arXiv subjects

Zhiqiang Shen

Publications and source records attributed to Zhiqiang Shen.

At least 73 records · Page 4Linked to original sources

arXiv2025

Style Content Decomposition-based Data Augmentation for Domain Generalizable Medical Image Segmentation

Due to domain shifts across diverse medical imaging modalities, learned segmentation models often suffer significant performance degradation during deployment. We posit that these domain shifts can generally be categorized into two main components: 1) "style" shifts, referring to global disparities in image properties such as illumination, contrast, and color; and 2) "content" shifts, which involve local discrepancies in anatomical structures. To address the domain shifts in medical image segmentation, we first factorize an image into style codes and content maps, explicitly modeling the "style" and "content" components. Building on this, we introduce a Style-Content decomposition-based data augmentation algorithm (StyCona), which performs augmentation on both the global style and local content of source-domain images, enabling the training of a well-generalized model for domain generalizable medical image segmentation. StyCona is a simple yet effective plug-and-play module that substantially improves model generalization without requiring additional training parameters or modifications to segmentation model architectures. Experiments on cardiac magnetic resonance imaging and fundus photography segmentation tasks, with single and multiple target domains respectively, demonstrate the effectiveness of StyCona and its superiority over state-of-the-art domain generalization methods. The code is available at https://github.com/Senyh/StyCona.

eess.IV↗

arXiv2025

RAGFort: Dual-Path Defense Against Proprietary Knowledge Base Extraction in Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) systems deployed over proprietary knowledge bases face growing threats from reconstruction attacks that aggregate model responses to replicate knowledge bases. Such attacks exploit both intra-class and inter-class paths, progressively extracting fine-grained knowledge within topics and diffusing it across semantically related ones, thereby enabling comprehensive extraction of the original knowledge base. However, existing defenses target only one path, leaving the other unprotected. We conduct a systematic exploration to assess the impact of protecting each path independently and find that joint protection is essential for effective defense. Based on this, we propose RAGFort, a structure-aware dual-module defense combining "contrastive reindexing" for inter-class isolation and "constrained cascade generation" for intra-class protection. Experiments across security, performance, and robustness confirm that RAGFort significantly reduces reconstruction success while preserving answer quality, offering comprehensive defense against knowledge base extraction attacks.

cs.AI↗

arXiv2025

A Frustratingly Simple Yet Highly Effective Attack Baseline: Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1

Despite promising performance on open-source large vision-language models (LVLMs), transfer-based targeted attacks often fail against closed-source commercial LVLMs. Analyzing failed adversarial perturbations reveals that the learned perturbations typically originate from a uniform distribution and lack clear semantic details, resulting in unintended responses. This critical absence of semantic information leads commercial black-box LVLMs to either ignore the perturbation entirely or misinterpret its embedded semantics, thereby causing the attack to fail. To overcome these issues, we propose to refine semantic clarity by encoding explicit semantic details within local regions, thus ensuring the capture of finer-grained features and inter-model transferability, and by concentrating modifications on semantically rich areas rather than applying them uniformly. To achieve this, we propose a simple yet highly effective baseline: at each optimization step, the adversarial image is cropped randomly by a controlled aspect ratio and scale, resized, and then aligned with the target image in the embedding space. While the naive source-target matching method has been utilized before in the literature, we are the first to provide a tight analysis, which establishes a close connection between perturbation optimization and semantics. Experimental results confirm our hypothesis. Our adversarial examples crafted with local-aggregated perturbations focused on crucial regions exhibit surprisingly good transferability to commercial LVLMs, including GPT-4.5, GPT-4o, Gemini-2.0-flash, Claude-3.5/3.7-sonnet, and even reasoning models like o1, Claude-3.7-thinking and Gemini-2.0-flash-thinking. Our approach achieves success rates exceeding 90% on GPT-4.5, 4o, and o1, significantly outperforming all prior state-of-the-art attack methods with lower $\ell_1/\ell_2$ perturbations.

cs.CV↗

arXiv2025

Bi-Mamba: Towards Accurate 1-Bit State Space Models

The typical Selective State-Space Model (SSM) used in Mamba addresses several limitations of Transformers, such as the quadratic computational complexity with respect to sequence length and the significant memory requirements during inference due to the key-value (KV) cache. However, the increasing size of Mamba models continues to pose challenges for training and deployment, particularly due to their substantial computational demands during both training and inference. In this work, we introduce $\texttt{Bi-Mamba}$, a scalable and powerful 1-bit Mamba architecture designed to enable more efficient large language models (LLMs), with model sizes of 780M, 1.3B, and 2.7B parameters. $\texttt{Bi-Mamba}$ models are trained from scratch on a standard LLM-scale dataset using an autoregressive distillation loss. Extensive experiments on language modeling benchmarks demonstrate that $\texttt{Bi-Mamba}$ achieves performance comparable to its full-precision (FP16 or BF16) counterparts, while outperforming post-training binarization (PTB) Mamba and binarization-aware training (BAT) Transformer baselines. Moreover, $\texttt{Bi-Mamba}$ drastically reduces memory usage and computational cost compared to the original Mamba. Our work pioneers a new line of linear-complexity LLMs under low-bit representation and provides the way for the design of specialized hardware optimized for efficient 1-bit Mamba-based models. Code and the pre-trained weights are available at https://github.com/Tangshengku/Bi-Mamba.

cs.CL↗

arXiv2025

Widespread Hot Molecular Gas Heated by Shear-induced Turbulence in the Galactic Center

We observed NH3 metastable inversion lines from (3, 3) to (18, 18) toward G0.66-0.13 in the Galactic center with the Shanghai Tianma 65m radio telescope and Yebes 40 m telescope. Highly-excited lines of NH3 (17, 17), (18, 18) were detected in emission for the first time in the interstellar medium, with upper energy levels up to 3100 K. Mapping observations reveal widespread hot molecular gas traced by NH3 (13, 13) toward G0.66-0.13. The rotation temperatures of hot gas traced by NH3 exceed 400 K, which amounts to five percent of the total NH3 in the Galactic Center. Hot gas (>400 K) and warm gas (100-140 K) are found in distinct clumps, with the hot gas located at the interfacing regions between different warm clouds. The theory of intermittency in turbulence reproduces the complex temperature structure in the central molecular zone, especially the hot gas observed here. The results presented here demonstrate that turbulence heating dominates the heating of the molecular gas in the Central Molecular Zone, while the turbulence is induced by the shear-motion of molecular clouds under the gravitational potential of the nuclear star clusters and the supermassive black hole. Our results suggest that shear-induced turbulence heating could be a widespread factor influencing galactic evolution.

astro-ph.GA↗

arXiv2025

MosaicDiff: Training-free Structural Pruning for Diffusion Model Acceleration Reflecting Pretraining Dynamics

Diffusion models are renowned for their generative capabilities, yet their pretraining processes exhibit distinct phases of learning speed that have been entirely overlooked in prior post-training acceleration efforts in the community. In this study, we introduce a novel framework called MosaicDiff that aligns diffusion pretraining dynamics with post-training sampling acceleration via trajectory-aware structural pruning. Our approach leverages the observation that the middle, fast-learning stage of diffusion pretraining requires more conservative pruning to preserve critical model features, while the early and later, slow-learning stages benefit from a more aggressive pruning strategy. This adaptive pruning mechanism is the first to explicitly mirror the inherent learning speed variations of diffusion pretraining, thereby harmonizing the model's inner training dynamics with its accelerated sampling process. Extensive experiments on DiT and SDXL demonstrate that our method achieves significant speed-ups in sampling without compromising output quality, outperforming previous state-of-the-art methods by large margins, also providing a new viewpoint for more efficient and robust training-free diffusion acceleration.

cs.LG↗

arXiv2025

Prompting Test-Time Scaling Is A Strong LLM Reasoning Data Augmentation

Large language models (LLMs) have demonstrated impressive reasoning capabilities when provided with chain-of-thought exemplars, but curating large reasoning datasets remains laborious and resource-intensive. In this work, we introduce Prompting Test-Time Scaling (P-TTS), a simple yet effective inference-time data augmentation strategy for enhancing LLM reasoning through finetuning. Rather than collecting thousands or even millions of examples, P-TTS leverages a small pool of only 90 manually selected reasoning instances and systematically varies exemplar augmentation through principled instruction prompting intensities at test time to synthesize diverse reasoning trajectory contexts. Then we finetune the various sizes of Qwen-2.5 models on P-TTS data. Across a suite of mathematical reasoning AIME2024 & 25, MATH500, and GPQA-Diamond, our P-TTS-7B and 32B models outperform the prior competitive baselines like S1 and S1.1 (1K-shot), achieving absolute accuracy gains of +26.66% and +30.00% on AIME'24 (7B), and +13.34% and +6.67% on AIME'25 (7B); P-TTS-32B yields gains of +23.33% and +16.63% on AIME'24, and +26.63% and +3.33% on AIME'25 (vs. S1 and S1.1, respectively), with comparable or better performance on MATH500 and GPQA-Diamond. We further show that P-TTS enhances zero-shot generalization accuracy on out-of-domain reasoning benchmarks of Gaokao, Kaoyan, OlympiadBench, AMC23, GradeSchoolMath, and Minerva. Our analysis suggests that test-time scaling effectively explores the latent space of reasoning patterns, amplifying LLM problem-solving with minimal annotation overhead, and further unlocking the reasoning potential and capabilities of LLMs. Prompting Test-Time Scaling offers a practical, low-cost way to elicit LLM reasoning in resource-constrained or rapidly evolving domains.

cs.CL↗

arXiv2025

Human Texts Are Outliers: Detecting LLM-generated Texts via Out-of-distribution Detection

The rapid advancement of large language models (LLMs) such as ChatGPT, DeepSeek, and Claude has significantly increased the presence of AI-generated text in digital communication. This trend has heightened the need for reliable detection methods to distinguish between human-authored and machine-generated content. Existing approaches both zero-shot methods and supervised classifiers largely conceptualize this task as a binary classification problem, often leading to poor generalization across domains and models. In this paper, we argue that such a binary formulation fundamentally mischaracterizes the detection task by assuming a coherent representation of human-written texts. In reality, human texts do not constitute a unified distribution, and their diversity cannot be effectively captured through limited sampling. This causes previous classifiers to memorize observed OOD characteristics rather than learn the essence of `non-ID' behavior, limiting generalization to unseen human-authored inputs. Based on this observation, we propose reframing the detection task as an out-of-distribution (OOD) detection problem, treating human-written texts as distributional outliers while machine-generated texts are in-distribution (ID) samples. To this end, we develop a detection framework using one-class learning method including DeepSVDD and HRN, and score-based learning techniques such as energy-based method, enabling robust and generalizable performance. Extensive experiments across multiple datasets validate the effectiveness of our OOD-based approach. Specifically, the OOD-based method achieves 98.3% AUROC and AUPR with only 8.9% FPR95 on DeepFake dataset. Moreover, we test our detection framework on multilingual, attacked, and unseen-model and -domain text settings, demonstrating the robustness and generalizability of our framework. Code, pretrained weights, and demo will be released.

cs.CL↗

arXiv2025

Introduction to the Chinese Space Station Survey Telescope (CSST)

The Chinese Space Station Survey Telescope (CSST) is an upcoming Stage-IV sky survey telescope, distinguished by its large field of view (FoV), high image quality, and multi-band observation capabilities. It can simultaneously conduct precise measurements of the Universe by performing multi-color photometric imaging and slitless spectroscopic surveys. The CSST is equipped with five scientific instruments, i.e. Multi-band Imaging and Slitless Spectroscopy Survey Camera (SC), Multi-Channel Imager (MCI), Integral Field Spectrograph (IFS), Cool Planet Imaging Coronagraph (CPI-C), and THz Spectrometer (TS). Using these instruments, CSST is expected to make significant contributions and discoveries across various astronomical fields, including cosmology, galaxies and active galactic nuclei (AGN), the Milky Way and nearby galaxies, stars, exoplanets, Solar System objects, astrometry, and transients and variable sources. This review aims to provide a comprehensive overview of the CSST instruments, observational capabilities, data products, and scientific potential.

astro-ph.IM↗

arXiv2025

A misaligned protostellar disk fed by gas streamers in a barred spiral-like massive dense core

High-mass stars, born in massive dense cores (MDCs), profoundly impact the cosmic ecosystem through feedback processes and metal enrichment, yet little is known about how MDCs assemble and transfer mass across scales to form high-mass young stellar objects (HMYSOs). Using multi-scale (40-2500 au) observations of an MDC hosting an HMYSO, we identify a coherent dynamical structure analogous to barred spiral galaxies: three 20,000 au spiral arms feed a 7,500 au central bar, which channels gas to a 2,000 au pseudodisk. Further accretion proceeds through the inner structures, including a Keplerian disk and an inner disk (100 au), which are thought to be driving a collimated bipolar outflow. This is the first time that these multi-scale structures (spiral arms, bar, streamers, envelope, disk, and outflow) have been simultaneously observed as a physically coherent structure within an MDC. Our discovery suggests that well-organized hierarchical structures play a crucial role during the gas accretion and angular momentum build-up of a massive disk.

astro-ph.GA↗

arXiv2025

Scientific Objectives of the Xue-shan-mu-chang 15-meter Submillimeter Telescope

Submillimeter astronomy is poised to revolutionize our understanding of the Universe by revealing cosmic phenomena hidden from optical and near-infrared observations, particularly those associated with interstellar dust, molecular gas, and star formation. The Xue-shan-mu-chang 15-meter submillimeter telescope (XSMT-15m), to be constructed at a premier high-altitude site (4813 m) in Qinghai, China, marks a major milestone for Chinese astronomy, establishing the China mainland's first independently developed, world-class submillimeter facility. Equipped with state-of-the-art instruments, XSMT-15m will address a diverse range of frontier scientific questions spanning extragalactic astronomy, Galactic structure, time-domain astrophysics, and astrochemistry. In synergy with current and forthcoming observatories, XSMT-15m will illuminate the formation and evolution of galaxies, unravel the physical and chemical processes shaping the interstellar medium, and explore transient phenomena in the submillimeter regime. These capabilities will advance our understanding across extragalactic astronomy, Galactic ecology, astrochemistry, and time-domain astrophysics, inaugurating a new era for submillimeter research in China and the northern hemisphere.

astro-ph.GA↗

arXiv2025

Pruning Spurious Subgraphs for Graph Out-of-Distribution Generalization

Graph Neural Networks (GNNs) often encounter significant performance degradation under distribution shifts between training and test data, hindering their applicability in real-world scenarios. Recent studies have proposed various methods to address the out-of-distribution generalization challenge, with many methods in the graph domain focusing on directly identifying an invariant subgraph that is predictive of the target label. However, we argue that identifying the edges from the invariant subgraph directly is challenging and error-prone, especially when some spurious edges exhibit strong correlations with the targets. In this paper, we propose PrunE, the first pruning-based graph OOD method that eliminates spurious edges to improve OOD generalizability. By pruning spurious edges, PrunE retains the invariant subgraph more comprehensively, which is critical for OOD generalization. Specifically, PrunE employs two regularization terms to prune spurious edges: 1) graph size constraint to exclude uninformative spurious edges, and 2) $ε$-probability alignment to further suppress the occurrence of spurious edges. Through theoretical analysis and extensive experiments, we show that PrunE achieves superior OOD performance and outperforms previous state-of-the-art methods significantly. Codes are available at: \href{https://github.com/tianyao-aka/PrunE-GraphOOD}{https://github.com/tianyao-aka/PrunE-GraphOOD}.

cs.LG↗

arXiv2025

SynMatch: Rethinking Consistency in Medical Image Segmentation with Sparse Annotations

Label scarcity remains a major challenge in deep learning-based medical image segmentation. Recent studies use strong-weak pseudo supervision to leverage unlabeled data. However, performance is often hindered by inconsistencies between pseudo labels and their corresponding unlabeled images. In this work, we propose \textbf{SynMatch}, a novel framework that sidesteps the need for improving pseudo labels by synthesizing images to match them instead. Specifically, SynMatch synthesizes images using texture and shape features extracted from the same segmentation model that generates the corresponding pseudo labels for unlabeled images. This design enables the generation of highly consistent synthesized-image-pseudo-label pairs without requiring any training parameters for image synthesis. We extensively evaluate SynMatch across diverse medical image segmentation tasks under semi-supervised learning (SSL), weakly-supervised learning (WSL), and barely-supervised learning (BSL) settings with increasingly limited annotations. The results demonstrate that SynMatch achieves superior performance, especially in the most challenging BSL setting. For example, it outperforms the recent strong-weak pseudo supervision-based method by 29.71\% and 10.05\% on the polyp segmentation task with 5\% and 10\% scribble annotations, respectively. The code will be released at https://github.com/Senyh/SynMatch.

cs.CV↗

arXiv2025

Radio continuum and \HI 21-cm line observations of a nearby luminous infrared galaxy IRAS 17526+3253

We present results from our EVN and GMRT observations of the radio continuum and spectral line emission in IRAS 17526+3253, along with an analysis of its arcsecond-scale radio properties using archival VLA data. The EVN observations detected radio continuum emission from both the northwest (NW) and southeast (SE) nuclei. The NW nucleus shows two components with high brightness temperatures and radio luminosities, likely indicating the presence of an AGN core and jet. Meanwhile, our EVN observation failed to detect the OH line emission, possibly due to radio frequency interference and/or the emission being partly resolved out and below our detection limit. The multi-band radio spectral energy distribution (SED) deviates from a single power-law at low frequencies, suggesting low-frequency absorption. The GMRT spectral line data reveal both \HI absorption and emission. The \HI emission is diffuse and shows a velocity gradient from about 7500 \kms in the NW to 7800 \kms in the SE nucleus. On larger scales, the \HI emission extends about 4' along the NW-SE direction, with the southeastern extension matching the optical tidal tail. In addition, the weak \HI absorption features show broad line profiles, possibly due to overlapping \HI gas from the two nuclei. The aforementioned results are consistent with properties of intermediate-stage mergers reported in the literature.

astro-ph.GA↗

arXiv2025

One Last Attention for Your Vision-Language Model

Pretrained vision-language models (VLMs), such as CLIP, achieve remarkable zero-shot performance, yet their downstream potential hinges on effective fine-tuning. Most adaptation methods typically focus on refining representation from separate modalities (text or vision) but neglect the critical role of their fused representations in the decision-making process, \emph{\ie} rational matrix that drives the final prediction. To bridge the gap, we propose a simple yet effective \textbf{R}ational \textbf{Ada}ptaion ({RAda}) to explicitly exploit the final fused representation during fine-tuning. RAda employs a learned mask, obtained from a lightweight attention layer attached at the end of a VLM, to dynamically calibrate the contribution of each element in the rational matrix, enabling targeted adjustments to the final cross-modal interactions without incurring costly modifications to intermediate features. Experiments in different settings (i.e., updating, or freezing pretrained encoders in adaptation, and test-time training that can only access the unlabeled test data) show that RAda serves as a versatile fine-tuning technique, improving the baseline with minimal code and performing comparably against current arts in most settings. Code is available at \href{https://github.com/khufia/RAda/tree/main}{github.com/khufia/RAda}.

cs.CV↗

arXiv2025

VideoMolmo: Spatio-Temporal Grounding Meets Pointing

Spatio-temporal localization is vital for precise interactions across diverse domains, from biological research to autonomous navigation and interactive interfaces. Current video-based approaches, while proficient in tracking, lack the sophisticated reasoning capabilities of large language models, limiting their contextual understanding and generalization. We introduce VideoMolmo, a large multimodal model tailored for fine-grained spatio-temporal pointing conditioned on textual descriptions. Building upon the Molmo architecture, VideoMolmo incorporates a temporal module utilizing an attention mechanism to condition each frame on preceding frames, ensuring temporal consistency. Additionally, our novel temporal mask fusion pipeline employs SAM2 for bidirectional point propagation, significantly enhancing coherence across video sequences. This two-step decomposition, i.e., first using the LLM to generate precise pointing coordinates, then relying on a sequential mask-fusion module to produce coherent segmentation, not only simplifies the task for the language model but also enhances interpretability. Due to the lack of suitable datasets, we curate a comprehensive dataset comprising 72k video-caption pairs annotated with 100k object points. To evaluate the generalization of VideoMolmo, we introduce VPoS-Bench, a challenging out-of-distribution benchmark spanning five real-world scenarios: Cell Tracking, Egocentric Vision, Autonomous Driving, Video-GUI Interaction, and Robotics. We also evaluate our model on Referring Video Object Segmentation (Refer-VOS) and Reasoning VOS tasks. In comparison to existing models, VideoMolmo substantially improves spatio-temporal pointing accuracy and reasoning capability. Our code and models are publicly available at https://github.com/mbzuai-oryx/VideoMolmo.

cs.CV↗

arXiv2025

FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation

Residual connection has been extensively studied and widely applied at the model architecture level. However, its potential in the more challenging data-centric approaches remains unexplored. In this work, we introduce the concept of Data Residual Matching for the first time, leveraging data-level skip connections to facilitate data generation and mitigate data information vanishing. This approach maintains a balance between newly acquired knowledge through pixel space optimization and existing core local information identification within raw data modalities, specifically for the dataset distillation task. Furthermore, by incorporating optimization-level refinements, our method significantly improves computational efficiency, achieving superior performance while reducing training time and peak GPU memory usage by 50%. Consequently, the proposed method Fast and Accurate Data Residual Matching for Dataset Distillation (FADRM) establishes a new state-of-the-art, demonstrating substantial improvements over existing methods across multiple dataset benchmarks in both efficiency and effectiveness. For instance, with ResNet-18 as the student model and a 0.8% compression ratio on ImageNet-1K, the method achieves 47.7% test accuracy in single-model dataset distillation and 50.0% in multi-model dataset distillation, surpassing RDED by +5.7% and outperforming state-of-the-art multi-model approaches, EDC and CV-DD, by +1.4% and +4.0%. Code is available at: https://github.com/Jiacheng8/FADRM.

cs.CV↗

arXiv2025

KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding

With the growing adoption of Retrieval-Augmented Generation (RAG) in document processing, robust text recognition has become increasingly critical for knowledge extraction. While OCR (Optical Character Recognition) for English and other languages benefits from large datasets and well-established benchmarks, Arabic OCR faces unique challenges due to its cursive script, right-to-left text flow, and complex typographic and calligraphic features. We present KITAB-Bench, a comprehensive Arabic OCR benchmark that fills the gaps in current evaluation systems. Our benchmark comprises 8,809 samples across 9 major domains and 36 sub-domains, encompassing diverse document types including handwritten text, structured tables, and specialized coverage of 21 chart types for business intelligence. Our findings show that modern vision-language models (such as GPT-4o, Gemini, and Qwen) outperform traditional OCR approaches (like EasyOCR, PaddleOCR, and Surya) by an average of 60% in Character Error Rate (CER). Furthermore, we highlight significant limitations of current Arabic OCR models, particularly in PDF-to-Markdown conversion, where the best model Gemini-2.0-Flash achieves only 65% accuracy. This underscores the challenges in accurately recognizing Arabic text, including issues with complex fonts, numeral recognition errors, word elongation, and table structure detection. This work establishes a rigorous evaluation framework that can drive improvements in Arabic document analysis methods and bridge the performance gap with English OCR technologies.

cs.CV↗