arXiv subjects

Cong Wang

Publications and source records attributed to Cong Wang.

At least 145 records · Page 8Linked to original sources

arXiv2026

vLLM-Omni: Fully Disaggregated Serving for Any-to-Any Multimodal Models

Any-to-any multimodal models that jointly handle text, images, video, and audio represent a significant advance in multimodal AI. However, their complex architectures (typically combining multiple autoregressive LLMs, diffusion transformers, and other specialized components) pose substantial challenges for efficient model serving. Existing serving systems are mainly tailored to a single paradigm, such as autoregressive LLMs for text generation or diffusion transformers for visual generation. They lack support for any-to-any pipelines that involve multiple interconnected model components. As a result, developers must manually handle cross-stage interactions, leading to huge performance degradation. We present vLLM-Omni, a fully disaggregated serving system for any-to-any models. vLLM-Omni features a novel stage abstraction that enables users to decompose complex any-to-any architectures into interconnected stages represented as a graph, and a disaggregated stage execution backend that optimizes resource utilization and throughput across stages. Each stage is independently served by an LLM or diffusion engine with per-stage request batching, flexible GPU allocation, and unified inter-stage connectors for data routing. Experimental results demonstrate that vLLM-Omni reduces job completion time (JCT) by up to 91.4% compared to baseline methods. The code is public available at https://github.com/vllm-project/vllm-omni.

cs.DC↗

arXiv2026

Who Transfers Safety? Identifying and Targeting Cross-Lingual Shared Safety Neurons

Multilingual safety remains significantly imbalanced, leaving non-high-resource (NHR) languages vulnerable compared to robust high-resource (HR) ones. Moreover, the neural mechanisms driving safety alignment remain unclear despite observed cross-lingual representation transfer. In this paper, we find that LLMs contain a set of cross-lingual shared safety neurons (SS-Neurons), a remarkably small yet critical neuronal subset that jointly regulates safety behavior across languages. We first identify monolingual safety neurons (MS-Neurons) and validate their causal role in safety refusal behavior through targeted activation and suppression. Our cross-lingual analyses then identify SS-Neurons as the subset of MS-Neurons shared between HR and NHR languages, serving as a bridge to transfer safety capabilities from HR to NHR domains. We observe that suppressing these neurons causes concurrent safety drops across NHR languages, whereas reinforcing them improves cross-lingual defensive consistency. Building on these insights, we propose a simple neuron-oriented training strategy that targets SS-Neurons based on language resource distribution and model architecture. Experiments demonstrate that fine-tuning this tiny neuronal subset outperforms state-of-the-art methods, significantly enhancing NHR safety while maintaining the model's general capabilities. The code and dataset will be available athttps://github.com/1518630367/SS-Neuron-Expansion.

cs.CV↗

arXiv2026

TraceRouter: Robust Safety for Large Foundation Models via Path-Level Intervention

Despite their capabilities, large foundation models (LFMs) remain susceptible to adversarial manipulation. Current defenses predominantly rely on the "locality hypothesis", suppressing isolated neurons or features. However, harmful semantics act as distributed, cross-layer circuits, rendering such localized interventions brittle and detrimental to utility. To bridge this gap, we propose \textbf{TraceRouter}, a path-level framework that traces and disconnects the causal propagation circuits of illicit semantics. TraceRouter operates in three stages: (1) it pinpoints a sensitive onset layer by analyzing attention divergence; (2) it leverages sparse autoencoders (SAEs) and differential activation analysis to disentangle and isolate malicious features; and (3) it maps these features to downstream causal pathways via feature influence scores (FIS) derived from zero-out interventions. By selectively suppressing these causal chains, TraceRouter physically severs the flow of harmful information while leaving orthogonal computation routes intact. Extensive experiments demonstrate that TraceRouter significantly outperforms state-of-the-art baselines, achieving a superior trade-off between adversarial robustness and general utility. Our code will be publicly released. WARNING: This paper contains unsafe model responses.

cs.CV↗

arXiv2026

Post-Norm can Resharpen Attention

Length Generalization is the essential capacity of autonomous agents to perform tasks in longer contexts than those encountered during training. To systematically study this feat, we test how well models can approximate the next token distributions in algorithmic tasks. This is to take into account the realistic possibility of multiple next tokens being legal. We present a prototypical benchmark for this line of study: in the Set Complement Task, the model needs to output a uniform distribution over tokens not in the input. We prove a theorem that states simple transformers can length generalize on this task, however, with performance degradation due to attention dispersion. A mechanistic reading of how dispersion takes effect lets us discover a remedy: Post-Norm can Resharpen Attention. We present experimental evidence to support this idea. We also show that Exponential Moving Averages can help the issue of noisy gradients that arises when many next tokens are legal. We validate the general applicability of our proposed methods on a suite of formal language experiments. Our source code will be available upon publication.

cs.LG↗

arXiv2026

Innovator-VL: A Multimodal Large Language Model for Scientific Discovery

We present Innovator-VL, a scientific multimodal large language model designed to advance understanding and reasoning across diverse scientific domains while maintaining excellent performance on general vision tasks. Contrary to the trend of relying on massive domain-specific pretraining and opaque pipelines, our work demonstrates that principled training design and transparent methodology can yield strong scientific intelligence with substantially reduced data requirements. (i) First, we provide a fully transparent, end-to-end reproducible training pipeline, covering data collection, cleaning, preprocessing, supervised fine-tuning, reinforcement learning, and evaluation, along with detailed optimization recipes. This facilitates systematic extension by the community. (ii) Second, Innovator-VL exhibits remarkable data efficiency, achieving competitive performance on various scientific tasks using fewer than five million curated samples without large-scale pretraining. These results highlight that effective reasoning can be achieved through principled data selection rather than indiscriminate scaling. (iii) Third, Innovator-VL demonstrates strong generalization, achieving competitive performance on general vision, multimodal reasoning, and scientific benchmarks. This indicates that scientific alignment can be integrated into a unified model without compromising general-purpose capabilities. Our practices suggest that efficient, reproducible, and high-performing scientific multimodal models can be built even without large-scale data, providing a practical foundation for future research.

cs.CV↗

arXiv2026

HYDRA: Breaking the Global Ordering Barrier in Multi-BFT Consensus

Multi-Byzantine Fault Tolerant (Multi-BFT) consensus, which runs multiple BFT instances in parallel, has recently emerged as a promising approach to overcome the leader bottleneck in classical BFT protocols. However, existing designs rely on a global ordering layer to serialize blocks across instances, an intuitive yet costly mechanism that constrains scalability, amplifies failure propagation, and complicates deployment. In this paper, we challenge this conventional wisdom. We present HYDRA, the first Multi-BFT consensus framework that eliminates global ordering altogether. HYDRA introduces an object-centric execution model that partitions transactions by their accessed objects, enabling concurrent yet deterministic execution across instances. To ensure consistency, HYDRA combines lightweight lock-based coordination with a deadlock resolution mechanism, achieving both scalability and correctness. We implement HYDRA and evaluate it on up to 128 replicas in both LAN and WAN environments. Experimental results show HYDRA outperforms several state-of-the-art Multi-BFT protocols in the presence of a straggler. These results demonstrate strong consistency and high performance by removing global ordering, opening a new direction toward scalable Multi-BFT consensus design.

cs.DC↗

arXiv2026

PrivTune: Efficient and Privacy-Preserving Fine-Tuning of Large Language Models via Device-Cloud Collaboration

With the rise of large language models, service providers offer language models as a service, enabling users to fine-tune customized models via uploaded private datasets. However, this raises concerns about sensitive data leakage. Prior methods, relying on differential privacy within device-cloud collaboration frameworks, struggle to balance privacy and utility, exposing users to inference attacks or degrading fine-tuning performance. To address this, we propose PrivTune, an efficient and privacy-preserving fine-tuning framework via Split Learning (SL). The key idea of PrivTune is to inject crafted noise into token representations from the SL bottom model, making each token resemble the $n$-hop indirect neighbors. PrivTune formulates this as an optimization problem to compute the optimal noise vector, aligning with defense-utility goals. On this basis, it then adjusts the parameters (i.e., mean) of the $d_χ$-Privacy noise distribution to align with the optimization direction and scales the noise according to token importance to minimize distortion. Experiments on five datasets (covering both classification and generation tasks) against three embedding inversion and three attribute inference attacks show that, using RoBERTa on the Stanford Sentiment Treebank dataset, PrivTune reduces the attack success rate to 10% with only a 3.33% drop in utility performance, outperforming state-of-the-art baselines.

cs.CR↗

arXiv2026

Multi-pathline flow visualization using PIV images

One of the oldest flow visualization techniques is through multiple pathlines generated by the movement of seeding particles spatially distributed in the flow. In the computerized era, particle images are used in quantitative measurements, such as particle image and particle tracking velocimetry (PIV and PTV). Here, we present several methods for post-processing raw particle images to generate enhanced flow visualization without a need for conducting additional experiments. Three post-processing methods will be shown: 1) controlling the exposure time, 2) color-coding temporal information, and 3) changing the frame of reference. We showcase how employing these three methods can highlight different flow features in three canonical flow cases: vortex ring, leading edge vortex, and turbulent boundary layer. In addition to the quantitative flow field, the multi-pathline visualization is expected to augment our ability to observe fluid flow from many different perspectives.

physics.flu-dyn↗

arXiv2025

FUSE-RSVLM: Feature Fusion Vision-Language Model for Remote Sensing

Large vision-language models (VLMs) exhibit strong performance across various tasks. However, these VLMs encounter significant challenges when applied to the remote sensing domain due to the inherent differences between remote sensing images and natural images. Existing remote sensing VLMs often fail to extract fine-grained visual features and suffer from visual forgetting during deep language processing. To address this, we introduce MF-RSVLM, a Multi-Feature Fusion Remote Sensing Vision--Language Model that effectively extracts and fuses visual features for RS understanding. MF-RSVLM learns multi-scale visual representations and combines global context with local details, improving the capture of small and complex structures in RS scenes. A recurrent visual feature injection scheme ensures the language model remains grounded in visual evidence and reduces visual forgetting during generation. Extensive experiments on diverse RS benchmarks show that MF-RSVLM achieves state-of-the-art or highly competitive performance across remote sensing classification, image captioning, and VQA tasks. Our code is publicly available at https://github.com/Yunkaidang/RSVLM.

cs.CV↗

arXiv2025

Kinetically accessible 1D magnetic chains of transition-metal chalcogenides and halides on van der Waals surfaces

One-dimensional (1D) chains offer unique opportunities for nanoelectronics and spintronics, yet their experimental realization remains challenging because 1D motifs are often thermodynamically disfavored relative to higher-dimensional phases. Here we present a high-throughput first-principles exploration of 1D single-atomic transition-metal chalcogenide and halide chains, screening 6,832 candidates constructed from binary combinations of 28 metals and 8 non-metals. To assess kinetic accessibility, we compare the formation energetics of 1D chains with competing two-dimensional polymorphs at the nucleation stage across relevant chemical-potential windows, using nucleation-stage thermodynamic selectivity as a proxy. This workflow identifies 183 kinetically accessible 1D chains. Interpretable machine-learning analysis reveals two simple stability descriptors as key drivers of 1D stabilization. The accessible chains exhibit diverse magnetic configurations with different magnetic characters. We further uncover their pronounced magnetoelastic couplings, exemplified by CrTe with giant magnetostriction reaching 5.93%. Finally, we show that selected metallic ferromagnetic chains retain robust edge magnetism on superconducting substrates, laying the groundwork for proximity-induced topological superconductivity and Majorana zero modes.

cond-mat.mtrl-sci↗

arXiv2025

Anomalous Hall effect and rich magnetic phase diagram of Mn$_{100-x}$Rh$_{x}$ epitaxial films

A series of Mn$_{100-x}$Rh$_x$ ($20 \le x \le 50$) thin films were epitaxially grown on the MgO substrate using magnetron sputtering technique, and were systematically investigated by magnetization, longitudinal electrical resistivity, and transverse Hall resistivity. After optimizing the growth conditions, phase-pure Mn$_{100-x}$Rh$_x$ films with a cubic CsCl-type structure were obtained, and their magnetic phase diagram was built. The manipulation of Rh content leads to a rich magnetic phase diagram, where three different regimes can be identified: for $x < 40$, Mn$_{100-x}$Rh$_x$ films undergo a ferromagnetic (FM) transition below $T_\mathrm{C} \approx$ 330-350 K; for $40 \le x \le 45$, in addition to the FM transition at $T_\mathrm{C} \approx$ 200 K, Mn$_{100-x}$Rh$_x$ films undergo a FM-to-antiferromagnetic (AFM) transition at $T_\mathrm{N} \approx$ 120 K; finally for $x > 45$, only one AFM transition at $T_\mathrm{N} \approx$ 150 K can be tracked. All the Mn$_{100-x}$Rh$_x$ films exhibit distinct anomalous Hall effect in their magnetically ordered state, which is most likely due to the intrinsic Berry-curvature mechanism. In addition, all the anomalous Hall transport properties, including the resistivity, conductivity, and angle exhibit a strong correlation with the magnetic properties of Mn$_{100-x}$Rh$_x$ films, which become most evident for $x$ = 35. Our systematic investigations suggest a strong correlation between magnetic properties and electronic band topology in Mn$_{100-x}$Rh$_x$ films, highlighting their great potential for AFM spintronics.

cond-mat.str-el↗

arXiv2025

Amulet: Fast TEE-Shielded Inference for On-Device Model Protection

On-device machine learning (ML) introduces new security concerns about model privacy. Storing valuable trained ML models on user devices exposes them to potential extraction by adversaries. The current mainstream solution for on-device model protection is storing the weights and conducting inference within Trusted Execution Environments (TEEs). However, due to limited trusted memory that cannot accommodate the whole model, most existing approaches employ a partitioning strategy, dividing a model into multiple slices that are loaded into the TEE sequentially. This frequent interaction between untrusted and trusted worlds dramatically increases inference latency, sometimes by orders of magnitude. In this paper, we propose Amulet, a fast TEE-shielded on-device inference framework for ML model protection. Amulet incorporates a suite of obfuscation methods specifically designed for common neural network architectures. After obfuscation by the TEE, the entire transformed model can be securely stored in untrusted memory, allowing the inference process to execute directly in untrusted memory with GPU acceleration. For each inference request, only two rounds of minimal-overhead interaction between untrusted and trusted memory are required to process input samples and output results. We also provide theoretical proof from an information-theoretic perspective that the obfuscated model does not leak information about the original weights. We comprehensively evaluated Amulet using diverse model architectures ranging from ResNet-18 to GPT-2. Our approach incurs inference latency only 2.8-4.8x that of unprotected models with negligible accuracy loss, achieving an 8-9x speedup over baseline methods that execute inference entirely within TEEs, and performing approximately 2.2x faster than the state-of-the-art obfuscation-based method.

cs.CR↗

arXiv2025

Mechanically and electrically switchable triferroic altermagnet in a pentagonal FeO2 monolayer

Two-dimensional multiferroics promise low-power, multifunctional devices, yet the intrinsic coexistence and mutual control of three coupled ferroic orders in a single layer remains elusive. Here, we identify pentagonal monolayer FeO$_2$ as an intrinsic triferroic altermagnet where ferroelectric (FE), ferroelastic (FA), and altermagnetic (AM) orders coexist and are tightly coupled, accompanied by a competing antiferroelectric (AFE) phase using first-principles calculations. The sole presence of glide mirror $M_x$ symmetry in a FeO$_2$ sublayer, with the breaking of four-fold rotation $C_{4z}$ symmetry, induces in-plane vector ferroelectricity and twin-related ferroelastic strains. Both FE and AFE phases break combined parity - time symmetry and display sizable altermagnetic spin splitting with Néel temperatures over 200~K. Electric-field-induced rotation of the FE polarization reverses the sign of the spin splitting, while in-plane uniaxial strain triggers ferroelastic switching that simultaneously rotates the FE polarization vector by $90^\circ$ and reverses the AM state. These electric-field- and strain-mediated pathways interlink six distinct polarization states that can be selected purely by electric fields and/or mechanical strain. This work extends intrinsic triferroicity to pentagonal monolayers and outlines a symmetry-based route toward mechanically and electrically configurable altermagnetic spintronics.

cond-mat.mtrl-sci↗

arXiv2025

Where Culture Fades: Revealing the Cultural Gap in Text-to-Image Generation

Multilingual text-to-image (T2I) models have advanced rapidly in terms of visual realism and semantic alignment, and are now widely utilized. Yet outputs vary across cultural contexts: because language carries cultural connotations, images synthesized from multilingual prompts should preserve cross-lingual cultural consistency. We conduct a comprehensive analysis showing that current T2I models often produce culturally neutral or English-biased results under multilingual prompts. Analyses of two representative models indicate that the issue stems not from missing cultural knowledge but from insufficient activation of culture-related representations. We propose a probing method that localizes culture-sensitive signals to a small set of neurons in a few fixed layers. Guided by this finding, we introduce two complementary alignment strategies: (1) inference-time cultural activation that amplifies the identified neurons without backbone fine-tuned; and (2) layer-targeted cultural enhancement that updates only culturally relevant layers. Experiments on our CultureBench demonstrate consistent improvements over strong baselines in cultural consistency while preserving fidelity and diversity.

cs.CV↗

arXiv2025

Writing With Machines and Peers: Designing for Critical Engagement with Generative AI

The growing integration of generative AI in higher education is transforming how students write, learn, and engage with knowledge. As AI tools become more integrated into classrooms, there is an urgent need for pedagogical approaches that help students use them critically and reflectively. This study proposes a pedagogical design that integrates AI and peer feedback in a graduate-level academic writing activity. Over eight weeks, students developed literature review projects through multiple writing and revision stages, receiving feedback from both a custom-built AI reviewer and human peers. We examine two questions: (1) How did students interact with and incorporate AI and peer feedback during the writing process? and (2) How did they reflect on and build relationships with both human and AI reviewers? Data sources include student writing artifacts, AI and peer feedback, AI chat logs, and student reflections. Findings show that students engaged differently with each feedback source-relying on AI for rubric alignment and surface-level edits, and on peer feedback for conceptual development and disciplinary relevance. Reflections revealed evolving relationships with AI, characterized by increasing confidence, strategic use, and critical awareness of its limitations. The pedagogical design supported writing development, AI literacy, and disciplinary understanding. This study offers a scalable pedagogical model for integrating AI into writing instruction and contributes insights for system-level approaches to fostering meaningful human-AI collaboration in higher education.

cs.CY↗

arXiv2025

RegionMarker: A Region-Triggered Semantic Watermarking Framework for Embedding-as-a-Service Copyright Protection

Embedding-as-a-Service (EaaS) is an effective and convenient deployment solution for addressing various NLP tasks. Nevertheless, recent research has shown that EaaS is vulnerable to model extraction attacks, which could lead to significant economic losses for model providers. For copyright protection, existing methods inject watermark embeddings into text embeddings and use them to detect copyright infringement. However, current watermarking methods often resist only a subset of attacks and fail to provide \textit{comprehensive} protection. To this end, we present the region-triggered semantic watermarking framework called RegionMarker, which defines trigger regions within a low-dimensional space and injects watermarks into text embeddings associated with these regions. By utilizing a secret dimensionality reduction matrix to project onto this subspace and randomly selecting trigger regions, RegionMarker makes it difficult for watermark removal attacks to evade detection. Furthermore, by embedding watermarks across the entire trigger region and using the text embedding as the watermark, RegionMarker is resilient to both paraphrasing and dimension-perturbation attacks. Extensive experiments on various datasets show that RegionMarker is effective in resisting different attack methods, thereby protecting the copyright of EaaS.

cs.CL↗

arXiv2025

HQ-SVC: Towards High-Quality Zero-Shot Singing Voice Conversion in Low-Resource Scenarios

Zero-shot singing voice conversion (SVC) transforms a source singer's timbre to an unseen target speaker's voice while preserving melodic content without fine-tuning. Existing methods model speaker timbre and vocal content separately, losing essential acoustic information that degrades output quality while requiring significant computational resources. To overcome these limitations, we propose HQ-SVC, an efficient framework for high-quality zero-shot SVC. HQ-SVC first extracts jointly content and speaker features using a decoupled codec. It then enhances fidelity through pitch and volume modeling, preserving critical acoustic information typically lost in separate modeling approaches, and progressively refines outputs via differentiable signal processing and diffusion techniques. Evaluations confirm HQ-SVC significantly outperforms state-of-the-art zero-shot SVC methods in conversion quality and efficiency. Beyond voice conversion, HQ-SVC achieves superior voice naturalness compared to specialized audio super-resolution methods while natively supporting voice super-resolution tasks.

cs.SD↗

arXiv2025

Gradient flow structure, well-posedness and asymptotic behavior of Fokker-Planck equation on locally finite graphs

This paper investigates the gradient flow structure, well-posedness, and asymptotic behavior of the Fokker-Planck equation defined on locally uniformly finite graphs, which is highly non-trivial compared with the finite case. We first construct a 2-Wasserstein-type metric and gradient flow equation in the probability density space associated with the underlying graphs. Then, we prove the global existence of solution to the Fokker-Planck equation using a novel approach that differs significantly from the methods applied in the finite case. We also demonstrate that the solution converges to the Gibbs distribution in the $\ell^{r}(V,\bmπ)$ norm with $r\in [2,\infty]$, by using the indicator set partitioning method. To the best of our knowledge, this work seems the first result on the study of Wasserstein-type metrics and the Fokker-Planck equation in probability density spaces defined on infinite graphs.

math.PR↗