arXiv subjects

Jian Zhang

Publications and source records attributed to Jian Zhang.

At least 217 records · Page 12Linked to original sources

arXiv2025

AvatarShield: Visual Reinforcement Learning for Human-Centric Synthetic Video Detection

Recent advances in Artificial Intelligence Generated Content have led to highly realistic synthetic videos, particularly in human-centric scenarios involving speech, gestures, and full-body motion, posing serious threats to information authenticity and public trust. Unlike DeepFake techniques that focus on localized facial manipulation, human-centric video generation methods can synthesize entire human bodies with controllable movements, enabling complex interactions with environments, objects, and even other people. However, existing detection methods largely overlook the growing risks posed by such full-body synthetic content. Meanwhile, a growing body of research has explored leveraging LLMs for interpretable fake detection, aiming to explain decisions in natural language. Yet these approaches heavily depend on supervised fine-tuning, which introduces limitations such as annotation bias, hallucinated supervision, and weakened generalization. To address these challenges, we propose AvatarShield, a novel multimodal human-centric synthetic video detection framework that eliminates the need for dense textual supervision by adopting Group Relative Policy Optimization, enabling LLMs to develop reasoning capabilities from simple binary labels. Our architecture combines a discrete vision tower for high-level semantic inconsistencies and a residual extractor for fine-grained artifact analysis. We further introduce FakeHumanVid, a large-scale benchmark containing 15K real and synthetic videos across nine state-of-the-art human generation methods driven by text, pose, or audio. Extensive experiments demonstrate that AvatarShield outperforms existing methods in both in-domain and cross-domain settings.

cs.CV↗

arXiv2025

AlignedGen: Aligning Style Across Generated Images

Despite their generative power, diffusion models struggle to maintain style consistency across images conditioned on the same style prompt, hindering their practical deployment in creative workflows. While several training-free methods attempt to solve this, they are constrained to the U-Net architecture, which not only leads to low-quality results and artifacts like object repetition but also renders them incompatible with superior Diffusion Transformer (DiT). To address these issues, we introduce AlignedGen, a novel training-free framework that enhances style consistency across images generated by DiT models. Our work first reveals a critical insight: naive attention sharing fails in DiT due to conflicting positional signals from improper position embeddings. We introduce Shifted Position Embedding (ShiftPE), an effective solution that resolves this conflict by allocating a non-overlapping set of positional indices to each image. Building on this foundation, we develop Advanced Attention Sharing (AAS), a suite of three techniques meticulously designed to fully unleash the potential of attention sharing within the DiT. Furthermore, to broaden the applicability of our method, we present an efficient query, key, and value feature extraction algorithm, enabling our method to seamlessly incorporate external images as style references. Extensive experimental results validate that our method effectively enhances style consistency across generated images while maintaining precise text-to-image alignment.

cs.CV↗

arXiv2025

$L^2$-contraction and asymptotic stability of large shock for scalar viscous conservation laws

We investigate $L^2$-contraction and time-asymptotic stability of large shock for scalar viscous conservation laws with polynomial flux. For the strictly convex flux $f(u)=u^p $ with $2\leq p \leq 4$, we can prove $L^2$-contraction and time-asymptotic stability of arbitrarily large viscous shock profile in $H^1$-framework by using $a$-contraction method with time-dependent shift and suitable weight function. Additionally, if the initial perturbation belongs to $L^1$, then $L^2$ time-asymptotic decay rate $t^{-\frac{1}{4}}$ can be obtained.

math.AP↗

arXiv2025

NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model

We introduce Nemotron-Nano-9B-v2, a hybrid Mamba-Transformer language model designed to increase throughput for reasoning workloads while achieving state-of-the-art accuracy compared to similarly-sized models. Nemotron-Nano-9B-v2 builds on the Nemotron-H architecture, in which the majority of the self-attention layers in the common Transformer architecture are replaced with Mamba-2 layers, to achieve improved inference speed when generating the long thinking traces needed for reasoning. We create Nemotron-Nano-9B-v2 by first pre-training a 12-billion-parameter model (Nemotron-Nano-12B-v2-Base) on 20 trillion tokens using an FP8 training recipe. After aligning Nemotron-Nano-12B-v2-Base, we employ the Minitron strategy to compress and distill the model with the goal of enabling inference on up to 128k tokens on a single NVIDIA A10G GPU (22GiB of memory, bfloat16 precision). Compared to existing similarly-sized models (e.g., Qwen3-8B), we show that Nemotron-Nano-9B-v2 achieves on-par or better accuracy on reasoning benchmarks while achieving up to 6x higher inference throughput in reasoning settings like 8k input and 16k output tokens. We are releasing Nemotron-Nano-9B-v2, Nemotron-Nano12B-v2-Base, and Nemotron-Nano-9B-v2-Base checkpoints along with the majority of our pre- and post-training datasets on Hugging Face.

cs.CL↗

arXiv2025

Quantile Function-Based Models for Neuroimaging Classification Using Wasserstein Regression

We propose a novel quantile function-based approach for neuroimaging classification using Wasserstein-Fréchet regression, specifically applied to the detection of mild traumatic brain injury (mTBI) based on the MEG and MRI data. Conventional neuroimaging classification methods for mTBI detection typically extract summary statistics from brain signals across the different epochs, which may result in the loss of important distributional information, such as variance, skewness, kurtosis, etc. Our approach treats complete probability density functions of epoch space results as functional response variables within a Wasserstein-Fréchet regression framework, thereby preserving the full distributional characteristics of epoch results from $L_{1}$ minimum norm solutions. The global Wasserstein-Fréchet regression model incorporating covariates (age and gender) allows us to directly compare the distributional patterns between healthy control subjects and mTBI patients. The classification procedure computes Wasserstein distances between estimated quantile functions from control and patient groups, respectively. These distances are then used as the basis for diagnostic decisions. This framework offers a statistically principled approach to improving diagnostic accuracy in mTBI detection. In practical applications, the test accuracy on unseen data from Innovision IP's dataset achieves up to 98\%.

stat.AP↗

arXiv2025

Immanant inequalities and weight spaces

We first obtain a trace formula for immanants of generalized principal submatrix of any complex matrix based on any weight space for finite dimensional representations of the general linear group. Our trace formula contains Kostant's famous formula for immanants on $0$-weight spaces as special case. We then present a criterion for non-vanishing immanants for any generalized principal submatrix of positive definite Hermitian or nonsingular totally nonnegative matrices, which strengthened the well-known results of Schur and Stembridge. Furthermore, we present an inequality that contains Kostant, Schur and Stembridge's famous inequalities as special cases.

math.RT↗

arXiv2025

A unified multi-perspective quadratic manifold for mitigating the Kolmogorov barrier in multiphysics damage

In multiphysics damage problems, material degradation is often modeled using local or global damage variables, whose evolution introduces strong nonlinearities and significant computational costs. Linear projection-based reduced-order models (ROMs) are widely used to accelerate these simulations but often fail to capture complex nonlinear damage evolution effectively. This limitation arises from the slow decay of the Kolmogorov n-width, which leads to a phenomenon known as the Kolmogorov barrier in linear approximation. To overcome this challenge, this study proposes a novel unified multi-perspective (multi-field and multi-state) quadratic manifold-based ROM framework for thermo-mechanically coupled damage-plasticity problems. A key feature lies in a multi-field and multi-state decomposition strategy that is grounded in the material's physical response to guide the selection of mode numbers for each coupled field. Moreover, the framework decouples both material states and physical fields, providing clearer insights into the contributions and interactions of each field within the overall multiphysics simulation. Benchmark tests demonstrate that the proposed approach mitigates the Kolmogorov barrier of linear projection-based ROMs by ensuring a smooth and monotonic decrease in error as the number of modes increases. The proposed multi-perspective quadratic manifold framework offers a robust and flexible approach for efficiently reducing complex damage-involved multiphysics problems and shows strong potential for industrial applications.

math-ph↗

arXiv2025

Comprehensive Statistical Analysis of Initial Lorentz Factor and Jet Opening Angle of Gamma-Ray Bursts

The initial Lorentz factor ($Γ_{0}$) and jet half-opening angle ($θ_{\rm jet}$) of gamma-ray bursts (GRBs) are critical physical parameters for understanding the dynamical evolution of relativistic jets and the true energy release of GRBs. We compile a sample of 89 GRBs that exhibit an onset bump feature in their early optical or GeV light curves, 42 of which also display a jet break feature, and derive their $Γ_{0}$ and $θ_{\rm jet}$ values. Using this sample, we re-eaxmine the correlations between $Γ_{0}$ and the prompt emission parameters (isotropic energy $E_{\rm iso}$, peak luminosity $L_{\rm iso}$, and peak energy $E_{\rm p}$). Our results confirm the previously reported $Γ_{0}$$-$$E_{\rm iso}$ ($L_{\rm iso}$), $Γ_{0}$$-$$E_{\rm p,z}$, and $E_{\rm iso}$ ($L_{\rm iso}$)$-$$E_{\rm p}$$-$$Γ_{0}$ relations for both homogeneous interstellar medium (ISM) and wind density profiles (Wind). Notably, we find that the short GRB 090510 complies with the $Γ_{0}$$-$$E_{\rm iso}$ relation, but significantly deviates from the $Γ_{0}$$-$$L_{\rm iso}$ and $Γ_{0}$$-$$E_{\rm p,z}$ relations. We systematically investigate the influence of $θ_{\rm jet}$ on $Γ_{0}$ and find a weak dependence. Additionally, we report, for the first time, three new three-parameter correlations, i.e., $E_{\rm iso}$ (or $L_{\rm iso}$, $E_{\rm p,z}$)$-$$Γ_{0}$$-$$θ_{\rm jet}$ correlations. In addition, we further explore the relations between the initial Lorentz factor and the jet-corrected energy. We also find that the jet-corrected correlations remain significant, suggesting that these relations are intrinsic to the physical nature of GRBs. However, the increased dispersion after correction implies that underlying differences persist among individual GRBs.

astro-ph.HE↗

arXiv2025

Diversity-enhanced Collaborative Mamba for Semi-supervised Medical Image Segmentation

Acquiring high-quality annotated data for medical image segmentation is tedious and costly. Semi-supervised segmentation techniques alleviate this burden by leveraging unlabeled data to generate pseudo labels. Recently, advanced state space models, represented by Mamba, have shown efficient handling of long-range dependencies. This drives us to explore their potential in semi-supervised medical image segmentation. In this paper, we propose a novel Diversity-enhanced Collaborative Mamba framework (namely DCMamba) for semi-supervised medical image segmentation, which explores and utilizes the diversity from data, network, and feature perspectives. Firstly, from the data perspective, we develop patch-level weak-strong mixing augmentation with Mamba's scanning modeling characteristics. Moreover, from the network perspective, we introduce a diverse-scan collaboration module, which could benefit from the prediction discrepancies arising from different scanning directions. Furthermore, from the feature perspective, we adopt an uncertainty-weighted contrastive learning mechanism to enhance the diversity of feature representation. Experiments demonstrate that our DCMamba significantly outperforms other semi-supervised medical image segmentation methods, e.g., yielding the latest SSM-based method by 6.69% on the Synapse dataset with 20% labeled data.

cs.CV↗

arXiv2025

SSPFusion: A Semantic Structure-Preserving Approach for Infrared and Visible Image Fusion

Most existing learning-based multi-modality image fusion (MMIF) methods suffer from significant structure inconsistency due to their inappropriate usage of structural features at the semantic level. To alleviate these issues, we propose a semantic structure-preserving fusion approach for MMIF, namely SSPFusion. At first, we design a structural feature extractor (SFE) to extract the prominent structural features from multiple input images. Concurrently, we introduce a transformation function with Sobel operator to generate self-supervised structural signals in these extracted features. Subsequently, we design a multi-scale structure-preserving fusion (SPF) module, guided by the generated structural signals, to merge the structural features of input images. This process ensures the preservation of semantic structure consistency between the resultant fusion image and the input images. Through the synergy of these two robust modules of SFE and SPF, our method can generate high-quality fusion images and demonstrate good generalization ability. Experimental results, on both infrared-visible image fusion and medical image fusion tasks, demonstrate that our method outperforms nine state-of-the-art methods in terms of both qualitative and quantitative evaluations. The code is publicly available at https://github.com/QiaoYang-CV/SSPFUSION.

cs.CV↗

arXiv2025

Towards Perfection: Building Inter-component Mutual Correction for Retinex-based Low-light Image Enhancement

In low-light image enhancement, Retinex-based deep learning methods have garnered significant attention due to their exceptional interpretability. These methods decompose images into mutually independent illumination and reflectance components, allows each component to be enhanced separately. In fact, achieving perfect decomposition of illumination and reflectance components proves to be quite challenging, with some residuals still existing after decomposition. In this paper, we formally name these residuals as inter-component residuals (ICR), which has been largely underestimated by previous methods. In our investigation, ICR not only affects the accuracy of the decomposition but also causes enhanced components to deviate from the ideal outcome, ultimately reducing the final synthesized image quality. To address this issue, we propose a novel Inter-correction Retinex model (IRetinex) to alleviate ICR during the decomposition and enhancement stage. In the decomposition stage, we leverage inter-component residual reduction module to reduce the feature similarity between illumination and reflectance components. In the enhancement stage, we utilize the feature similarity between the two components to detect and mitigate the impact of ICR within each enhancement unit. Extensive experiments on three low-light benchmark datasets demonstrated that by reducing ICR, our method outperforms state-of-the-art approaches both qualitatively and quantitatively.

cs.CV↗

arXiv2025

Correspondence as Video: Test-Time Adaption on SAM2 for Reference Segmentation in the Wild

Large vision models like the Segment Anything Model (SAM) exhibit significant limitations when applied to downstream tasks in the wild. Consequently, reference segmentation, which leverages reference images and their corresponding masks to impart novel knowledge to the model, emerges as a promising new direction for adapting vision models. However, existing reference segmentation approaches predominantly rely on meta-learning, which still necessitates an extensive meta-training process and brings massive data and computational cost. In this study, we propose a novel approach by representing the inherent correspondence between reference-target image pairs as a pseudo video. This perspective allows the latest version of SAM, known as SAM2, which is equipped with interactive video object segmentation (iVOS) capabilities, to be adapted to downstream tasks in a lightweight manner. We term this approach Correspondence As Video for SAM (CAV-SAM). CAV-SAM comprises two key modules: the Diffusion-Based Semantic Transition (DBST) module employs a diffusion model to construct a semantic transformation sequence, while the Test-Time Geometric Alignment (TTGA) module aligns the geometric changes within this sequence through test-time fine-tuning. We evaluated CAVSAM on widely-used datasets, achieving segmentation performance improvements exceeding 5% over SOTA methods. Implementation is provided in the supplementary materials.

cs.CV↗

arXiv2025

4DVD: Cascaded Dense-view Video Diffusion Model for High-quality 4D Content Generation

Given the high complexity of directly generating high-dimensional data such as 4D, we present 4DVD, a cascaded video diffusion model that generates 4D content in a decoupled manner. Unlike previous multi-view video methods that directly model 3D space and temporal features simultaneously with stacked cross view/temporal attention modules, 4DVD decouples this into two subtasks: coarse multi-view layout generation and structure-aware conditional generation, and effectively unifies them. Specifically, given a monocular video, 4DVD first predicts the dense view content of its layout with superior cross-view and temporal consistency. Based on the produced layout priors, a structure-aware spatio-temporal generation branch is developed, combining these coarse structural priors with the exquisite appearance content of input monocular video to generate final high-quality dense-view videos. Benefit from this, explicit 4D representation~(such as 4D Gaussian) can be optimized accurately, enabling wider practical application. To train 4DVD, we collect a dynamic 3D object dataset, called D-Objaverse, from the Objaverse benchmark and render 16 videos with 21 frames for each object. Extensive experiments demonstrate our state-of-the-art performance on both novel view synthesis and 4D generation. Our project page is https://4dvd.github.io/

cs.CV↗

arXiv2025

Fitness aligned structural modeling enables scalable virtual screening with AuroBind

Most human proteins remain undrugged, over 96% of human proteins remain unexploited by approved therapeutics. While structure-based virtual screening promises to expand the druggable proteome, existing methods lack atomic-level precision and fail to predict binding fitness, limiting translational impact. We present AuroBind, a scalable virtual screening framework that fine-tunes a custom atomic-level structural model on million-scale chemogenomic data. AuroBind integrates direct preference optimization, self-distillation from high-confidence complexes, and a teacher-student acceleration strategy to jointly predict ligand-bound structures and binding fitness. The proposed models outperform state-of-the-art models on structural and functional benchmarks while enabling 100,000-fold faster screening across ultra-large compound libraries. In a prospective screen across ten disease-relevant targets, AuroBind achieved experimental hit rates of 7-69%, with top compounds reaching sub-nanomolar to picomolar potency. For the orphan GPCRs GPR151 and GPR160, AuroBind identified both agonists and antagonists with success rates of 16-30%, and functional assays confirmed GPR160 modulation in liver and prostate cancer models. AuroBind offers a generalizable framework for structure-function learning and high-throughput molecular screening, bridging the gap between structure prediction and therapeutic discovery.

cs.LG↗

arXiv2025

Ambiguity-Guided Learnable Distribution Calibration for Semi-Supervised Few-Shot Class-Incremental Learning

Few-Shot Class-Incremental Learning (FSCIL) focuses on models learning new concepts from limited data while retaining knowledge of previous classes. Recently, many studies have started to leverage unlabeled samples to assist models in learning from few-shot samples, giving rise to the field of Semi-supervised Few-shot Class-Incremental Learning (Semi-FSCIL). However, these studies often assume that the source of unlabeled data is only confined to novel classes of the current session, which presents a narrow perspective and cannot align well with practical scenarios. To better reflect real-world scenarios, we redefine Semi-FSCIL as Generalized Semi-FSCIL (GSemi-FSCIL) by incorporating both base and all the ever-seen novel classes in the unlabeled set. This change in the composition of unlabeled samples poses a new challenge for existing methods, as they struggle to distinguish between unlabeled samples from base and novel classes. To address this issue, we propose an Ambiguity-guided Learnable Distribution Calibration (ALDC) strategy. ALDC dynamically uses abundant base samples to correct biased feature distributions for few-shot novel classes. Experiments on three benchmark datasets show that our method outperforms existing works, setting new state-of-the-art results.

cs.CV↗

arXiv2025

Testing Autonomous Driving Systems -- What Really Matters and What Doesn't

Despite extensive research, the testing of autonomous driving systems (ADS) landscape remains fragmented, and there is currently no basis for an informed technical assessment of the importance and contribution of the current state of the art. This paper attempts to address this problem by exploring two complementary aspects. First, it proposes a framework for comparing existing test methods in terms of their intrinsic effectiveness and validity. It shows that many methods do not meet both of these requirements. Either because they are based on criteria that do not allow for rapid, inexpensive, and comprehensive detection of failures, or because the degree of validity of the properties tested cannot be accurately estimated. In particular, it is shown that most critical test methods do not take into account the nominal operational capabilities of autopilots and generate scenarios that are impossible for the tested vehicles to handle, resulting in unjustified rejections. Secondly, the paper shows that test effectiveness and validity are highly dependent on how autopilots are designed: how they choose between different control policies to perform maneuvers, as well as on the reproducibility of the results. In fact, most test methods take for granted two principles underlying traditional methods, but do not generally apply to ADS. We maintain that the absence of rationality and determinacy significantly impairs the effectiveness and validity of test methods, and provide test results on eight open autopilots, in which most do not satisfy these properties, thereby illustrating this fact. We conclude that under the current state of the art, it is impossible to obtain strong enough guarantees for essential autopilot properties and recommend that autopilots be developed with a view to both rationality and determinacy.

cs.SE↗

arXiv2025

Robot Operation of Home Appliances by Reading User Manuals

Operating home appliances, among the most common tools in every household, is a critical capability for assistive home robots. This paper presents ApBot, a robot system that operates novel household appliances by "reading" their user manuals. ApBot faces multiple challenges: (i) infer goal-conditioned partial policies from their unstructured, textual descriptions in a user manual document, (ii) ground the policies to the appliance in the physical world, and (iii) execute the policies reliably over potentially many steps, despite compounding errors. To tackle these challenges, ApBot constructs a structured, symbolic model of an appliance from its manual, with the help of a large vision-language model (VLM). It grounds the symbolic actions visually to control panel elements. Finally, ApBot closes the loop by updating the model based on visual feedback. Our experiments show that across a wide range of simulated and real-world appliances, ApBot achieves consistent and statistically significant improvements in task success rate, compared with state-of-the-art large VLMs used directly as control policies. These results suggest that a structured internal representations plays an important role in robust robot operation of home appliances, especially, complex ones.

cs.RO↗

arXiv2025

Towards Cross-modal Retrieval in Chinese Cultural Heritage Documents: Dataset and Solution

China has a long and rich history, encompassing a vast cultural heritage that includes diverse multimodal information, such as silk patterns, Dunhuang murals, and their associated historical narratives. Cross-modal retrieval plays a pivotal role in understanding and interpreting Chinese cultural heritage by bridging visual and textual modalities to enable accurate text-to-image and image-to-text retrieval. However, despite the growing interest in multimodal research, there is a lack of specialized datasets dedicated to Chinese cultural heritage, limiting the development and evaluation of cross-modal learning models in this domain. To address this gap, we propose a multimodal dataset named CulTi, which contains 5,726 image-text pairs extracted from two series of professional documents, respectively related to ancient Chinese silk and Dunhuang murals. Compared to existing general-domain multimodal datasets, CulTi presents a challenge for cross-modal retrieval: the difficulty of local alignment between intricate decorative motifs and specialized textual descriptions. To address this challenge, we propose LACLIP, a training-free local alignment strategy built upon a fine-tuned Chinese-CLIP. LACLIP enhances the alignment of global textual descriptions with local visual regions by computing weighted similarity scores during inference. Experimental results on CulTi demonstrate that LACLIP significantly outperforms existing models in cross-modal retrieval, particularly in handling fine-grained semantic associations within Chinese cultural heritage.

cs.CV↗