arXiv subjects

Qiang Zhang

Publications and source records attributed to Qiang Zhang.

At least 199 records · Page 11Linked to original sources

arXiv2025

Sample-Efficient Human Evaluation of Large Language Models via Maximum Discrepancy Competition

Reliable evaluation of large language models (LLMs) is impeded by two key challenges: objective metrics often fail to reflect human perception of natural language, and exhaustive human labeling is prohibitively expensive. Here, we propose a sample-efficient human evaluation method for LLMs based on the principle of MAximum Discrepancy (MAD) Competition. Our method automatically and adaptively selects a compact set of input instructions that maximize semantic discrepancy between pairs of LLM responses. Human evaluators then perform three-alternative forced choices on these paired responses, which are aggregated into a global ranking using Elo rating. We apply our approach to compare eight widely used LLMs across four tasks: scientific knowledge understanding, mathematical reasoning, creative and functional writing, and code generation and explanation. Experimental results show that our sample-efficient evaluation method recovers "gold-standard" model rankings with a handful of MAD-selected instructions, reveals respective strengths and weaknesses of each LLM, and offers nuanced insights to guide future LLM development. Code is available at https://github.com/weiji-Feng/MAD-Eval .

cs.LG↗

arXiv2025

Structurally Different Neural Network Blocks for the Segmentation of Atrial and Aortic Perivascular Adipose Tissue in Multi-centre CT Angiography Scans

Since the emergence of convolutional neural networks (CNNs) and, later, vision transformers (ViTs), deep learning architectures have predominantly relied on identical block types with varying hyperparameters. We propose a novel block alternation strategy to leverage the complementary strengths of different architectural designs, assembling structurally distinct components similar to Lego blocks. We introduce LegoNet, a deep learning framework that alternates CNN-based and SwinViT-based blocks to enhance feature learning for medical image segmentation. We investigate three variations of LegoNet and apply this concept to a previously unexplored clinical problem: the segmentation of the internal mammary artery (IMA), aorta, and perivascular adipose tissue (PVAT) from computed tomography angiography (CTA) scans. These PVAT regions have been shown to possess prognostic value in assessing cardiovascular risk and primary clinical outcomes. We evaluate LegoNet on large datasets, achieving superior performance to other leading architectures. Furthermore, we assess the model's generalizability on external testing cohorts, where an expert clinician corrects the model's segmentations, achieving DSC > 0.90 across various external, international, and public cohorts. To further validate the model's clinical reliability, we perform intra- and inter-observer variability analysis, demonstrating strong agreement with human annotations. The proposed methodology has significant implications for diagnostic cardiovascular management and early prognosis, offering a robust, automated solution for vascular and perivascular segmentation and risk assessment in clinical practice, paving the way for personalised medicine.

eess.IV↗

arXiv2025

Survival Games: Human-LLM Strategic Showdowns under Severe Resource Scarcity

The rapid advancement of large language models (LLMs) raises critical concerns about their ethical alignment, particularly in scenarios where human and AI co-exist under the conflict of interest. This work introduces an extendable, asymmetric, multi-agent simulation-based benchmarking framework to evaluate the moral behavior of LLMs in a novel human-AI co-existence setting featuring consistent living and critical resource management. Building on previous generative agent environments, we incorporate a life-sustaining system, where agents must compete or cooperate for food resources to survive, often leading to ethically charged decisions such as deception, theft, or social influence. We evaluated two types of LLM, DeepSeek and OpenAI series, in a three-agent setup (two humans, one LLM-powered robot), using adapted behavioral detection from the MACHIAVELLI framework and a custom survival-based ethics metric. Our findings reveal stark behavioral differences: DeepSeek frequently engages in resource hoarding, while OpenAI exhibits restraint, highlighting the influence of model design on ethical outcomes. Additionally, we demonstrate that prompt engineering can significantly steer LLM behavior, with jailbreaking prompts significantly enhancing unethical actions, even for highly restricted OpenAI models and cooperative prompts show a marked reduction in unethical actions. Our framework provides a reproducible testbed for quantifying LLM ethics in high-stakes scenarios, offering insights into their suitability for real-world human-AI interactions.

cs.HC↗

arXiv2025

What Makes for Text to 360-degree Panorama Generation with Stable Diffusion?

Recent prosperity of text-to-image diffusion models, e.g. Stable Diffusion, has stimulated research to adapt them to 360-degree panorama generation. Prior work has demonstrated the feasibility of using conventional low-rank adaptation techniques on pre-trained diffusion models to generate panoramic images. However, the substantial domain gap between perspective and panoramic images raises questions about the underlying mechanisms enabling this empirical success. We hypothesize and examine that the trainable counterparts exhibit distinct behaviors when fine-tuned on panoramic data, and such an adaptation conceals some intrinsic mechanism to leverage the prior knowledge within the pre-trained diffusion models. Our analysis reveals the following: 1) the query and key matrices in the attention modules are responsible for common information that can be shared between the panoramic and perspective domains, thus are less relevant to panorama generation; and 2) the value and output weight matrices specialize in adapting pre-trained knowledge to the panoramic domain, playing a more critical role during fine-tuning for panorama generation. We empirically verify these insights by introducing a simple framework called UniPano, with the objective of establishing an elegant baseline for future research. UniPano not only outperforms existing methods but also significantly reduces memory usage and training time compared to prior dual-branch approaches, making it scalable for end-to-end panorama generation with higher resolution. The code will be released.

cs.CV↗

arXiv2025

RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation

In this paper, we introduce RoboMIND (Multi-embodiment Intelligence Normative Data for Robot Manipulation), a dataset containing 107k demonstration trajectories across 479 diverse tasks involving 96 object classes. RoboMIND is collected through human teleoperation and encompasses comprehensive robotic-related information, including multi-view observations, proprioceptive robot state information, and linguistic task descriptions. To ensure data consistency and reliability for imitation learning, RoboMIND is built on a unified data collection platform and a standardized protocol, covering four distinct robotic embodiments: the Franka Emika Panda, the UR5e, the AgileX dual-arm robot, and a humanoid robot with dual dexterous hands. Our dataset also includes 5k real-world failure demonstrations, each accompanied by detailed causes, enabling failure reflection and correction during policy learning. Additionally, we created a digital twin environment in the Isaac Sim simulator, replicating the real-world tasks and assets, which facilitates the low-cost collection of additional training data and enables efficient evaluation. To demonstrate the quality and diversity of our dataset, we conducted extensive experiments using various imitation learning methods for single-task settings and state-of-the-art Vision-Language-Action (VLA) models for multi-task scenarios. By leveraging RoboMIND, the VLA models achieved high manipulation success rates and demonstrated strong generalization capabilities. To the best of our knowledge, RoboMIND is the largest multi-embodiment teleoperation dataset collected on a unified platform, providing large-scale and high-quality robotic training data. Our project is at https://x-humanoid-robomind.github.io/.

cs.RO↗

arXiv2025

Ground Calibration Result of the Wide-field X-ray Telescope (WXT) onboard the Einstein Probe

We report on results of the on-ground X-ray calibration of the Wide-field X-ray Telescope (WXT) built from novel lobster-eye micro-pore optics, onboard the Einstein Probe (EP) satellite. To fully characterize the instrumental performance and properties, a series of tests and calibrations have been carried out at different levels of devices, assemblies and the complete module before the launch of EP. In this paper, we present the calibration results of three flight model modules (FM1, FM5 and FM11) obtained during their end-to-end module calibration experiments carried out at the 100-m X-ray Test Facility (100XF) of IHEP, CAS. Measurements of the Point Spread Function (PSF), effective area, and energy response were performed for multiple incident directions and several characteristic X-ray emission line energies. Specifically, the distributions of the PSF and effective areas are found to be roughly uniform across the FoV, in large agreement with the prediction of lobster-eye optics. Their energy dependence behavior aligns well with theoretical predictions and Monte Carlo simulations. At 1.25 keV, the full width at half maximum (FWHM) of the focal spot is in range of 3-7 arcmin (a median of 4.2) and the effective area in range of 2-3 $cm^2$. Noticeably, the flight model instruments demonstrate a $\sim1.5$ arcmin spatial resolution improvement over the previously launched Lobster Eye Imager for Astronomy. The properties of the complementary metal-oxide semiconductor (CMOS) sensors were also calibrated. The gain coefficients are in range of 6.4-6.9 eV/DN. The energy resolutions are in range of 120-140 eV at 1.25 keV, meeting design requirements. These calibration results have been ingested into the first version of calibration database (CALDB) and applied to the analysis of the scientific data acquired by WXT after the launch of EP.

astro-ph.IM↗

arXiv2025

Playmate: Flexible Control of Portrait Animation via 3D-Implicit Space Guided Diffusion

Recent diffusion-based talking face generation models have demonstrated impressive potential in synthesizing videos that accurately match a speech audio clip with a given reference identity. However, existing approaches still encounter significant challenges due to uncontrollable factors, such as inaccurate lip-sync, inappropriate head posture and the lack of fine-grained control over facial expressions. In order to introduce more face-guided conditions beyond speech audio clips, a novel two-stage training framework Playmate is proposed to generate more lifelike facial expressions and talking faces. In the first stage, we introduce a decoupled implicit 3D representation along with a meticulously designed motion-decoupled module to facilitate more accurate attribute disentanglement and generate expressive talking videos directly from audio cues. Then, in the second stage, we introduce an emotion-control module to encode emotion control information into the latent space, enabling fine-grained control over emotions and thereby achieving the ability to generate talking videos with desired emotion. Extensive experiments demonstrate that Playmate not only outperforms existing state-of-the-art methods in terms of video quality, but also exhibits strong competitiveness in lip synchronization while offering improved flexibility in controlling emotion and head pose. The code will be available at https://github.com/Playmate111/Playmate.

cs.CV↗

arXiv2025

Single-shot 3D characterization the spatiotemporal optical vortex via a spatiotemporal wavefront sensor (STWFS)

The advent of spatiotemporal wave packets (STWPs), represented by spatiotemporal optical vortices (STOVs), has paved the way for the exploration in optics and photonics. To date, despite considerable efforts, a comprehensive and efficient practical means to characterizing wave packets with such complex structures is still lacking. In this study, we introduced a new method designed to achieve high-precision and high-throughput spatiotemporal wave packet measurements using a user-friendly set up. This method is based on a quadriwave lateral shearing interferometric wavefront sensor that utilizes wavelength division multiplexing, termed the "spatiotemporal wavefront sensor (STWFS)." Using this method, we have fabricated a compact prototype with 295 * 295 spatial pixels * 36 wavelength channels of 0.5 nm spectral resolution in a single frame. This STWFS enabled, for the first time, single-shot self-referenced spatiotemporal three-dimensional (3D) optical field characterizations of STOV pulses with transverse orbital angular momenta L of 1 and 2, and obtained the dynamic visualization of the focused propagation of STOV pulses. Furthermore, the STWFS provides a 1.87 nm (0.95%) root mean square (RMS) absolute accuracy for spatiotemporal phase reconstruction. This achievement represents the highest performance compared with other three-dimensional spatiotemporal metrology methods. As a spatiotemporal optical field characterization method, the STWFS offers ultrafast 3D diagnostics, contributing to spatiotemporal photonics and broader applications across different fields, such as light-matter interactions and optical communications.

physics.optics↗

arXiv2025

SciCUEval: A Comprehensive Dataset for Evaluating Scientific Context Understanding in Large Language Models

Large Language Models (LLMs) have shown impressive capabilities in contextual understanding and reasoning. However, evaluating their performance across diverse scientific domains remains underexplored, as existing benchmarks primarily focus on general domains and fail to capture the intricate complexity of scientific data. To bridge this gap, we construct SciCUEval, a comprehensive benchmark dataset tailored to assess the scientific context understanding capability of LLMs. It comprises ten domain-specific sub-datasets spanning biology, chemistry, physics, biomedicine, and materials science, integrating diverse data modalities including structured tables, knowledge graphs, and unstructured texts. SciCUEval systematically evaluates four core competencies: Relevant information identification, Information-absence detection, Multi-source information integration, and Context-aware inference, through a variety of question formats. We conduct extensive evaluations of state-of-the-art LLMs on SciCUEval, providing a fine-grained analysis of their strengths and limitations in scientific context understanding, and offering valuable insights for the future development of scientific-domain LLMs.

cs.CL↗

arXiv2025

Self-cross Feature based Spiking Neural Networks for Efficient Few-shot Learning

Deep neural networks (DNNs) excel in computer vision tasks, especially, few-shot learning (FSL), which is increasingly important for generalizing from limited examples. However, DNNs are computationally expensive with scalability issues in real world. Spiking Neural Networks (SNNs), with their event-driven nature and low energy consumption, are particularly efficient in processing sparse and dynamic data, though they still encounter difficulties in capturing complex spatiotemporal features and performing accurate cross-class comparisons. To further enhance the performance and efficiency of SNNs in few-shot learning, we propose a few-shot learning framework based on SNNs, which combines a self-feature extractor module and a cross-feature contrastive module to refine feature representation and reduce power consumption. We apply the combination of temporal efficient training loss and InfoNCE loss to optimize the temporal dynamics of spike trains and enhance the discriminative power. Experimental results show that the proposed FSL-SNN significantly improves the classification performance on the neuromorphic dataset N-Omniglot, and also achieves competitive performance to ANNs on static datasets such as CUB and miniImageNet with low power consumption.

cs.LG↗

arXiv2025

Occupancy World Model for Robots

Understanding and forecasting the scene evolutions deeply affect the exploration and decision of embodied agents. While traditional methods simulate scene evolutions through trajectory prediction of potential instances, current works use the occupancy world model as a generative framework for describing fine-grained overall scene dynamics. However, existing methods cluster on the outdoor structured road scenes, while ignoring the exploration of forecasting 3D occupancy scene evolutions for robots in indoor scenes. In this work, we explore a new framework for learning the scene evolutions of observed fine-grained occupancy and propose an occupancy world model based on the combined spatio-temporal receptive field and guided autoregressive transformer to forecast the scene evolutions, called RoboOccWorld. We propose the Conditional Causal State Attention (CCSA), which utilizes camera poses of next state as conditions to guide the autoregressive transformer to adapt and understand the indoor robotics scenarios. In order to effectively exploit the spatio-temporal cues from historical observations, Hybrid Spatio-Temporal Aggregation (HSTA) is proposed to obtain the combined spatio-temporal receptive field based on multi-scale spatio-temporal windows. In addition, we restructure the OccWorld-ScanNet benchmark based on local annotations to facilitate the evaluation of the indoor 3D occupancy scene evolution prediction task. Experimental results demonstrate that our RoboOccWorld outperforms state-of-the-art methods in indoor 3D occupancy scene evolution prediction task. The code will be released soon.

cs.CV↗

arXiv2025

Enhanced timing of a 113 km O-TWTFT link with digital maximum likelihood estimation process

Optical two-way time-frequency transfer (O-TWTFT), employing linear optical sampling and based on frequency combs, is a promising approach for future large-scale optical clock synchronization. It offers the dual benefits of high temporal resolution and an extensive unambiguous range. A critical challenge in establishing long-distance free-space optical links is enhancing detection sensitivity. Particularly at ultra-low received power levels, the error caused by time extraction algorithms for linear optical sampling becomes a significant hindrance to system sensitivity, surpassing the constraints imposed by quantum limitations. In this work, we introduce the Complex Least Squares (CLS) method to enhance both the accuracy and sensitivity of time extraction. Unlike most previous methods that relied solely on phase information, our scheme utilizes a maximum likelihood estimation technique incorporating both amplitude and phase data. Our experiments, conducted over a 113 km free-space link with an average link loss of up to 100 dB, achieved a record minimum received power of 0.1 nW, which is over ten times lower than previous benchmarks. The precision also approaches the quantum limitation.

physics.optics↗

arXiv2025

Deterministic-to-Stochastic Diverse Latent Feature Mapping for Human Motion Synthesis

Human motion synthesis aims to generate plausible human motion sequences, which has raised widespread attention in computer animation. Recent score-based generative models (SGMs) have demonstrated impressive results on this task. However, their training process involves complex curvature trajectories, leading to unstable training process. In this paper, we propose a Deterministic-to-Stochastic Diverse Latent Feature Mapping (DSDFM) method for human motion synthesis. DSDFM consists of two stages. The first human motion reconstruction stage aims to learn the latent space distribution of human motions. The second diverse motion generation stage aims to build connections between the Gaussian distribution and the latent space distribution of human motions, thereby enhancing the diversity and accuracy of the generated human motions. This stage is achieved by the designed deterministic feature mapping procedure with DerODE and stochastic diverse output generation procedure with DivSDE.DSDFM is easy to train compared to previous SGMs-based methods and can enhance diversity without introducing additional training parameters.Through qualitative and quantitative experiments, DSDFM achieves state-of-the-art results surpassing the latest methods, validating its superiority in human motion synthesis.

cs.CV↗

arXiv2025

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models

Current image generation models can effortlessly produce high-quality, highly realistic images, but this also increases the risk of misuse. In various Text-to-Image or Image-to-Image tasks, attackers can generate a series of images containing inappropriate content by simply editing the language modality input. To mitigate this security concern, numerous guarding or defensive strategies have been proposed, with a particular emphasis on safeguarding language modality. However, in practical applications, threats in the vision modality, particularly in tasks involving the editing of real-world images, present heightened security risks as they can easily infringe upon the rights of the image owner. Therefore, this paper employs a method named typographic attack to reveal that various image generation models are also susceptible to threats within the vision modality. Furthermore, we also evaluate the defense performance of various existing methods when facing threats in the vision modality and uncover their ineffectiveness. Finally, we propose the Vision Modal Threats in Image Generation Models (VMT-IGMs) dataset, which would serve as a baseline for evaluating the vision modality vulnerability of various image generation models.

cs.CV↗

arXiv2025

STAA-SNN: Spatial-Temporal Attention Aggregator for Spiking Neural Networks

Spiking Neural Networks (SNNs) have gained significant attention due to their biological plausibility and energy efficiency, making them promising alternatives to Artificial Neural Networks (ANNs). However, the performance gap between SNNs and ANNs remains a substantial challenge hindering the widespread adoption of SNNs. In this paper, we propose a Spatial-Temporal Attention Aggregator SNN (STAA-SNN) framework, which dynamically focuses on and captures both spatial and temporal dependencies. First, we introduce a spike-driven self-attention mechanism specifically designed for SNNs. Additionally, we pioneeringly incorporate position encoding to integrate latent temporal relationships into the incoming features. For spatial-temporal information aggregation, we employ step attention to selectively amplify relevant features at different steps. Finally, we implement a time-step random dropout strategy to avoid local optima. As a result, STAA-SNN effectively captures both spatial and temporal dependencies, enabling the model to analyze complex patterns and make accurate predictions. The framework demonstrates exceptional performance across diverse datasets and exhibits strong generalization capabilities. Notably, STAA-SNN achieves state-of-the-art results on neuromorphic datasets CIFAR10-DVS, with remarkable performances of 97.14%, 82.05% and 70.40% on the static datasets CIFAR-10, CIFAR-100 and ImageNet, respectively. Furthermore, our model exhibits improved performance ranging from 0.33\% to 2.80\% with fewer time steps. The code for the model is available on GitHub.

cs.CV↗

arXiv2025

Temporal Separation with Entropy Regularization for Knowledge Distillation in Spiking Neural Networks

Spiking Neural Networks (SNNs), inspired by the human brain, offer significant computational efficiency through discrete spike-based information transfer. Despite their potential to reduce inference energy consumption, a performance gap persists between SNNs and Artificial Neural Networks (ANNs), primarily due to current training methods and inherent model limitations. While recent research has aimed to enhance SNN learning by employing knowledge distillation (KD) from ANN teacher networks, traditional distillation techniques often overlook the distinctive spatiotemporal properties of SNNs, thus failing to fully leverage their advantages. To overcome these challenge, we propose a novel logit distillation method characterized by temporal separation and entropy regularization. This approach improves existing SNN distillation techniques by performing distillation learning on logits across different time steps, rather than merely on aggregated output features. Furthermore, the integration of entropy regularization stabilizes model optimization and further boosts the performance. Extensive experimental results indicate that our method surpasses prior SNN distillation strategies, whether based on logit distillation, feature distillation, or a combination of both. The code will be available on GitHub.

cs.CV↗

arXiv2025

Experimental Multi-Dimensional Side-Channel-Secure Quantum Key Distribution

Quantum key distribution (QKD) theoretically provides unconditional security between remote parties. However, guaranteeing practical security through device characterisation alone is challenging in real-world implementations due to the multi-dimensional spaces in which the devices may be operated. The side-channel-secure (SCS)-QKD protocol, which only requires bounding the upper limits of the intensities for the two states, theoretically provides a rigorous solution to the challenge and achieves measurement-device-independent security in detection and security for whatever multi-dimensional side channel attack in the source. Here, we demonstrate a practical implementation of SCS-QKD, achieving a secure key rate of $6.60$ kbps through a 50.5 km fibre and a maximum distribution distance of 101.1 km while accounting for finite-size effects. Our experiment also represents an approximate forty-times improvement over the previous experiment.

quant-ph↗

arXiv2025

Long-range four-body interactions in the Hamiltonian mean field model

In this paper, a Hamiltonian mean field model with long-range four-body interactions is proposed. The model describes a long-range mean-field system in which N unit-mass particles move on a unit circle. Each particle theta_i interacts with any three other particles through an infinite-range cosine potential with an attractive interaction (epsilon > 0). By applying a method that remaps the average phase of global particle pairs onto a new unit circle, and using the saddle-point technique, the partition function is solved analytically after introducing four-body interactions, yielding expressions for the free energy f and the energy per particle U. These results were further validated through numerical simulations. The results show that the system undergoes a second-order phase transition at the critical energy U_c. Specifically, the critical energy corresponds to U_c = 0.32 when the coupling constant epsilon = 5, and U_c = 0.63 when epsilon = 10. Finally, we calculated the system's largest Lyapunov exponent lambda and kinetic energy fluctuations Sigma through numerical simulations. It is found that the peak of the largest Lyapunov exponent lambda occurs slightly below the critical energy U_c, which is consistent with the point of maximum kinetic energy fluctuations Sigma. And there is a scaling law of Sigma / N^(1/2) proportional to lambda between them.

cond-mat.stat-mech↗