arXiv subjects

Tao Zhang

Publications and source records attributed to Tao Zhang.

At least 253 records · Page 14Linked to original sources

arXiv2025

PCIE_Interaction Solution for Ego4D Social Interaction Challenge

This report presents our team's PCIE_Interaction solution for the Ego4D Social Interaction Challenge at CVPR 2025, addressing both Looking At Me (LAM) and Talking To Me (TTM) tasks. The challenge requires accurate detection of social interactions between subjects and the camera wearer, with LAM relying exclusively on face crop sequences and TTM combining speaker face crops with synchronized audio segments. In the LAM track, we employ face quality enhancement and ensemble methods. For the TTM task, we extend visual interaction analysis by fusing audio and visual cues, weighted by a visual quality score. Our approach achieved 0.81 and 0.71 mean average precision (mAP) on the LAM and TTM challenges leader board. Code is available at https://github.com/KanokphanL/PCIE_Ego4D_Social_Interaction

cs.CV↗

arXiv2025

PCIE_Pose Solution for EgoExo4D Pose and Proficiency Estimation Challenge

This report introduces our team's (PCIE_EgoPose) solutions for the EgoExo4D Pose and Proficiency Estimation Challenges at CVPR2025. Focused on the intricate task of estimating 21 3D hand joints from RGB egocentric videos, which are complicated by subtle movements and frequent occlusions, we developed the Hand Pose Vision Transformer (HP-ViT+). This architecture synergizes a Vision Transformer and a CNN backbone, using weighted fusion to refine the hand pose predictions. For the EgoExo4D Body Pose Challenge, we adopted a multimodal spatio-temporal feature integration strategy to address the complexities of body pose estimation across dynamic contexts. Our methods achieved remarkable performance: 8.31 PA-MPJPE in the Hand Pose Challenge and 11.25 MPJPE in the Body Pose Challenge, securing championship titles in both competitions. We extended our pose estimation solutions to the Proficiency Estimation task, applying core technologies such as transformer-based architectures. This extension enabled us to achieve a top-1 accuracy of 0.53, a SOTA result, in the Demonstrator Proficiency Estimation competition.

cs.CV↗

arXiv2025

BugRepro: Enhancing Android Bug Reproduction with Domain-Specific Knowledge Integration

Mobile application development is a fast-paced process where maintaining high-quality user experiences is crucial. Bug reproduction, a key aspect of maintaining app quality, often faces significant challenges. Specifically, when descriptions in bug reports are ambiguous or difficult to comprehend, current approaches fail to extract accurate information. Moreover, modern applications exhibit inherent complexity with multiple pages and diverse functionalities, making it challenging for existing methods to map the relevant information in bug reports to the corresponding UI elements that need to be manipulated. To address these challenges, we propose BugRepro, a novel technique that integrates domain-specific knowledge to enhance the accuracy and efficiency of bug reproduction. BugRepro adopts a Retrieval-Augmented Generation (RAG) approach. It retrieves similar bug reports along with their corresponding steps to reproduce (S2R) entities from an example-rich RAG document. In addition, BugRepro explores the graphical user interface (GUI) of the app and extracts transition graphs from the user interface to incorporate app-specific knowledge to guide large language models (LLMs) in their exploration process. Our experiments demonstrate that BugRepro significantly outperforms two state-of-the-art methods (ReCDroid and AdbGPT). For S2R entity extraction accuracy, it achieves a 7.57 to 28.89 percentage point increase over prior methods. For the bug reproduction success rate, the improvement reaches 74.55% and 152.63%. In reproduction efficiency, the gains are 0.72% and 76.68%.

cs.SE↗

arXiv2025

Active-Spin-State-Derived Descriptor for Hydrogen Evolution Reaction Catalysis

Spin states are pivotal in modulating the electrocatalytic activity of transition-metal (TM)-based compounds, yet quantitatively evaluating the activity-spin state correlation remains a formidable challenge. Here, we propose an 'activity index n' as a descriptor, to assess the activity of the spin states for the hydrogen evolution reaction (HER). n descriptor integrates three key electronic parameters: the proportion (P), broadening range (R) and center cc of active spin state, which collectively account for the electronic structure modulation induced by both the intrinsic active site and its local coordination environment. Using 1T-phase ZrSe2-anchored TM atoms (TM=Sc to Ni) as prototypes, we reveal that the correlation between Gibbs free energy and the n value follows a linear relation, namely, the vGH reduces as the n decreases. Notably, ZrSe2-Mn exhibits the optimal n value (-0.56), corresponding the best HER activity with a vGH of 0.04 eV closer to the thermoneutral ideal value (0 eV) than even Pt (vGH = -0.09 eV). This relationship suggests that n is the effective descriptor of active spin state for HER of TM-based catalysts. Our study brings fundamental insights into the HER activity-spin state correlation, offering new strategies for HER catalyst design.

cond-mat.mtrl-sci↗

arXiv2025

EGFormer: Towards Efficient and Generalizable Multimodal Semantic Segmentation

Recent efforts have explored multimodal semantic segmentation using various backbone architectures. However, while most methods aim to improve accuracy, their computational efficiency remains underexplored. To address this, we propose EGFormer, an efficient multimodal semantic segmentation framework that flexibly integrates an arbitrary number of modalities while significantly reducing model parameters and inference time without sacrificing performance. Our framework introduces two novel modules. First, the Any-modal Scoring Module (ASM) assigns importance scores to each modality independently, enabling dynamic ranking based on their feature maps. Second, the Modal Dropping Module (MDM) filters out less informative modalities at each stage, selectively preserving and aggregating only the most valuable features. This design allows the model to leverage useful information from all available modalities while discarding redundancy, thus ensuring high segmentation quality. In addition to efficiency, we evaluate EGFormer on a synthetic-to-real transfer task to demonstrate its generalizability. Extensive experiments show that EGFormer achieves competitive performance with up to 88 percent reduction in parameters and 50 percent fewer GFLOPs. Under unsupervised domain adaptation settings, it further achieves state-of-the-art transfer performance compared to existing methods.

cs.CV↗

arXiv2025

S2SBench: A Benchmark for Quantifying Intelligence Degradation in Speech-to-Speech Large Language Models

End-to-end speech large language models ((LLMs)) extend the capabilities of text-based models to directly process and generate audio tokens. However, this often leads to a decline in reasoning and generation performance compared to text input, a phenomenon referred to as intelligence degradation. To systematically evaluate this gap, we propose S2SBench, a benchmark designed to quantify performance degradation in Speech LLMs. It includes diagnostic datasets targeting sentence continuation and commonsense reasoning under audio input. We further introduce a pairwise evaluation protocol based on perplexity differences between plausible and implausible samples to measure degradation relative to text input. We apply S2SBench to analyze the training process of Baichuan-Audio, which further demonstrates the benchmark's effectiveness. All datasets and evaluation code are available at https://github.com/undobug/S2SBench.

cs.SD↗

arXiv2025

Cooperative Causal GraphSAGE

GraphSAGE is a widely used graph neural network. The introduction of causal inference has improved its robust performance and named as Causal GraphSAGE. However, Causal GraphSAGE focuses on measuring causal weighting among individual nodes, but neglecting the cooperative relationships among sampling nodes as a whole. To address this issue, this paper proposes Cooperative Causal GraphSAGE (CoCa-GraphSAGE), which combines cooperative game theory with Causal GraphSAGE. Initially, a cooperative causal structure model is constructed in the case of cooperation based on the graph structure. Subsequently, Cooperative Causal sampling (CoCa-sampling) algorithm is proposed, employing the Shapley values to calculate the cooperative contribution based on causal weights of the nodes sets. CoCa-sampling guides the selection of nodes with significant cooperative causal effects during the neighborhood sampling process, thus integrating the selected neighborhood features under cooperative relationships, which takes the sampled nodes as a whole and generates more stable target node embeddings. Experiments on publicly available datasets show that the proposed method has comparable classification performance to the compared methods and outperforms under perturbations, demonstrating the robustness improvement by CoCa-sampling.

cs.LG↗

arXiv2025

Confidence-Regulated Generative Diffusion Models for Reliable AI Agent Migration in Vehicular Metaverses

Vehicular metaverses are an emerging paradigm that merges intelligent transportation systems with virtual spaces, leveraging advanced digital twin and Artificial Intelligence (AI) technologies to seamlessly integrate vehicles, users, and digital environments. In this paradigm, vehicular AI agents are endowed with environment perception, decision-making, and action execution capabilities, enabling real-time processing and analysis of multi-modal data to provide users with customized interactive services. Since vehicular AI agents require substantial resources for real-time decision-making, given vehicle mobility and network dynamics conditions, the AI agents are deployed in RoadSide Units (RSUs) with sufficient resources and dynamically migrated among them. However, AI agent migration requires frequent data exchanges, which may expose vehicular metaverses to potential cyber attacks. To this end, we propose a reliable vehicular AI agent migration framework, achieving reliable dynamic migration and efficient resource scheduling through cooperation between vehicles and RSUs. Additionally, we design a trust evaluation model based on the theory of planned behavior to dynamically quantify the reputation of RSUs, thereby better accommodating the personalized trust preferences of users. We then model the vehicular AI agent migration process as a partially observable markov decision process and develop a Confidence-regulated Generative Diffusion Model (CGDM) to efficiently generate AI agent migration decisions. Numerical results demonstrate that the CGDM algorithm significantly outperforms baseline methods in reducing system latency and enhancing robustness against cyber attacks.

cs.LG↗

arXiv2025

Measurement of two-neutrino double electron capture half-life of $^{124}$Xe with PandaX-4T

Detailed studies of two-neutrino double electron capture (2$ν$DEC) is a crucial step towards searching for the neutrino-less mode to explore the Majorana nature of neutrinos. We have measured precisely the half-life of the 2$ν$DEC process in $^{124}$Xe, utilizing a total exposure of 1.73 tonne$\cdot$year from the commissioning run and the first science run of the PandaX-4T experiment. A time-dependent background model in the $\mathcal{O}$(10 keV) energy is constructed for the first time in PandaX-4T data. With an unbinned maximum likelihood fit, we determine the half-life of the 2$ν$DEC process to be $(1.03\pm0.15_{\rm stat}\pm0.08_{\rm sys})\times 10^{22}$$\,$yr. Furthermore, we have evaluated the branching ratio for both electrons captured from the $K$ shell ($KK$) to be $(65\pm5)\%$, which aligns with the $^{124}$Xe nuclear model calculations within 1.8$\,$$σ$.

nucl-ex↗

arXiv2025

On lattice tilings of $\mathbb{Z}^n$ by limited magnitude error balls $\mathcal{B}(n,2,k_{1},k_{2})$ with $k_1>k_2$

Lattice tilings of $\mathbb{Z}^n$ by limited-magnitude error balls correspond to linear perfect codes under such error models and play a crucial role in flash memory applications. In this work, we establish three main results. First, we fully determine the existence of lattice tilings by $\mathcal{B}(n,2,3,0)$ in all dimensions $n$. Second, we completely resolve the case $k_1=k_2+1$. Finally, we prove that for any integers $k_1>k_2\ge0$ where $k_1+k_2+1$ is composite, no lattice tiling of $\mathbb{Z}^n$ by the error ball $\mathcal{B}(n,2,k_1,k_2)$ exists for sufficiently large $n$.

math.CO↗

arXiv2025

Search for Solar Boosted Dark Matter Particles at the PandaX-4T Experiment

We present a novel constraint on light dark matter utilizing $1.54$ tonne$\cdot$year of data acquired from the PandaX-4T dual-phase xenon time projection chamber. This constraint is derived through detecting electronic recoil signals resulting from the interaction with solar-enhanced dark matter flux. Low-mass dark matter particles, lighter than a few MeV/$c^2$, can scatter with the thermal electrons in the Sun. Consequently, with higher kinetic energy, the boosted dark matter component becomes detectable via contact scattering with xenon electrons, resulting in a few keV energy deposition that exceeds the threshold of PandaX-4T. We calculate the expected recoil energy in PandaX-4T considering the Sun's acceleration and the detection capabilities of the xenon detector. The first experimental search results using the xenon detector yield the most stringent cross-section of $3.51 \times 10^{-39}~\mathrm{cm}^2$ at $0.08~\mathrm{MeV}$/$c^2$ for a solar boosted dark matter mass ranging from $0.02$ to $10~ \mathrm{MeV}$/$c^2$, achieving a 23 fold improvement compared with earlier experimental studies.

hep-ex↗

arXiv2025

Observation of Near-Critical Kibble-Zurek Scaling in Rydberg Atom Arrays

The Kibble-Zurek scaling reveals the universal dynamics when a system is linearly ramped across a symmetry-breaking phase transition. However, in reality, inevitable finite-size effects or symmetrybreaking perturbations can often smear out the critical point and render the phase transition into a smooth crossover. In this letter, we show experimentally that the precise Kibble-Zurek scaling can be retained in the near-critical crossover regime, not necessarily crossing the critical point strictly. The key ingredient to achieving this near-critical Kibble-Zurek scaling is that the system size and the symmetry-breaking field must be appropriately scaled following the variation of ramping speeds. The experiment is performed in a reconfigurable Rydberg atom array platform, where the Rydberg blockade effect induces a Z2 symmetry-breaking transition. The atom array platform enables precise control of the system size and the zigzag geometry as a symmetry-breaking field. Therefore, we can demonstrate notable differences in the precision of the Kibble-Zurek scaling with or without properly scaling the system size and the zigzag geometry. Our results strengthen the Kibble-Zurek scaling as an increasingly valuable tool for investigating phase transition in quantum simulation platforms.

cond-mat.quant-gas↗

arXiv2025

M2PDE: Compositional Generative Multiphysics and Multi-component PDE Simulation

Multiphysics simulation, which models the interactions between multiple physical processes, and multi-component simulation of complex structures are critical in fields like nuclear and aerospace engineering. Previous studies use numerical solvers or ML-based surrogate models for these simulations. However, multiphysics simulations typically require integrating multiple specialized solvers-each for a specific physical process-into a coupled program, which introduces significant development challenges. Furthermore, existing numerical algorithms struggle with highly complex large-scale structures in multi-component simulations. Here we propose compositional Multiphysics and Multi-component PDE Simulation with Diffusion models (M2PDE) to overcome these challenges. During diffusion-based training, M2PDE learns energy functions modeling the conditional probability of one physical process/component conditioned on other processes/components. In inference, M2PDE generates coupled multiphysics and multi-component solutions by sampling from the joint probability distribution. We evaluate M2PDE on two multiphysics tasks-reaction-diffusion and nuclear thermal coupling-where it achieves more accurate predictions than surrogate models in challenging scenarios. We then apply it to a multi-component prismatic fuel element problem, demonstrating that M2PDE scales from single-component training to a 64-component structure and outperforms existing domain-decomposition and graph-based approaches. The code is available at https://github.com/AI4Science-WestlakeU/M2PDE.

cs.LG↗

arXiv2025

Buckling of residually stressed cylindrical tubes under compression

We evaluate the loss of stability of axially compressed slender and thick-walled tubes subject to a residual stress distribution. The nonlinear theory of elasticity, when used to analyze the underlying deformation, shows that the residual stress induces preferred directions in the reference configuration. The incremental theory, given in Stroh form, is used to derive an exact bifurcation condition. The critical stretch and the associated critical buckling mode are identified for axisymmetric and asymmetric increments in the deformation. Mode transitions are illustrated as the tube slenderness varies. For slender tubes, Euler buckling is energetically favorable, and the effect of residual stress is negligible. However, for short and thick-walled tubes where barreling mode is dominant, the residual stress significantly affects the buckling behavior and may eliminate barreling instability. We show that, depending on its magnitude and direction, residual stress can either accelerate or delay instability. Phase diagrams for various modes are obtained and provide insight into pattern selection across different tube geometries.

cond-mat.soft↗

arXiv2025

On Path to Multimodal Generalist: General-Level and General-Bench

The Multimodal Large Language Model (MLLM) is currently experiencing rapid growth, driven by the advanced capabilities of LLMs. Unlike earlier specialists, existing MLLMs are evolving towards a Multimodal Generalist paradigm. Initially limited to understanding multiple modalities, these models have advanced to not only comprehend but also generate across modalities. Their capabilities have expanded from coarse-grained to fine-grained multimodal understanding and from supporting limited modalities to arbitrary ones. While many benchmarks exist to assess MLLMs, a critical question arises: Can we simply assume that higher performance across tasks indicates a stronger MLLM capability, bringing us closer to human-level AI? We argue that the answer is not as straightforward as it seems. This project introduces General-Level, an evaluation framework that defines 5-scale levels of MLLM performance and generality, offering a methodology to compare MLLMs and gauge the progress of existing systems towards more robust multimodal generalists and, ultimately, towards AGI. At the core of the framework is the concept of Synergy, which measures whether models maintain consistent capabilities across comprehension and generation, and across multiple modalities. To support this evaluation, we present General-Bench, which encompasses a broader spectrum of skills, modalities, formats, and capabilities, including over 700 tasks and 325,800 instances. The evaluation results that involve over 100 existing state-of-the-art MLLMs uncover the capability rankings of generalists, highlighting the challenges in reaching genuine AI. We expect this project to pave the way for future research on next-generation multimodal foundation models, providing a robust infrastructure to accelerate the realization of AGI. Project page: https://generalist.top/

cs.CV↗

arXiv2025

CFBench: A Comprehensive Constraints-Following Benchmark for LLMs

The adeptness of Large Language Models (LLMs) in comprehending and following natural language instructions is critical for their deployment in sophisticated real-world applications. Existing evaluations mainly focus on fragmented constraints or narrow scenarios, but they overlook the comprehensiveness and authenticity of constraints from the user's perspective. To bridge this gap, we propose CFBench, a large-scale Comprehensive Constraints Following Benchmark for LLMs, featuring 1,000 curated samples that cover more than 200 real-life scenarios and over 50 NLP tasks. CFBench meticulously compiles constraints from real-world instructions and constructs an innovative systematic framework for constraint types, which includes 10 primary categories and over 25 subcategories, and ensures each constraint is seamlessly integrated within the instructions. To make certain that the evaluation of LLM outputs aligns with user perceptions, we propose an advanced methodology that integrates multi-dimensional assessment criteria with requirement prioritization, covering various perspectives of constraints, instructions, and requirement fulfillment. Evaluating current leading LLMs on CFBench reveals substantial room for improvement in constraints following, and we further investigate influencing factors and enhancement strategies. The data and code are publicly available at https://github.com/PKU-Baichuan-MLSystemLab/CFBench

cs.CL↗

arXiv2025

Unaligned RGB Guided Hyperspectral Image Super-Resolution with Spatial-Spectral Concordance

Hyperspectral images super-resolution aims to improve the spatial resolution, yet its performance is often limited at high-resolution ratios. The recent adoption of high-resolution reference images for super-resolution is driven by the poor spatial detail found in low-resolution HSIs, presenting it as a favorable method. However, these approaches cannot effectively utilize information from the reference image, due to the inaccuracy of alignment and its inadequate interaction between alignment and fusion modules. In this paper, we introduce a Spatial-Spectral Concordance Hyperspectral Super-Resolution (SSC-HSR) framework for unaligned reference RGB guided HSI SR to address the issues of inaccurate alignment and poor interactivity of the previous approaches. Specifically, to ensure spatial concordance, i.e., align images more accurately across resolutions and refine textures, we construct a Two-Stage Image Alignment with a synthetic generation pipeline in the image alignment module, where the fine-tuned optical flow model can produce a more accurate optical flow in the first stage and warp model can refine damaged textures in the second stage. To enhance the interaction between alignment and fusion modules and ensure spectral concordance during reconstruction, we propose a Feature Aggregation module and an Attention Fusion module. In the feature aggregation module, we introduce an Iterative Deformable Feature Aggregation block to achieve significant feature matching and texture aggregation with the fusion multi-scale results guidance, iteratively generating learnable offset. Besides, we introduce two basic spectral-wise attention blocks in the attention fusion module to model the inter-spectra interactions. Extensive experiments on three natural or remote-sensing datasets show that our method outperforms state-of-the-art approaches on both quantitative and qualitative evaluations.

cs.CV↗

arXiv2025

On-chip Non-Hermitian Cavity Quantum Electrodynamics

Exceptional points (EPs) promise revolutionary control over quantum light-matter interactions. Here, we experimentally demonstrate flexible and reversible engineering of quantum vacuum fluctuation in an integrated microcavity supporting chiral Eps. We develop a hybrid lithium niobate (LN)-GaAs quantum photonic platform, seamlessly combining high-quality quantum emitters, a low-loss photonic circuit, efficient electro-optic (EO) effect, and local strain actuator in a single device. Chiral EPs are implemented by dynamically tuning the coupling between the modes associated with a micro-ring resonator, resulting in anomalous spontaneous emission dynamic with a 7-fold modulation of the lifetime (120 ps to 850 ps). Meanwhile, we reshape single-photon spectra via cavity local density of states (LDOS) engineering and generate non-Lorentzian spectral profiles: squared-Lorentzian, Fano-like, and EP-induced transparency (EPIT), a suppression of emission at zero detuning. This work unveils exotic cavity quantum electrodynamics (cQED) effects unique to EPs and establishes a universal paradigm for non-Hermitian quantum photonics.

physics.optics↗