arXiv subjects

Ying Huang

Publications and source records attributed to Ying Huang.

At least 37 records · Page 2Linked to original sources

arXiv2025

MT-Mark: Rethinking Image Watermarking via Mutual-Teacher Collaboration with Adaptive Feature Modulation

Existing deep image watermarking methods follow a fixed embedding-distortion-extraction pipeline, where the embedder and extractor are weakly coupled through a final loss and optimized in isolation. This design lacks explicit collaboration, leaving no structured mechanism for the embedder to incorporate decoding-aware cues or for the extractor to guide embedding during training. To address this architectural limitation, we rethink deep image watermarking by reformulating embedding and extraction as explicitly collaborative components. To realize this reformulation, we introduce a Collaborative Interaction Mechanism (CIM) that establishes direct, bidirectional communication between the embedder and extractor, enabling a mutual-teacher training paradigm and coordinated optimization. Built upon this explicitly collaborative architecture, we further propose an Adaptive Feature Modulation Module (AFMM) to support effective interaction. AFMM enables content-aware feature regulation by decoupling modulation structure and strength, guiding watermark embedding toward stable image features while suppressing host interference during extraction. Under CIM, the AFMMs on both sides form a closed-loop collaboration that aligns embedding behavior with extraction objectives. This architecture-level redesign changes how robustness is learned in watermarking systems. Rather than relying on exhaustive distortion simulation, robustness emerges from coordinated representation learning between embedding and extraction. Experiments on real-world and AI-generated datasets demonstrate that the proposed method consistently outperforms state-of-the-art approaches in watermark extraction accuracy while maintaining high perceptual quality, showing strong robustness and generalization.

cs.CV↗

arXiv2025

HyperVL: An Efficient and Dynamic Multimodal Large Language Model for Edge Devices

Current multimodal large lanauge models possess strong perceptual and reasoning capabilities, however high computational and memory requirements make them difficult to deploy directly on on-device environments. While small-parameter models are progressively endowed with strong general capabilities, standard Vision Transformer (ViT) encoders remain a critical bottleneck, suffering from excessive latency and memory consumption when processing high-resolution inputs.To address these challenges, we introduce HyperVL, an efficient multimodal large language model tailored for on-device inference. HyperVL adopts an image-tiling strategy to cap peak memory usage and incorporates two novel techniques: (1) a Visual Resolution Compressor (VRC) that adaptively predicts optimal encoding resolutions to eliminate redundant computation, and (2) Dual Consistency Learning (DCL), which aligns multi-scale ViT encoders within a unified framework, enabling dynamic switching between visual branches under a shared LLM. Extensive experiments demonstrate that HyperVL achieves state-of-the-art performance among models of comparable size across multiple benchmarks. Furthermore, it significantly significantly reduces latency and power consumption on real mobile devices, demonstrating its practicality for on-device multimodal inference.

cs.CV↗

arXiv2025

From Imitation to Discrimination: Toward A Generalized Curriculum Advantage Mechanism Enhancing Cross-Domain Reasoning Tasks

Reinforcement learning has emerged as a paradigm for post-training large language models, boosting their reasoning capabilities. Such approaches compute an advantage value for each sample, reflecting better or worse performance than expected, thereby yielding both positive and negative signals for training. However, the indiscriminate mixing of the two signals in existing methods, especially from the early stages, may lead to ambiguous guidance and limited gains. To address this issue, we propose **CAPO** (**C**urriculum **A**dvantage **P**olicy **O**ptimization), an adaptive curriculum mechanism based on advantage signals. The proposed mechanism bootstraps imitation learning with positive-only advantage samples to establish robust foundations, and subsequently introduces negative signals to cultivate discriminative capabilities, thereby improving generalization across complex scenarios. Compatible with diverse optimization methods including GRPO, PPO, RLOO, and Reinforce++, our method consistently achieves stable and significant improvements in mathematical reasoning tasks, and further generalizes effectively to multimodal Graphical User Interface (GUI) reasoning scenarios, establishing itself as a versatile and robust optimization framework.

cs.CL↗

arXiv2025

Sequential Testing for Assessing the Incremental Value of Biomarkers Under Biorepository Specimen Constraints with Robustness to Model Misspecification

In cancer biomarker development, a key objective is to evaluate whether a new biomarker, when combined with an established one, improves early cancer detection compared to using the established biomarker alone. Incremental value is often quantified by changes at specific points on the ROC curve, such as an increase in sensitivity at a fixed specificity, which is especially relevant in early cancer detection. Our research is motivated by the Early Detection Research Network (EDRN) biorepository studies, which aim to validate multiple cancer biomarkers across laboratories using specimens obtained from a centralized biorepository, under the constraint of limited specimen availability. To address this challenge, we propose a two-stage group sequential hypothesis testing framework for assessing incremental effects, allowing early stopping for futility or efficacy to conserve valuable samples. Our asymptotic results are derived under a logistic working model and remain valid even under model misspecification, ensuring robustness and broad applicability. We further integrate a rotating group membership design to facilitate validation of multiple candidate biomarkers across laboratories. Through extensive simulations, we demonstrate valid type I error control and efficient utilization of specimens. Finally, we apply our method to data from a multicenter EDRN pancreatic cancer reference set study and show how the proposed approach identifies promising candidate biomarkers that provide incremental performance when combined with CA19-9, while enabling efficient evaluation of a large number of such candidates.

stat.ME↗

arXiv2025

BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent

In the field of AI-driven human-GUI interaction automation, while rapid advances in multimodal large language models and reinforcement fine-tuning techniques have yielded remarkable progress, a fundamental challenge persists: their interaction logic significantly deviates from natural human-GUI communication patterns. To fill this gap, we propose "Blink-Think-Link" (BTL), a brain-inspired framework for human-GUI interaction that mimics the human cognitive process between users and graphical interfaces. The system decomposes interactions into three biologically plausible phases: (1) Blink - rapid detection and attention to relevant screen areas, analogous to saccadic eye movements; (2) Think - higher-level reasoning and decision-making, mirroring cognitive planning; and (3) Link - generation of executable commands for precise motor control, emulating human action selection mechanisms. Additionally, we introduce two key technical innovations for the BTL framework: (1) Blink Data Generation - an automated annotation pipeline specifically optimized for blink data, and (2) BTL Reward -- the first rule-based reward mechanism that enables reinforcement learning driven by both process and outcome. Building upon this framework, we develop a GUI agent model named BTL-UI, which demonstrates competitive performance across both static GUI understanding and dynamic interaction tasks in comprehensive benchmarks. These results provide conclusive empirical validation of the framework's efficacy in developing advanced GUI Agents.

cs.CV↗

arXiv2025

Lego-Edit: A General Image Editing Framework with Model-Level Bricks and MLLM Builder

Instruction-based image editing has garnered significant attention due to its direct interaction with users. However, real-world user instructions are immensely diverse, and existing methods often fail to generalize effectively to instructions outside their training domain, limiting their practical application. To address this, we propose Lego-Edit, which leverages the generalization capability of Multi-modal Large Language Model (MLLM) to organize a suite of model-level editing tools to tackle this challenge. Lego-Edit incorporates two key designs: (1) a model-level toolkit comprising diverse models efficiently trained on limited data and several image manipulation functions, enabling fine-grained composition of editing actions by the MLLM; and (2) a three-stage progressive reinforcement learning approach that uses feedback on unannotated, open-domain instructions to train the MLLM, equipping it with generalized reasoning capabilities for handling real-world instructions. Experiments demonstrate that Lego-Edit achieves state-of-the-art performance on GEdit-Bench and ImgBench. It exhibits robust reasoning capabilities for open-domain instructions and can utilize newly introduced editing tools without additional fine-tuning. Code is available: https://github.com/xiaomi-research/lego-edit.

cs.CV↗

arXiv2025

AdaRing: Towards Ultra-Light Vision-Language Adaptation via Cross-Layer Tensor Ring Decomposition

Adapter-based fine-tuning has gained remarkable attention in adapting large pre-trained vision language models (VLMs) for a wide range of downstream tasks efficiently. In this paradigm, only the inserted adapters are fine-tuned, without the need for training the original VLM backbone. Existing works scale adapters by integrating them into every layer of VLMs to increase the capacity of adapters. However, these methods face two primary limitations: 1) limited compression rate due to ignoring cross-layer redundancy, and 2) limited representational capacity across homogeneous adapters. In this paper, we propose a novel vision-language fine-tuning framework based on cross-layer tensor ring decomposition (TRD) with the integration and collaboration of diverse adapters, called AdaRing, achieving ultra-light parameter-efficient adaptation of VLMs on various tasks. To remove the high redundancy that exists among adapters across layers, we exploit the tensor-level low-rankness to formulate adapters as layer-shared tensor cores and layer-specific slices. Moreover, guided by generalization-aware fine-tuning, diverse rank-driven adapters cooperate to handle tasks that require different representations. Our experiments show that the proposed AdaRing achieves the state-of-the-art performance while reducing average training parameters by 90%.

cs.CV↗

arXiv2025

PASC-Net:Plug-and-play Shape Self-learning Convolutions Network with Hierarchical Topology Constraints for Vessel Segmentation

Accurate vessel segmentation is crucial to assist in clinical diagnosis by medical experts. However, the intricate tree-like tubular structure of blood vessels poses significant challenges for existing segmentation algorithms. Small vascular branches are often overlooked due to their low contrast compared to surrounding tissues, leading to incomplete vessel segmentation. Furthermore, the complex vascular topology prevents the model from accurately capturing and reconstructing vascular structure, resulting in incorrect topology, such as breakpoints at the bifurcation of the vascular tree. To overcome these challenges, we propose a novel vessel segmentation framework called PASC Net. It includes two key modules: a plug-and-play shape self-learning convolutional (SSL) module that optimizes convolution kernel design, and a hierarchical topological constraint (HTC) module that ensures vascular connectivity through topological constraints. Specifically, the SSL module enhances adaptability to vascular structures by optimizing conventional convolutions into learnable strip convolutions, which improves the network's ability to perceive fine-grained features of tubular anatomies. Furthermore, to better preserve the coherence and integrity of vascular topology, the HTC module incorporates hierarchical topological constraints-spanning linear, planar, and volumetric levels-which serve to regularize the network's representation of vascular continuity and structural consistency. We replaced the standard convolutional layers in U-Net, FCN, U-Mamba, and nnUNet with SSL convolutions, leading to consistent performance improvements across all architectures. Furthermore, when integrated into the nnUNet framework, our method outperformed other methods on multiple metrics, achieving state-of-the-art vascular segmentation performance.

eess.IV↗

arXiv2025

Ground state solutions of a class of (2,q)-Laplacian Schrödinger equations with inhomogeneous nonlinearity

In this paper, we systematically investigate the ground state solutions of a class of (2,q)-Laplacian Schrödinger equations with inhomogeneous nonlinearity. By analyzing global and local constrained variational problems, we establish the existence, non-existence, and asymptotic behavior of ground states, addressing the mass-subcritical,mass-critical, and mass-supercritical regimes. As a byproduct, we prove a multiplicity of bound states with prescribed mass. Some of our existence results are sharp. The proofs are based primarily on constrained variational techniques.

math.AP↗

arXiv2025

S3Former: Self-supervised High-resolution Transformer for Solar PV Profiling

As the impact of climate change escalates, the global necessity to transition to sustainable energy sources becomes increasingly evident. Renewable energies have emerged as a viable solution for users, with Photovoltaic energy being a favored choice for small installations due to its reliability and efficiency. Accurate mapping of PV installations is crucial for understanding the extension of its adoption and informing energy policy. To meet this need, we introduce S3Former, designed to segment solar panels from aerial imagery and provide size and location information critical for analyzing the impact of such installations on the grid. Solar panel identification is challenging due to factors such as varying weather conditions, roof characteristics, Ground Sampling Distance variations and lack of appropriate initialization weights for optimized training. To tackle these complexities, S3Former features a Masked Attention Mask Transformer incorporating a self-supervised learning pretrained backbone. Specifically, our model leverages low-level and high-level features extracted from the backbone and incorporates an instance query mechanism incorporated on the Transformer architecture to enhance the localization of solar PV installations. We introduce a self-supervised learning phase (pretext task) to improve the initialization weights on the backbone of S3Former. We evaluated S3Former using diverse datasets, demonstrate improvement state-of-the-art models.

cs.CV↗

arXiv2025

Modeling Coupled Epidemic-Information Dynamics via Reaction-Diffusion Processes on Multiplex Networks with Media and Mobility Effects

While most existing epidemic models focus on the influence of isolated factors, infectious disease transmission is inherently shaped by the complex interplay of multiple interacting elements. To better capture real-world dynamics, it is essential to develop epidemic models that incorporate diverse, realistic factors. In this study, we propose a coupled disease-information spreading model on multiplex networks that simultaneously accounts for three critical dimensions: media influence, higher-order interactions, and population mobility. This integrated framework enables a systematic analysis of synergistic spreading mechanisms under practical constraints and facilitates the exploration of effective epidemic containment strategies. We employ a microscopic Markov chain approach (MMCA) to derive the coupled dynamical equations and identify epidemic thresholds, which are then validated through extensive Monte Carlo (MC) simulations. Our results show that both mass media dissemination and higher-order network structures contribute to suppressing disease transmission by enhancing public awareness. However, the containment effect of higher-order interactions weakens as the order of simplices increases. We also explore the influence of subpopulation characteristics, revealing that increasing inter-subpopulation connectivity in a connected metapopulation network leads to lower disease prevalence. Furthermore, guiding individuals to migrate toward less accessible or more isolated subpopulations is shown to effectively mitigate epidemic spread. These findings offer valuable insights for designing targeted and adaptive intervention strategies in complex epidemic settings.

physics.soc-ph↗

arXiv2025

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction

The advancements in large language models (LLMs) have propelled the improvement of video understanding tasks by incorporating LLMs with visual models. However, most existing LLM-based models (e.g., VideoLLaMA, VideoChat) are constrained to processing short-duration videos. Recent attempts to understand long-term videos by extracting and compressing visual features into a fixed memory size. Nevertheless, those methods leverage only visual modality to merge video tokens and overlook the correlation between visual and textual queries, leading to difficulties in effectively handling complex question-answering tasks. To address the challenges of long videos and complex prompts, we propose AdaCM$^2$, which, for the first time, introduces an adaptive cross-modality memory reduction approach to video-text alignment in an auto-regressive manner on video streams. Our extensive experiments on various video understanding tasks, such as video captioning, video question answering, and video classification, demonstrate that AdaCM$^2$ achieves state-of-the-art performance across multiple datasets while significantly reducing memory usage. Notably, it achieves a 4.5% improvement across multiple tasks in the LVU dataset with a GPU memory consumption reduction of up to 65%.

cs.CV↗

arXiv2025

Practical considerations for variable screening in the super learner

Estimating a prediction function is a fundamental component of many data analyses. The super learner ensemble, a particular implementation of stacking, has desirable theoretical properties and has been used successfully in many applications. Dimension reduction can be accomplished by using variable screening algorithms (screeners), including the lasso, within the ensemble prior to fitting other prediction algorithms. However, the performance of a super learner using the lasso for dimension reduction has not been fully explored in cases where the lasso is known to perform poorly. We provide empirical results that suggest that a diverse set of candidate screeners should be used to protect against poor performance of any one screener, similar to the guidance for choosing a library of prediction algorithms for the super learner. These results are further illustrated through the analysis of HIV-1 antibody data.

stat.ML↗

arXiv2024

Searches for exotic spin-dependent interactions with spin sensors

Numerous theories have postulated the existence of exotic spin-dependent interactions beyond the Standard Model of particle physics. Spin-based quantum sensors, which utilize the quantum properties of spins to enhance measurement precision, emerge as powerful tools for probing these exotic interactions. These sensors encompass a wide range of technologies, such as optically pumped magnetometers, atomic comagnetometers, spin masers, nuclear magnetic resonance, spin amplifiers, and nitrogen-vacancy centers. These technologies stand out for their ultrahigh sensitivity, compact tabletop design, and cost-effectiveness, offering complementary approaches to the large-scale particle colliders and astrophysical observations. This article reviews the underlying physical principles of various spin sensors and highlights the recent theoretical and experimental progress in the searches for exotic spin-dependent interactions with these quantum sensors. Investigations covered include the exotic interactions of spins with ultralight dark matter, exotic spin-dependent forces, electric dipole moment, spin-gravity interactions, and among others. Ongoing and forthcoming experiments using advanced spin-based sensors to investigate exotic spin-dependent interactions are discussed.

quant-ph↗

arXiv2024

Observation of continuous time crystals and quasi-crystals in spin gases

Continuous time crystal (CTC) and quasi-crystal (CTQC) are two novel phases of matter characterized by the spontaneous breaking of continuous time-translation symmetry. To date, realizations of CTCs with periodic oscillations have been reported in only a few physical platforms, and their complex properties still require further exploration. Additionally, CTQCs, which feature quasi-periodic oscillations at multiple incommensurate frequencies, remain elusive. Here we report the experimental observation of CTC and CTQC signatures in noble-gas nuclear spins that interact nonlinearly with each other through feedback mechanisms. The observed limit cycle and quasi-periodic phases display persistent spin oscillations with coherence times extending beyond several hours. Notably, these oscillations are robust against noise perturbations and exhibit random time phases upon repetitive realization, epitomizing the continuous time-translation symmetry-breaking intrinsic to CTCs and CTQCs. As the feedback strength increases, the system undergoes a phase transition into a new phase characterized by chaotic oscillations, indicative of the ``melting" of time crystals. Interestingly, within certain feedback regimes, we even observe an unusual reverse phase transition from a chaotic phase back to time crystal phases. This work broadens the catalog of new phases of spin gas and unlocks opportunities in precision measurements, including multimode masers and tests of fundamental symmetries.

quant-ph↗

arXiv2024

Beyond Point Annotation: A Weakly Supervised Network Guided by Multi-Level Labels Generated from Four-Point Annotation for Thyroid Nodule Segmentation in Ultrasound Image

Weakly-supervised methods typically guided the pixel-wise training by comparing the predictions to single-level labels containing diverse segmentation-related information at once, but struggled to represent delicate feature differences between nodule and background regions and confused incorrect information, resulting in underfitting or overfitting in the segmentation predictions. In this work, we propose a weakly-supervised network that generates multi-level labels from four-point annotation to refine diverse constraints for delicate nodule segmentation. The Distance-Similarity Fusion Prior referring to the points annotations filters out information irrelevant to nodules. The bounding box and pure foreground/background labels, generated from the point annotation, guarantee the rationality of the prediction in the arrangement of target localization and the spatial distribution of target/background regions, respectively. Our proposed network outperforms existing weakly-supervised methods on two public datasets with respect to the accuracy and robustness, improving the applicability of deep-learning based segmentation in the clinical practice of thyroid nodule diagnosis.

eess.IV↗

arXiv2024

The Growth of Passive Membranes: Evidence from Ti and Like Metals

Current contradictory understanding of passivation comes from overly-complex passive models, defective characterization and misplaced theoretical approaches. From brand-new experimentation, we find that a Ti passive membrane has spatiotemporally-ordered macrostructure. At the start, a thermodynamically-stable chemisorbed Ti-O monolayer is immediately formed to inactivate the outmost Ti atoms and shield direct reaction of environmental oxygens on metallic matrix, and then an underneath TiOx@Ti ceramet-like non-equilibrium gradient oxide layer rapidly forms. The two layers work synergistically to keep the macro-ordered passive membrane growing slowly via non-linear mechanism of incremental oxidation damping, thus effecting passivation. These findings disprove "the adsorption theory of passivation" and "the theory of passivity film" and inform a new theory we call "passivation theory of incremental oxidation damping".

cond-mat.mtrl-sci↗

arXiv2023

SolarFormer: Multi-scale Transformer for Solar PV Profiling

As climate change intensifies, the global imperative to shift towards sustainable energy sources becomes more pronounced. Photovoltaic (PV) energy is a favored choice due to its reliability and ease of installation. Accurate mapping of PV installations is crucial for understanding their adoption and informing energy policy. To meet this need, we introduce the SolarFormer, designed to segment solar panels from aerial imagery, offering insights into their location and size. However, solar panel identification in Computer Vision is intricate due to various factors like weather conditions, roof conditions, and Ground Sampling Distance (GSD) variations. To tackle these complexities, we present the SolarFormer, featuring a multi-scale Transformer encoder and a masked-attention Transformer decoder. Our model leverages low-level features and incorporates an instance query mechanism to enhance the localization of solar PV installations. We rigorously evaluated our SolarFormer using diverse datasets, including GGE (France), IGN (France), and USGS (California, USA), across different GSDs. Our extensive experiments consistently demonstrate that our model either matches or surpasses state-of-the-art models, promising enhanced solar panel segmentation for global sustainable energy initiatives.

cs.CV↗