-focused model DeepSeek-R1 achieved the highest accuracy of 61.82% on SuperGPQA), highlighting the considerable gap between current model capabilities and artificial general intelligence. Additionally, we present comprehensive insights from our management of a large-scale annotation process, involving over 80 expert annotators and an interactive Human-LLM collaborative system, offering valuable methodological guidance for future research initiatives of comparable scope.

cs.CL↗

arXiv2025

StyleStudio: Text-Driven Style Transfer with Selective Control of Style Elements

Text-driven style transfer aims to merge the style of a reference image with content described by a text prompt. Recent advancements in text-to-image models have improved the nuance of style transformations, yet significant challenges remain, particularly with overfitting to reference styles, limiting stylistic control, and misaligning with textual content. In this paper, we propose three complementary strategies to address these issues. First, we introduce a cross-modal Adaptive Instance Normalization (AdaIN) mechanism for better integration of style and text features, enhancing alignment. Second, we develop a Style-based Classifier-Free Guidance (SCFG) approach that enables selective control over stylistic elements, reducing irrelevant influences. Finally, we incorporate a teacher model during early generation stages to stabilize spatial layouts and mitigate artifacts. Our extensive evaluations demonstrate significant improvements in style transfer quality and alignment with textual prompts. Furthermore, our approach can be integrated into existing style transfer frameworks without fine-tuning.

cs.CV↗

arXiv2025

An Empirical Study of the Impact of Federated Learning on Machine Learning Model Accuracy

Federated Learning (FL) enables distributed ML model training on private user data at the global scale. Despite the potential of FL demonstrated in many domains, an in-depth view of its impact on model accuracy remains unclear. In this paper, we investigate, systematically, how this learning paradigm can affect the accuracy of state-of-the-art ML models for a variety of ML tasks. We present an empirical study that involves various data types: text, image, audio, and video, and FL configuration knobs: data distribution, FL scale, client sampling, and local and global computations. Our experiments are conducted in a unified FL framework to achieve high fidelity, with substantial human efforts and resource investments. Based on the results, we perform a quantitative analysis of the impact of FL, and highlight challenging scenarios where applying FL degrades the accuracy of the model drastically and identify cases where the impact is negligible. The detailed and extensive findings can benefit practical deployments and future development of FL.

cs.LG↗

arXiv2025

StableToolBench-MirrorAPI: Modeling Tool Environments as Mirrors of 7,000+ Real-World APIs

The rapid advancement of large language models (LLMs) has spurred significant interest in tool learning, where LLMs are augmented with external tools to tackle complex tasks. However, existing tool environments face challenges in balancing stability, scalability, and realness, particularly for benchmarking purposes. To address this problem, we propose MirrorAPI, a novel framework that trains specialized LLMs to accurately simulate real API responses, effectively acting as "mirrors" to tool environments. Using a comprehensive dataset of request-response pairs from 7,000+ APIs, we employ supervised fine-tuning and chain-of-thought reasoning to enhance simulation fidelity. MirrorAPI achieves superior accuracy and stability compared to state-of-the-art methods, as demonstrated by its performance on the newly constructed MirrorAPI-Bench and its integration into StableToolBench.

cs.CL↗

arXiv2025

GAA-TSO: Geometry-Aware Assisted Depth Completion for Transparent and Specular Objects

Transparent and specular objects are frequently encountered in daily life, factories, and laboratories. However, due to the unique optical properties, the depth information on these objects is usually incomplete and inaccurate, which poses significant challenges for downstream robotics tasks. Therefore, it is crucial to accurately restore the depth information of transparent and specular objects. Previous depth completion methods for these objects usually use RGB information as an additional channel of the depth image to perform depth prediction. Due to the poor-texture characteristics of transparent and specular objects, these methods that rely heavily on color information tend to generate structure-less depth predictions. Moreover, these 2D methods cannot effectively explore the 3D structure hidden in the depth channel, resulting in depth ambiguity. To this end, we propose a geometry-aware assisted depth completion method for transparent and specular objects, which focuses on exploring the 3D structural cues of the scene. Specifically, besides extracting 2D features from RGB-D input, we back-project the input depth to a point cloud and build the 3D branch to extract hierarchical scene-level 3D structural features. To exploit 3D geometric information, we design several gated cross-modal fusion modules to effectively propagate multi-level 3D geometric features to the image branch. In addition, we propose an adaptive correlation aggregation strategy to appropriately assign 3D features to the corresponding 2D features. Extensive experiments on ClearGrasp, OOD, TransCG, and STD datasets show that our method outperforms other state-of-the-art methods. We further demonstrate that our method significantly enhances the performance of downstream robotic grasping tasks.

cs.CV↗

arXiv2025

Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition

In skeleton-based action recognition, a key challenge is distinguishing between actions with similar trajectories of joints due to the lack of image-level details in skeletal representations. Recognizing that the differentiation of similar actions relies on subtle motion details in specific body parts, we direct our approach to focus on the fine-grained motion of local skeleton components. To this end, we introduce ProtoGCN, a Graph Convolutional Network (GCN)-based model that breaks down the dynamics of entire skeleton sequences into a combination of learnable prototypes representing core motion patterns of action units. By contrasting the reconstruction of prototypes, ProtoGCN can effectively identify and enhance the discriminative representation of similar actions. Without bells and whistles, ProtoGCN achieves state-of-the-art performance on multiple benchmark datasets, including NTU RGB+D, NTU RGB+D 120, Kinetics-Skeleton, and FineGYM, which demonstrates the effectiveness of the proposed method. The code is available at https://github.com/firework8/ProtoGCN.

cs.CV↗

arXiv2025

Training Video Foundation Models with NVIDIA NeMo

Video Foundation Models (VFMs) have recently been used to simulate the real world to train physical AI systems and develop creative visual experiences. However, there are significant challenges in training large-scale, high quality VFMs that can generate high-quality videos. We present a scalable, open-source VFM training pipeline with NVIDIA NeMo, providing accelerated video dataset curation, multimodal data loading, and parallelized video diffusion model training and inference. We also provide a comprehensive performance analysis highlighting best practices for efficient VFM training and inference.

cs.CV↗

arXiv2025

Dynamics of a coupled nonlocal PDE-ODE system with spatial memory: well-posedness, stability, and bifurcation analysis

Nonlocal aggregation-diffusion models, when coupled with a spatial map, can capture cognitive and memory-based influences on animal movement and population-level patterns. In this work, we study a one-dimensional reaction-diffusion-aggregation system in which a population's spatiotemporal dynamics are tightly linked to a separate, dynamically updating map. Depending on the local population density, the map amplifies and suppresses certain landscape regions and contributes to directed movement through a nonlocal spatial kernel. After establishing the well-posedness of the coupled PDE-ODE system, we perform a linear stability analysis to identify critical aggregation strengths. We then perform a rigorous bifurcation analysis to determine the precise solution behavior at a steady state near these critical thresholds, deciding whether the bifurcation is sub- or supercritical and the stability of the emergent branch. Based on our analytical findings, we highlight several interesting biological consequences. First, we observe that whether the spatial map functions as attractive or repulsive depends precisely on the map's relative excitation rate versus adaptory rate: when the excitatory effect is larger (smaller) than the adaptatory effect, the map is attractive (repulsive). Second, in the absence of growth dynamics, populations can only form a single aggregate. Therefore, the presence of intraspecific competition is necessary to drive multi-peaked aggregations, reflecting higher-frequency spatial patterns. Finally, we show how subcritical bifurcations can trigger abrupt shifts in average population abundance, suggesting a tipping-point phenomenon in which moderate changes in movement parameters can cause a sudden population decline.

math.AP↗

arXiv2025

A complete waveform comparison of post-Newtonian and numerical relativity in eccentric orbits

This study presents a thorough comparative analysis between post-Newtonian (PN) and numerically relativistic (NR) waveforms in eccentric orbits, covering nonspinning and spin-aligned configurations. The comparison examines frequency, amplitude, and phase characteristics of various harmonic modes, such as 22, 21, 33, 32, 44, 43, and 55 modes. The study utilizes eccentric PN waveforms based on 3PN quasi-Keplerian parameterization with 3PN radiative reaction, surpassing Newtonian quadrupole moment with higher-order moments. NR waveforms from RIT and SXS catalogs span mass ratios from 1/4 to 1, eccentricities up to 0.45, and durations exceeding $17000M$ across nonspinning and spin-aligned configurations. Focusing on the 22 mode, frequency comparisons between quadrupole and higher-order moments of $Ψ_4^{22}$ and $h^{22}$ were conducted. Amplitude comparisons revealed superior accuracy in quadrupole moments of $Ψ_4^{22}$. Analysis of total 180 sets of eccentric waveforms showed increasing fitting residuals with rising eccentricity, correlating with smaller mass ratios. Comparisons of initial eccentricity from PN fitting, 3PN quasi-Keplerian parameterization, and RIT/SXS catalogs revealed alignment discrepancies. Frequency, phase, and amplitude comparisons of 22 modes showed consistent inspiral behavior between PN and NR, with divergences near merger for nonspinning PN and pre-200M for spin-aligned PN.

gr-qc↗

arXiv2025

Ranking dynamics of urban mobility

Human mobility, a pivotal aspect of urban dynamics, displays a profound and multifaceted relationship with urban sustainability. Despite considerable efforts analyzing mobility patterns over decades, the ranking dynamics of urban mobility has received limited attention. This study aims to contribute to the field by investigating changes in rank and size of hourly inflows to various locations across 60 Chinese cities throughout the day. We find that the rank-size distribution of hourly inflows over the course of the day is stable across cities. To uncover the microdynamics beneath the stable aggregate distribution amidst shifting location inflows, we analyzed consecutive-hour inflow size and ranking variations. Our findings reveal a dichotomy: locations with higher daily average inflow display a clear monotonic trend, with more pronounced increases or decreases in consecutive-hour inflow. In contrast, ranking variations exhibit a non-monotonic pattern, distinguished by the stability of not only the top and bottom rankings but also those in moderately-inflowed locations. Finally, we compare ranking dynamics across cities using a ranking metric, the rank turnover. The results advance our understanding of urban mobility dynamics, providing a basis for applications in urban planning and traffic engineering.

physics.soc-ph↗

arXiv2025

A Mesh Is Worth 512 Numbers: Spectral-domain Diffusion Modeling for High-dimension Shape Generation

Recent advancements in learning latent codes derived from high-dimensional shapes have demonstrated impressive outcomes in 3D generative modeling. Traditionally, these approaches employ a trained autoencoder to acquire a continuous implicit representation of source shapes, which can be computationally expensive. This paper introduces a novel framework, spectral-domain diffusion for high-quality shape generation SpoDify, that utilizes singular value decomposition (SVD) for shape encoding. The resulting eigenvectors can be stored for subsequent decoding, while generative modeling is performed on the eigenfeatures. This approach efficiently encodes complex meshes into continuous implicit representations, such as encoding a 15k-vertex mesh to a 512-dimensional latent code without learning. Our method exhibits significant advantages in scenarios with limited samples or GPU resources. In mesh generation tasks, our approach produces high-quality shapes that are comparable to state-of-the-art methods.

cs.CV↗

arXiv2025

Quantum Langevin Dynamics for Optimization

We initiate the study of utilizing Quantum Langevin Dynamics (QLD) to solve optimization problems, particularly those non-convex objective functions that present substantial obstacles for traditional gradient descent algorithms. Specifically, we examine the dynamics of a system coupled with an infinite heat bath. This interaction induces both random quantum noise and a deterministic damping effect to the system, which nudge the system towards a steady state that hovers near the global minimum of objective functions. We theoretically prove the convergence of QLD in convex landscapes, demonstrating that the average energy of the system can approach zero in the low temperature limit with an exponential decay rate correlated with the evolution time. Numerically, we first show the energy dissipation capability of QLD by retracing its origins to spontaneous emission. Furthermore, we conduct detailed discussion of the impact of each parameter. Finally, based on the observations when comparing QLD with classical Fokker-Plank-Smoluchowski equation, we propose a time-dependent QLD by making temperature and $\hbar$ time-dependent parameters, which can be theoretically proven to converge better than the time-independent case and also outperforms a series of state-of-the-art quantum and classical optimization algorithms in many non-convex landscapes.

quant-ph↗

arXiv2025

The asymptotic behavior of Lorentz-violating photon fields

In this work, we derive the Newman-Penrose formalism of Maxwell's equations using two approaches: differential forms and intrinsic derivatives. Denoting $(k_{AF})^μ$ as $k^μ$, with $k^μ=(k^t,k^r,0,0)$ in spherically symmetric spacetimes, we show that the expansion in $r^{-1}$ fails to produce consistent, closed solutions due to the inability to separate Lorentz-violating (LV) phase factors, as the Lorentz-invariant (LI) null tetrad does not adapt to the LV wavefront. Moreover, with exact formal solutions, we demonstrate that the expansion is nonperturbative in the LV parameter $k^2\equiv k^t-k^r$. For $r\gg1/k^2$, higher powers of $k^2$ dominate over lower powers, as the latter decay more rapidly with increasing $r$. Although the Coulomb mode $ϕ_1\sim\mathcal{O}(\ln{r}/r^2)$ deviates from the LI expectation $\mathcal{O}(r^{-2})$ due to LV corrections, the leading outgoing radiation mode remains unaffected, i.e., $ϕ_2\sim\mathcal{O}(r^{-1})$. Given the constraint $|k_{AF}|\le10^{-44}$GeV \cite{CMBLV-N}, the three complex scalars $ϕ_a$ ($a=0,1,2$) still obey the peeling theorem: $ϕ_a\sim\mathcal{O}(r^{(a-3)}),~a=0,1,2$ for large, finite distances.

hep-ph↗

arXiv2025

Search for Double Beta Decay of $^{136}$Xe to the $0^+_1$ Excited State of $^{136}$Ba with PandaX-4T

We perform a search of double beta decay of $^{136}$Xe to the excited state, $0^+_1$, of $^{136}$Ba (2$νββ$-0$_1^+$), using the dual-phase xenon detector of PandaX-4T with the first 94.9-day commissioning data. The multi-site events are reconstructed up to the MeV energy scale, which helps to improve the background model significantly. The background contribution from the stainless steel platform outside PandaX-4T cryostat is evaluated for the first time. No significant evidence for 2$νββ$-$0_1^+$ is observed, resulting in a lower limit on half-life of $7.5 \times 10^{22}$ yr at the 90% confidence level. This is the first experimental limit on such a rare decay in a natural xenon-based detector.

nucl-ex↗

arXiv2025

Search for MeV-Scale Axionlike Particles and Dark Photons with PandaX-4T

Axionlike particles (ALPs) and dark photons (DPs) are viable dark matter particle candidates. We have searched for possible ALP/DP signals in the PandaX-4T liquid xenon detector using 440 kg$\cdot$yr of data. A binned likelihood fit is constructed to search for possible mono-energetic peaks induced by the absorption processes between ALPs/DPs and atomic electrons of xenon. A detailed temporal model of decays associated with xenon isotopes is introduced to constrain the number of background events. No signal excess over background expectations is observed, and we have established the most stringent exclusion limits for most ALP/DP masses across the range of 150 keV/$c^2$ to 1 MeV/$c^2$. The improvement is particularly significant within the mass range of \text{150-400}~keV/$c^2$, with the average factor of 3.5 compared to previous results.

hep-ex↗

arXiv2025

StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models

Large Language Models (LLMs) have witnessed remarkable advancements in recent years, prompting the exploration of tool learning, which integrates LLMs with external tools to address diverse real-world challenges. Assessing the capability of LLMs to utilise tools necessitates large-scale and stable benchmarks. However, previous works relied on either hand-crafted online tools with limited scale, or large-scale real online APIs suffering from instability of API status. To address this problem, we introduce StableToolBench, a benchmark evolving from ToolBench, proposing a virtual API server and stable evaluation system. The virtual API server contains a caching system and API simulators which are complementary to alleviate the change in API status. Meanwhile, the stable evaluation system designs solvable pass and win rates using GPT-4 as the automatic evaluator to eliminate the randomness during evaluation. Experimental results demonstrate the stability of StableToolBench, and further discuss the effectiveness of API simulators, the caching system, and the evaluator system.

cs.CL↗

arXiv2025

RASD: Retrieval-Augmented Speculative Decoding

Speculative decoding accelerates inference in large language models (LLMs) by generating draft tokens for target model verification. Current approaches for obtaining draft tokens rely on lightweight draft models or additional model structures to generate draft tokens and retrieve context from databases. Due to the draft model's small size and limited training data, model-based speculative decoding frequently becomes less effective in out-of-domain scenarios. Additionally, the time cost of the drafting phase results in a low upper limit on acceptance length during the verification step, limiting overall efficiency. This paper proposes RASD (Retrieval-Augmented Speculative Decoding), which adopts retrieval methods to enhance model-based speculative decoding. We introduce tree pruning and tree fusion to achieve this. Specifically, we develop a pruning method based on the draft model's probability distribution to construct the optimal retrieval tree. Second, we employ the longest prefix matching algorithm to merge the tree generated by the draft model with the retrieval tree, resulting in a unified tree for verification. Experimental results demonstrate that RASD achieves state-of-the-art inference acceleration across tasks such as DocQA, Summary, Code, and In-Domain QA. Moreover, RASD exhibits strong scalability, seamlessly integrating with various speculative decoding approaches, including both generation-based and retrieval-based methods.

cs.CL↗

arXiv2025

Designing a Dataset for Convolutional Neural Networks to Predict Space Groups Consistent with Extinction Laws

In this paper, a dataset of one-dimensional powder diffraction patterns was designed with new strategy to train Convolutional Neural Networks for predicting space groups. The diffraction pattern was calculated based on lattice parameters and Extinction Laws, instead of the traditional approach of generating it from a crystallographic database. This paper demonstrates that the new strategy is more effective than the conventional method. As a result, the model trained on the cubic and tetragonal training set from the newly designed dataset achieves prediction accuracy that matches the theoretical maximums calculated based on Extinction Laws. These results demonstrate that machine learning-based prediction can be both physically reasonable and reliable. Additionally, the model trained on our newly designed dataset shows excellent generalization capability, much better than the one trained on a traditionally designed dataset.

cs.NE↗