arXiv subjects

Qian Sun

Publications and source records attributed to Qian Sun.

At least 19 recordsLinked to original sources

arXiv2026

ClockRoPE: Random Fourier Rotations for Temporal Routine Modeling

Rotary Position Embedding (RoPE) has been widely adopted in transformer-based large language models. However, its log-linear frequency schedule, originally designed to produce long-term attention decay, limits its adoption in domains with more complex distance-correlation patterns, such as temporal periodicity in sequential recommendation. We investigate the expressiveness of general query/key rotations and find that any normalized continuous positive-definite attention modulation function can be approximated by random rotations induced by its own Fourier transform, which we term Random Fourier Rotations. Building on this theory, we propose ClockRoPE for routine modeling in sequential recommendation, where rotation frequencies are derived from periodic attention modulation functions. In online A/B tests, ClockRoPE demonstrates consistent improvements in valued engagement metrics, and has been successfully deployed in production-scale generative retrieval system at a major video-sharing platform.

cs.LG↗

arXiv2026

RMISC: A Large-scale Real-world Multivariate Corpus for Time Series Foundation Models

Recent years have witnessed the emergence of multivariate modeling using time series foundation models (TSFMs), which achieve advanced zero-shot generalization. Modern multivariate TSFMs are predominantly pretrained on multivariate synthetic data, which is easier to scale but may fail to capture the complex temporal dynamics and cross-variable relationships present in real-world time series. This raises a key question: Whether and to what extent the leading TSFMs trained with the real-world corpus perform better than those trained with synthetic data? To answer this, we establish the RMISC corpus, a considerably large-scale, high-quality, openly accessible, real-world, and multivariate time series archive that contains around 200 datasets and 142 billion time points across diverse domains. Furthermore, we pretrain four advanced TSFMs on univariate, synthetic multivariate, and real-world multivariate data and evaluate their zero-shot generalization capabilities on standard in-distribution and out-of-distribution benchmarks. Experimental results show that incorporating real-world multivariate data predominantly improves the generalization performance for both univariate and multivariate TSFMs. These results provide a deeper understanding of how real-world multivariate data contributes to the development of stronger TSFMs.

cs.AI↗

arXiv2026

Interactive Benchmarks

Existing reasoning evaluation paradigms suffer from different limitations: fixed benchmarks are increasingly saturated and vulnerable to contamination, while preference-based evaluations rely on subjective judgments. We argue that a core aspect of intelligence is the ability to decide what information to acquire and how to use it effectively. We propose Interactive Benchmarks, a unified evaluation paradigm that assesses a model's reasoning ability through budgeted multi-turn interaction. We evaluate models under this framework in two settings: Interactive Proofs, where models interact with a judge to solve Logic, UI2Html, and Mathematics tasks under objective feedback; and Interactive Games, where models reason strategically to maximize long-horizon utilities. Our results show that interactive benchmarks provide a more robust assessment of this dimension of model intelligence, revealing substantial room for improvement in interactive scenarios.

cs.AI↗

arXiv2026

TP-Spikformer: Token Pruned Spiking Transformer

Spiking neural networks (SNNs) offer an energy-efficient alternative to traditional neural networks due to their event-driven computing paradigm. However, recent advancements in spiking transformers have focused on improving accuracy with large-scale architectures, which require significant computational resources and limit deployment on resource-constrained devices. In this paper, we propose a simple yet effective token pruning method for spiking transformers, termed TP-Spikformer, that reduces storage and computational overhead while maintaining competitive performance. Specifically, we first introduce a heuristic spatiotemporal information-retaining criterion that comprehensively evaluates tokens' importance, assigning higher scores to informative tokens for retention and lower scores to uninformative ones for pruning. Based on this criterion, we propose an information-retaining token pruning framework that employs a block-level early stopping strategy for uninformative tokens, instead of removing them outright. This also helps preserve more information during token pruning. We demonstrate the effectiveness, efficiency and scalability of TP-Spikformer through extensive experiments across diverse architectures, including Spikformer, QKFormer and Spike-driven Transformer V1 and V3, and a range of tasks such as image classification, object detection, semantic segmentation and event-based object tracking. Particularly, TP-Spikformer performs well in a training-free manner. These results reveal its potential as an efficient and practical solution for deploying SNNs in real-world applications with limited computational resources.

cs.CV↗

arXiv2026

Towards Sample Efficient Entanglement Classification for 3 and 4 Qubit Systems: A Tailored CNN-BiLSTM Approach

Accurate classification of multipartite entanglement in high-dimensional quantum systems is crucial for advancing quantum communication and information processing. However, conventional methods are resource-intensive, and even many machine-learning-based approaches necessitate large training datasets, creating a significant experimental bottleneck for data acquisition. To address this challenge, we propose a hybrid neural network architecture integrating Convolutional and Bidirectional Long Short-Term Memory networks (CNN-BiLSTM). This design leverages CNNs for local feature extraction and BiLSTMs for sequential dependency modeling, enabling robust feature learning from minimal training data. We investigate two fusion paradigms: Architecture 1 (flattening-based) and Architecture 2 (dimensionality-transforming). When trained on only 100 samples, Architecture 2 maintains classification accuracies exceeding 90% for both 3-qubit and 4-qubit systems, demonstrating rapid loss convergence within tens of epochs. Under full-data conditions (400 000 samples), both architectures achieve accuracies above 99.97%. Comparative benchmarks reveal that our CNN-BiLSTM models, especially Architecture 2, consistently outperform standalone CNNs, BiLSTMs, and MLPs in low-data regimes, albeit with increased training time. These results demonstrates that the tailored CNN-BiLSTM fusion significantly alleviates experimental data acquisition burden, offering a practical pathway toward scalable entanglement verification in complex quantum systems.

quant-ph↗

arXiv2025

Unveiling the Spatial-temporal Effective Receptive Fields of Spiking Neural Networks

Spiking Neural Networks (SNNs) demonstrate significant potential for energy-efficient neuromorphic computing through an event-driven paradigm. While training methods and computational models have greatly advanced, SNNs struggle to achieve competitive performance in visual long-sequence modeling tasks. In artificial neural networks, the effective receptive field (ERF) serves as a valuable tool for analyzing feature extraction capabilities in visual long-sequence modeling. Inspired by this, we introduce the Spatio-Temporal Effective Receptive Field (ST-ERF) to analyze the ERF distributions across various Transformer-based SNNs. Based on the proposed ST-ERF, we reveal that these models suffer from establishing a robust global ST-ERF, thereby limiting their visual feature modeling capabilities. To overcome this issue, we propose two novel channel-mixer architectures: \underline{m}ulti-\underline{l}ayer-\underline{p}erceptron-based m\underline{ixer} (MLPixer) and \underline{s}plash-and-\underline{r}econstruct \underline{b}lock (SRB). These architectures enhance global spatial ERF through all timesteps in early network stages of Transformer-based SNNs, improving performance on challenging visual long-sequence modeling tasks. Extensive experiments conducted on the Meta-SDT variants and across object detection and semantic segmentation tasks further validate the effectiveness of our proposed method. Beyond these specific applications, we believe the proposed ST-ERF framework can provide valuable insights for designing and optimizing SNN architectures across a broader range of tasks. The code is available at \href{https://github.com/EricZhang1412/Spatial-temporal-ERF}{\faGithub~EricZhang1412/Spatial-temporal-ERF}.

cs.NE↗

arXiv2025

Decision-focused Sensing and Forecasting for Adaptive and Rapid Flood Response: An Implicit Learning Approach

Timely and reliable decision-making is vital for flood emergency response, yet it remains severely hindered by limited and imprecise situational awareness due to various budget and data accessibility constraints. Traditional flood management systems often rely on in-situ sensors to calibrate remote sensing-based large-scale flood depth forecasting models, and further take flood depth estimates to optimize flood response decisions. However, these approaches often take fixed, decision task-agnostic strategies to decide where to put in-situ sensors (e.g., maximize overall information gain) and train flood forecasting models (e.g., minimize average forecasting errors), but overlook that systems with the same sensing gain and average forecasting errors may lead to distinct decisions. To address this, we introduce a novel decision-focused framework that strategically selects locations for in-situ sensor placement and optimize spatio-temporal flood forecasting models to optimize downstream flood response decision regrets. Our end-to-end pipeline integrates four components: a contextual scoring network, a differentiable sensor selection module under hard budget constraints, a spatio-temporal flood reconstruction and forecasting model, and a differentiable decision layer tailored to task-specific objectives. Central to our approach is the incorporation of Implicit Maximum Likelihood Estimation (I-MLE) to enable gradient-based learning over discrete sensor configurations, and probabilistic decision heads to enable differentiable approximation to various constrained disaster response tasks.

cs.LG↗

arXiv2025

Advancing Metallic Surface Defect Detection via Anomaly-Guided Pretraining on a Large Industrial Dataset

The pretraining-finetuning paradigm is a crucial strategy in metallic surface defect detection for mitigating the challenges posed by data scarcity. However, its implementation presents a critical dilemma. Pretraining on natural image datasets such as ImageNet, faces a significant domain gap. Meanwhile, naive self-supervised pretraining on in-domain industrial data is often ineffective due to the inability of existing learning objectives to distinguish subtle defect patterns from complex background noise and textures. To resolve this, we introduce Anomaly-Guided Self-Supervised Pretraining (AGSSP), a novel paradigm that explicitly guides representation learning through anomaly priors. AGSSP employs a two-stage framework: (1) it first pretrains the model's backbone by distilling knowledge from anomaly maps, encouraging the network to capture defect-salient features; (2) it then pretrains the detector using pseudo-defect boxes derived from these maps, aligning it with localization tasks. To enable this, we develop a knowledge-enhanced method to generate high-quality anomaly maps and collect a large-scale industrial dataset of 120,000 images. Additionally, we present two small-scale, pixel-level labeled metallic surface defect datasets for validation. Extensive experiments demonstrate that AGSSP consistently enhances performance across various settings, achieving up to a 10\% improvement in mAP@0.5 and 11.4\% in mAP@0.5:0.95 compared to ImageNet-based models. All code, pretrained models, and datasets are publicly available at https://clovermini.github.io/AGSSP-Dev/.

cs.CV↗

arXiv2025

Training-Free ANN-to-SNN Conversion for High-Performance Spiking Transformer

Leveraging the event-driven paradigm, Spiking Neural Networks (SNNs) offer a promising approach for energy-efficient Transformer architectures.While ANN-to-SNN conversion avoids the high training cost of directly trained Spiking Transformers, existing approaches still struggle to handle the nonlinear operations within Transformer blocks, and often require additional fine-tuning of pretrained ANNs.To address these limitations, we propose a training-free and high-performance ANN-to-SNN conversion framework tailored for Transformer architectures. Specifically, we introduce a Multi-basis Exponential Decay (MBE) neuron that combines exponential decay with a multi-basis encoding strategy to effectively approximate nonlinear operations, eliminating the need for weight modifications in pretrained ANNs.Extensive experiments across diverse tasks (CV, NLU, NLG) and mainstream Transformer architectures (ViT, RoBERTa, GPT-2) demonstrate that our method achieves near-lossless conversion accuracy with significantly lower latency. This provides a promising pathway for the efficient and scalable deployment of Spiking Transformers in real-world applications.

cs.LG↗

arXiv2025

A Multimodal Data Fusion Attention-Empowered Generative Adversarial Network for Real Time 3D Underwater Sound Speed Field Construction

Sound speed profiles (SSPs) are crucial underwater parameters that determine the propagation patterns of acoustic signals, directly influencing the energy efficiency of underwater communication and the accuracy of positioning systems. Conventional techniques for obtaining SSPs, such as matched field processing (MFP), compressive sensing (CS), and deep learning (DL), typically depend on on-site sonar measurements, which impose stringent requirements on the deployment of underwater observation systems. To overcome this limitation and enable high-precision sound speed field reconstruction without the need for on-site underwater data collection, we propose a novel multimodal data-fusion generative adversarial network enhanced with residual attention blocks (MDF-RAGAN). This architecture integrates attention mechanisms to capture global spatial feature correlations effectively, while residual modules are employed to extract subtle perturbations in deep-ocean sound velocity distribution caused by sea surface temperature (SST) variations. Experimental results on a public real-world dataset demonstrate that the proposed model outperforms other state-of-the-art methods, achieving an estimation error of less than 0.3 m/s. Specifically, MDF-RAGAN reduces the root mean square error (RMSE) by nearly half compared to convolutional neural network (CNN) and spatial interpolation (SITP) methods, and attains a 65.8\% RMSE reduction relative to the mean profile method. These results highlight the effectiveness of multi-source fusion and cross-modal attention in enhancing the accuracy and robustness of sound speed profile reconstruction.

cs.SD↗

arXiv2025

Spiking Vision Transformer with Saccadic Attention

The combination of Spiking Neural Networks (SNNs) and Vision Transformers (ViTs) holds potential for achieving both energy efficiency and high performance, particularly suitable for edge vision applications. However, a significant performance gap still exists between SNN-based ViTs and their ANN counterparts. Here, we first analyze why SNN-based ViTs suffer from limited performance and identify a mismatch between the vanilla self-attention mechanism and spatio-temporal spike trains. This mismatch results in degraded spatial relevance and limited temporal interactions. To address these issues, we draw inspiration from biological saccadic attention mechanisms and introduce an innovative Saccadic Spike Self-Attention (SSSA) method. Specifically, in the spatial domain, SSSA employs a novel spike distribution-based method to effectively assess the relevance between Query and Key pairs in SNN-based ViTs. Temporally, SSSA employs a saccadic interaction module that dynamically focuses on selected visual areas at each timestep and significantly enhances whole scene understanding through temporal interactions. Building on the SSSA mechanism, we develop a SNN-based Vision Transformer (SNN-ViT). Extensive experiments across various visual tasks demonstrate that SNN-ViT achieves state-of-the-art performance with linear computational complexity. The effectiveness and efficiency of the SNN-ViT highlight its potential for power-critical edge vision applications.

cs.CV↗

arXiv2024

On Active Privacy Auditing in Supervised Fine-tuning for White-Box Language Models

The pretraining and fine-tuning approach has become the leading technique for various NLP applications. However, recent studies reveal that fine-tuning data, due to their sensitive nature, domain-specific characteristics, and identifiability, pose significant privacy concerns. To help develop more privacy-resilient fine-tuning models, we introduce a novel active privacy auditing framework, dubbed Parsing, designed to identify and quantify privacy leakage risks during the supervised fine-tuning (SFT) of language models (LMs). The framework leverages improved white-box membership inference attacks (MIAs) as the core technology, utilizing novel learning objectives and a two-stage pipeline to monitor the privacy of the LMs' fine-tuning process, maximizing the exposure of privacy risks. Additionally, we have improved the effectiveness of MIAs on large LMs including GPT-2, Llama2, and certain variants of them. Our research aims to provide the SFT community of LMs with a reliable, ready-to-use privacy auditing tool, and to offer valuable insights into safeguarding privacy during the fine-tuning process. Experimental results confirm the framework's efficiency across various models and tasks, emphasizing notable privacy concerns in the fine-tuning process. Project code available for https://anonymous.4open.science/r/PARSING-4817/.

cs.CL↗

arXiv2024

Horizon-wise Learning Paradigm Promotes Gene Splicing Identification

Identifying gene splicing is a core and significant task confronted in modern collaboration between artificial intelligence and bioinformatics. Past decades have witnessed great efforts on this concern, such as the bio-plausible splicing pattern AT-CG and the famous SpliceAI. In this paper, we propose a novel framework for the task of gene splicing identification, named Horizon-wise Gene Splicing Identification (H-GSI). The proposed H-GSI follows the horizon-wise identification paradigm and comprises four components: the pre-processing procedure transforming string data into tensors, the sliding window technique handling long sequences, the SeqLab model, and the predictor. In contrast to existing studies that process gene information with a truncated fixed-length sequence, H-GSI employs a horizon-wise identification paradigm in which all positions in a sequence are predicted with only one forward computation, improving accuracy and efficiency. The experiments conducted on the real-world Human dataset show that our proposed H-GSI outperforms SpliceAI and achieves the best accuracy of 97.20\%. The source code is available from this link.

q-bio.QM↗

arXiv2023

Normalized solutions for a fractional Choquard-type equation with exponential critical growth in $\mathbb{R}$

In this paper, we study the following fractional Choquard-type equation with prescribed mass \begin{align*} \begin{cases} (-\Delta)^{1/2}u=\lambda u +(I_\mu*F(u))f(u),\ \ \mbox{in}\ \mathbb{R}, \displaystyle\int_{\mathbb{R}}|u|^2 \mathrm{d}x=a^2, \end{cases} \end{align*} where $(-\Delta)^{1/2}$ denotes the $1/2$-Laplacian operator, $a>0$, $\lambda\in \mathbb{R}$, $I_\mu(x)=\frac{{1}}{{|x|^\mu}}$ with $\mu\in(0,1)$, $F(u)$ is the primitive function of $f(u)$, and $f$ is a continuous function with exponential critical growth in the sense of the Trudinger-Moser inequality. By using a minimax principle based on the homotopy stable family, we obtain that there is at least one normalized ground state solution to the above equation.

math.AP↗

arXiv2023

Semi-Weakly Supervised Object Kinematic Motion Prediction

Given a 3D object, kinematic motion prediction aims to identify the mobile parts as well as the corresponding motion parameters. Due to the large variations in both topological structure and geometric details of 3D objects, this remains a challenging task and the lack of large scale labeled data also constrain the performance of deep learning based approaches. In this paper, we tackle the task of object kinematic motion prediction problem in a semi-weakly supervised manner. Our key observations are two-fold. First, although 3D dataset with fully annotated motion labels is limited, there are existing datasets and methods for object part semantic segmentation at large scale. Second, semantic part segmentation and mobile part segmentation is not always consistent but it is possible to detect the mobile parts from the underlying 3D structure. Towards this end, we propose a graph neural network to learn the map between hierarchical part-level segmentation and mobile parts parameters, which are further refined based on geometric alignment. This network can be first trained on PartNet-Mobility dataset with fully labeled mobility information and then applied on PartNet dataset with fine-grained and hierarchical part-level segmentation. The network predictions yield a large scale of 3D objects with pseudo labeled mobility information and can further be used for weakly-supervised learning with pre-existing segmentation. Our experiments show there are significant performance boosts with the augmented data for previous method designed for kinematic motion prediction on 3D partial scans.

cs.CV↗

arXiv2023

Search By Image: Deeply Exploring Beneficial Features for Beauty Product Retrieval

Searching by image is popular yet still challenging due to the extensive interference arose from i) data variations (e.g., background, pose, visual angle, brightness) of real-world captured images and ii) similar images in the query dataset. This paper studies a practically meaningful problem of beauty product retrieval (BPR) by neural networks. We broadly extract different types of image features, and raise an intriguing question that whether these features are beneficial to i) suppress data variations of real-world captured images, and ii) distinguish one image from others which look very similar but are intrinsically different beauty products in the dataset, therefore leading to an enhanced capability of BPR. To answer it, we present a novel variable-attention neural network to understand the combination of multiple features (termed VM-Net) of beauty product images. Considering that there are few publicly released training datasets for BPR, we establish a new dataset with more than one million images classified into more than 20K categories to improve both the generalization and anti-interference abilities of VM-Net and other methods. We verify the performance of VM-Net and its competitors on the benchmark dataset Perfect-500K, where VM-Net shows clear improvements over the competitors in terms of MAP@7. The source code and dataset will be released upon publication.

cs.CV↗

arXiv2023

OPE-SR: Orthogonal Position Encoding for Designing a Parameter-free Upsampling Module in Arbitrary-scale Image Super-Resolution

Implicit neural representation (INR) is a popular approach for arbitrary-scale image super-resolution (SR), as a key component of INR, position encoding improves its representation ability. Motivated by position encoding, we propose orthogonal position encoding (OPE) - an extension of position encoding - and an OPE-Upscale module to replace the INR-based upsampling module for arbitrary-scale image super-resolution. Same as INR, our OPE-Upscale Module takes 2D coordinates and latent code as inputs; however it does not require training parameters. This parameter-free feature allows the OPE-Upscale Module to directly perform linear combination operations to reconstruct an image in a continuous manner, achieving an arbitrary-scale image reconstruction. As a concise SR framework, our method has high computing efficiency and consumes less memory comparing to the state-of-the-art (SOTA), which has been confirmed by extensive experiments and evaluations. In addition, our method has comparable results with SOTA in arbitrary scale image super-resolution. Last but not the least, we show that OPE corresponds to a set of orthogonal basis, justifying our design principle.

cs.CV↗

arXiv2022

Metalenses with polarization-independent adaptive nano-antennas

Metalens research has made major advances in recent years. These advances rely on the simple design principle of arranging meta-atoms in regular arrays to create an arbitrary phase and polarization profile. Unfortunately, the concept of equally spaced meta-atoms reaches its limit for high deflection angles where the deflection efficiency decreases. The efficiency can be increased using nano-antennas with multiple elements, but their polarization sensitivity hinders their application in metalenses. Here, we show that by designing polarization-insensitive dimer nano-antennas and abandoning the principle of equally spaced unit cells, polarization-independent ultrahigh numerical aperture (NA=1.48) oil-immersion operation with an efficiency of 43% can be demonstrated. This represents a significant improvement on other polarization-independent designs at visible wavelength. We also use this single layer metalens to replace a conventional objective lens and demonstrate the confocal scanning microscopic imaging of a grating with a period of 300 nm at 532 nm operating wavelength. Overall, our results experimentally demonstrate a novel design concept that further improves metalens performance.

physics.optics↗