Searcharxiv⌕ Search

arXiv subjects

Yan Wang

Publications and source records attributed to Yan Wang.

At least 235 records · Page 13Linked to original sources
arXiv2026

RAWIC: Bit-Depth Adaptive Lossless Raw Image Compression

Raw images preserve linear sensor measurements and high bit-depth information crucial for advanced vision tasks and photography applications, yet their storage remains challenging due to large file sizes, varying bit depths, and sensor-dependent characteristics. Existing learned lossless compression methods mainly target 8-bit sRGB images, while raw reconstruction approaches are inherently lossy and rely on camera-specific assumptions. To address these challenges, we introduce RAWIC, a bit-depth-adaptive learned lossless compression framework for Bayer-pattern raw images. We first convert single-channel Bayer data into a four-channel RGGB format and partition it into patches. For each patch, we compute its bit depth and use it as auxiliary input to guide compression. A bit-depth-adaptive entropy model is then designed to estimate patch distributions conditioned on their bit depths. This architecture enables a single model to handle raw images from diverse cameras and bit depths. Experiments show that RAWIC consistently surpasses traditional lossless codecs, achieving an average 7.7% bitrate reduction over JPEG-XL. Our code is available at https://github.com/chunbaobao/RAWIC.

cs.CV↗
arXiv2026

Effects of gravity on lean hydrogen/air flame instability: From linear scaling law to nonlinear morphology evolution

The instability characteristics of lean hydrogen/air flames have attracted considerable research attention, yet the effect of gravity remains insufficiently understood. In this study, time-resolved two-dimensional simulations with detailed chemistry and transport are conducted to investigate the influence of gravity-induced Rayleigh-Taylor (RT) instability on the linear growth rate of disturbances and nonlinear morphology evolution of cellular flame fronts at different length scales. In the linear regime, a parametric study is performed across various equivalence ratios, initial temperatures and pressures; in each case, the dispersion relation is calculated for various gravity levels. The influence of gravity is most pronounced under ultra-lean, low-temperature, and high-pressure conditions, and a universal scaling law between gravity sensitivity and the Froude number is established. In the nonlinear regime, gravity has opposite effects on the large-scale and small-scale structures of lean hydrogen flames. On the one hand, gravity inhibits the splitting of small-scale cellular structures through a baroclinic torque mechanism; on the other hand, it promotes the development of large-scale finger-like structures, thereby increasing the total surface area and the global consumption speed of the flame. The effects of gravity on the probability distributions of cell size, displacement speed, Karlovitz number, and local curvature are also analyzed. The results and findings of the present study should advance the fundamental understanding of hydrogen flame dynamics under varying gravity conditions and provide insight for relevant applications, including fire safety and space propulsion.

physics.flu-dyn↗
arXiv2026

Versatile Recompression-Aware Perceptual Image Super-Resolution

Perceptual image super-resolution (SR) methods restore degraded images and produce sharp outputs. In practice, those outputs are usually recompressed for storage and transmission. Ignoring recompression is suboptimal as the downstream codec might add additional artifacts to restored images. However, jointly optimizing SR and recompression is challenging, as the codecs are not differentiable and vary in configuration. In this paper, we present \textbf{Versatile Recompression-Aware Perceptual Super-Resolution (VRPSR)}, which makes existing perceptual SR aware of versatile compression. First, we formulate compression as conditional text-to-image generation and utilize a pre-trained diffusion model to build a generalizable codec simulator. Next, we propose a set of training techniques tailored for perceptual SR, including optimizing the simulator using perceptual targets and adopting slightly compressed images as the training target. Empirically, our VRPSR achieves 10% - 40% bitrate savings based on Real-ESRGAN and S3Diff under H.264/H.265/H.266 single-picture (intra) compression. Besides, our VRPSR facilitates joint optimization of SR and the post-processing model after recompression.

cs.CV↗
arXiv2026

MSRL: Scaling Generative Multimodal Reward Modeling via Multi-Stage Reinforcement Learning

Recent advances in multimodal reward modeling have been largely driven by a paradigm shift from discriminative to generative approaches. Building on this progress, recent studies have further employed reinforcement learning from verifiable rewards (RLVR) to enhance multimodal reward models (MRMs). Despite their success, RLVR-based training typically relies on labeled multimodal preference data, which are costly and labor-intensive to obtain, making it difficult to scale MRM training. To overcome this limitation, we propose a Multi-Stage Reinforcement Learning (MSRL) approach, which can achieve scalable RL for MRMs with limited multimodal data. MSRL replaces the conventional RLVR-based training paradigm by first learning a generalizable reward reasoning capability from large-scale textual preference data, and then progressively transferring this capability to multimodal tasks through caption-based and fully multimodal reinforcement-learning stages. Furthermore, we introduce a cross-modal knowledge distillation approach to improve preference generalization within MSRL. Extensive experiments demonstrate that MSRL effectively scales the RLVR-based training of generative MRMs and substantially improves their performance across both visual understanding and visual generation tasks (e.g., from 66.6% to 75.9% on VL-RewardBench and from 70.2% to 75.7% on GenAI-Bench), without requiring additional multimodal preference annotations. Our code is available at: https://github.com/wangclnlp/MSRL.

cs.CV↗
arXiv2026

Dictionary-based Pathology Mining with Hard-instance-assisted Classifier Debiasing for Genetic Biomarker Prediction from WSIs

Prediction of genetic biomarkers, e.g., microsatellite instability in colorectal cancer is crucial for clinical decision making. But, two primary challenges hamper accurate prediction: (1) It is difficult to construct a pathology-aware representation involving the complex interconnections among pathological components. (2) WSIs contain a large proportion of areas unrelated to genetic biomarkers, which make the model easily overfit simple but irrelative instances. We hereby propose a Dictionary-based hierarchical pathology mining with hard-instance-assisted classifier Debiasing framework to address these challenges, dubbed as D2Bio. Our first module, dictionary-based hierarchical pathology mining, is able to mine diverse and very fine-grained pathological contextual interaction without the limit to the distances between patches. The second module, hard-instance-assisted classfier debiasing, learns a debiased classifier via focusing on hard but task-related features, without any additional annotations. Experimental results on five cohorts show the superiority of our method, with over 4% improvement in AUROC compared with the second best on the TCGA-CRC-MSI cohort. Our analysis further shows the clinical interpretability of D2Bio in genetic biomarker diagnosis and potential clinical utility in survival analysis. Code will be available at https://github.com/DeepMed-Lab-ECNU/D2Bio.

q-bio.QM↗
arXiv2026

A User-Friendly Framework for Generating Model-Preferred Prompts in Text-to-Image Synthesis

Well-designed prompts have demonstrated the potential to guide text-to-image models in generating amazing images. Although existing prompt engineering methods can provide high-level guidance, it is challenging for novice users to achieve the desired results by manually entering prompts due to a discrepancy between novice-user-input prompts and the model-preferred prompts. To bridge the distribution gap between user input behavior and model training datasets, we first construct a novel Coarse-Fine Granularity Prompts dataset (CFP) and propose a novel User-Friendly Fine-Grained Text Generation framework (UF-FGTG) for automated prompt optimization. For CFP, we construct a novel dataset for text-to-image tasks that combines coarse and fine-grained prompts to facilitate the development of automated prompt generation methods. For UF-FGTG, we propose a novel framework that automatically translates user-input prompts into model-preferred prompts. Specifically, we propose a prompt refiner that continually rewrites prompts to empower users to select results that align with their unique needs. Meanwhile, we integrate image-related loss functions from the text-to-image model into the training process of text generation to generate model-preferred prompts. Additionally, we propose an adaptive feature extraction module to ensure diversity in the generated results. Experiments demonstrate that our approach is capable of generating more visually appealing and diverse images than previous state-of-the-art methods, achieving an average improvement of 5% across six quality and aesthetic metrics.

cs.MM↗
arXiv2026

On the structures of {diamond, bowtie}-free graphs that do not contain an induced subdivision of $K_4$

A graph is $\mathrm{ISK}_4$-free if it contains no induced subdivision of $K_4$. Lévêque et al. [\emph{J. Combin. Theory Ser. B} \textbf{102} (2012) 924--947] conjectured that all $\mathrm{ISK}_4$-free graphs are 4-colorable. Chen et al. [\emph{J. Graph Theory} \textbf{96} (2021) 554--577] proved that $\{\mathrm{ISK}_4, \mathrm{diamond}, \mathrm{bowtie}\}$-free graphs are 4-colorable and asked whether such graphs are 3-colorable, where a diamond is $K_4$ minus one edge and a bowtie consists of two triangles sharing a vertex. In this paper, we characterize the structures of $\{\mathrm{ISK}_4, \mathrm{diamond}, \mathrm{bowtie}\}$-free graphs and prove that such graphs are 3-colorable, which answers a question of Chen et al. [\emph{J. Graph Theory} \textbf{96} (2021) 554--577] affirmatively and extends a result of Chudnovsky et al. [\emph{J. Graph Theory} \textbf{92} (2019) 67--95]. Furthermore, our structural theorem yields a polynomial-time algorithm for decomposing $\{\mathrm{ISK}_4, \mathrm{diamond}, \mathrm{bowtie}\}$-free graphs, and consequently a polynomial-time algorithm for coloring this class of graphs.

math.CO↗
arXiv2026

Diffusion-Guided Semantic Consistency for Multimodal Heterogeneity

Federated learning (FL) is severely challenged by non-independent and identically distributed (non-IID) client data, a problem that degrades global model performance, especially in multimodal perception settings. Conventional methods often fail to address the underlying semantic discrepancies between clients, leading to suboptimal performance for multimedia systems requiring robust perception. To overcome this, we introduce SemanticFL, a novel framework that leverages the rich semantic representations of pre-trained diffusion models to provide privacy-preserving guidance for local training. Our approach leverages multi-layer semantic representations from a pre-trained Stable Diffusion model (including VAE-encoded latents and U-Net hierarchical features) to create a shared latent space that aligns heterogeneous clients, facilitated by an efficient client-server architecture that offloads heavy computation to the server. A unified consistency mechanism, employing cross-modal contrastive learning, further stabilizes convergence. We conduct extensive experiments on benchmarks including CIFAR-10, CIFAR-100, and TinyImageNet under diverse heterogeneity scenarios. Our results demonstrate that SemanticFL surpasses existing federated learning approaches, achieving accuracy gains of up to 5.49% over FedAvg, validating its effectiveness in learning robust representations for heterogeneous and multimodal data for perception tasks.

cs.CV↗
arXiv2026

On the $(k+2,k)$-problem of Brown, Erdős and Sós for even integers $k$

Let $f^{(r)}(n;s,k)$ denote the maximum number of edges in an $r$-graph on $n$ vertices in which every $k$ edges span more than $s$ vertices. Brown, Erdős and Sós in 1973 conjectured that for every $k\geq 2$, the limit $\lim_{n\to\infty} n^{-2} f^{(3)}(n;k+2,k)$ exists and verified the conjecture for $k=2$ by showing that $\lim_{n\to\infty} n^{-2} f^{(3)}(n;4,2)=\frac{1}{6}$. Delcourt and Postle, building on the work of Glock, Joos, Kim, Kühn, Lichev and Pikhurko, proved that for every $k\geq 2$, the limit $\lim_{n\to\infty} n^{-2} f^{(3)}(n;k+2,k)$ exists, thereby solving this conjecture. Their approach was later generalised by Shangguan to every uniformity $r\geq 4$: the limit $\lim_{n\to\infty} n^{-2} f^{(r)}(n; rk-2k+2,k)$ exists for all $r\geq 3$ and $k\geq 2$. However, its exact value was not determined. When $k\in\{2,3,\ldots,7\}$, the exact values of $\lim_{n\to\infty} n^{-2} f^{(r)}(n; rk-2k+2,k)$ were determined by Glock, Joos, Kim, Kühn, Lichev, Pikhurko, Rödl and Sun. Very recently, the limit for $k=8$ and $r\geq 4$ was determined by Pikhurko and Sun. For a general even integer $k$, Letzter and Sgueglia obtained the exact values of $\lim_{n\to\infty} n^{-2} f^{(r)}(n;rk-2k+2,k)$ for every even integer $k$ and uniformity $r\geq 2+\sqrt{2}\,k^{3/2}$. In this paper, we determine the exact value of $\lim_{n\to\infty} n^{-2} f^{(r)}(n;rk-2k+2,k)$ for every even integer $k\geq 4$ and $r\geq 2+\sqrt{\frac{3}{2}k-4}$, and show that it is $\frac{1}{r^2-r}.$

math.CO↗
arXiv2026

Edge-Cloud Collaborative Computing on Distributed Intelligence and Model Optimization: A Survey

Edge-cloud collaborative computing (ECCC) has emerged as a pivotal paradigm for addressing the computational demands of modern intelligent applications, integrating cloud resources with edge devices to enable efficient, low-latency processing. Recent advancements in AI, particularly deep learning and large language models (LLMs), have dramatically enhanced the capabilities of these distributed systems, yet introduce significant challenges in model deployment and resource management. In this survey, we comprehensive examine the intersection of distributed intelligence and model optimization within edge-cloud environments, providing a structured tutorial on fundamental architectures, enabling technologies, and emerging applications. Additionally, we systematically analyze model optimization approaches, including compression, adaptation, and neural architecture search, alongside AI-driven resource management strategies that balance performance, energy efficiency, and latency requirements. We further explore critical aspects of privacy protection and security enhancement within ECCC systems and examines practical deployments through diverse applications, spanning autonomous driving, healthcare, and industrial automation. Performance analysis and benchmarking techniques are also thoroughly explored to establish evaluation standards for these complex systems. Furthermore, the review identifies critical research directions including LLMs deployment, 6G integration, neuromorphic computing, and quantum computing, offering a roadmap for addressing persistent challenges in heterogeneity management, real-time processing, and scalability. By bridging theoretical advancements and practical deployments, this survey offers researchers and practitioners a holistic perspective on leveraging AI to optimize distributed computing environments, fostering innovation in next-generation intelligent systems.

cs.DC↗
arXiv2026

MeMix: Writing Less, Remembering More for Streaming 3D Reconstruction

Reconstruction is a fundamental task in 3D vision and a fundamental capability for spatial intelligence. Particularly, streaming 3D reconstruction is central to real-time spatial perception, yet existing recurrent online models often suffer from progressive degradation on long sequences due to state drift and forgetting, motivating inference-time remedies. We present MeMix, a training-free, plug-and-play module that improves streaming reconstruction by recasting the recurrent state into a Memory Mixture. MeMix partitions the state into multiple independent memory patches and updates only the least-aligned memory patches while exactly preserving others. This selective update mitigates catastrophic forgetting while retaining $O(1)$ inference memory, and requires no fine-tuning or additional learnable parameters, making it directly applicable to existing recurrent reconstruction models. Across standard benchmarks (ScanNet, 7-Scenes, KITTI, etc.), under identical backbones and inference settings, MeMix reduces reconstruction completeness error by 15.3% on average (up to 40.0%) across 300--500 frame streams on 7-Scenes. The code is available at https://dongjiacheng06.github.io/MeMix/

cs.CV↗
arXiv2026

OARS: Process-Aware Online Alignment for Generative Real-World Image Super-Resolution

Aligning generative real-world image super-resolution models with human visual preference is challenging due to the perception--fidelity trade-off and diverse, unknown degradations. Prior approaches rely on offline preference optimization and static metric aggregation, which are often non-interpretable and prone to pseudo-diversity under strong conditioning. We propose OARS, a process-aware online alignment framework built on COMPASS, a MLLM-based reward that evaluates the LR to SR transition by jointly modeling fidelity preservation and perceptual gain with an input-quality-adaptive trade-off. To train COMPASS, we curate COMPASS-20K spanning synthetic and real degradations, and introduce a three-stage perceptual annotation pipeline that yields calibrated, fine-grained training labels. Guided by COMPASS, OARS performs progressive online alignment from cold-start flow matching to full-reference and finally reference-free RL via shallow LoRA optimization for on-policy exploration. Extensive experiments and user studies demonstrate consistent perceptual improvements while maintaining fidelity, achieving state-of-the-art performance on Real-ISR benchmarks.

cs.CV↗
arXiv2026

Analyzing coherent phonon mode-conversion in gradient superlattices with atomistic wave-packet simulations

In this study, we have used atomistic phonon wave-packet simulations to investigate the manifestation of coherent phonons and phonon transmission in gradient superlattices (SL) based on ordered arrangements of varied SL period sizes. We specifically explore how coherent mode-conversion in these quasi-periodic structures changes as function of three key structural parameters: (1) the number of distinct period sizes, (2) the number of periods present for each distinct period size, and (3) the arrangement of period sizes in either an ascending or descending arrangement. Comparisons to periodic SLs and aperiodic SLs are highlighted, revealing that coherent phonons in gradient SLs generally exhibit behaviors characteristic of intermediate states between the fully ordered and disordered structures. Interestingly, changes to the short-range order of GMLs does not significantly influence transmission, indicating that long-range disorder is far more important to coherent mode-conversion. Our results indicate that manipulating the long-range disorder of interfaces could be an effective strategy to tailor phonon thermal conductivity of SL architectures.

cond-mat.mtrl-sci↗
arXiv2026

PD-Diag-Net: Clinical-Priors guided Network on Brain MRI for Auxiliary Diagnosis of Parkinson's Disease

Parkinson's disease (PD) is a common neurodegenerative disorder that severely diminishes patients' quality of life. Its global prevalence has increased markedly in recent decades. Current diagnostic workflows are complex and heavily reliant on neurologists' expertise, often resulting in delays in early detection and missed opportunities for timely intervention. To address these issues, we propose an end-to-end automated diagnostic method for PD, termed PD-Diag-Net, which performs risk assessment and auxiliary diagnosis directly from raw MRI scans. This framework first introduces an MRI Pre-processing Module (MRI-Processor) to mitigate inter-subject and inter-scanner variability by flexibly integrating established medical imaging preprocessing tools. It then incorporates two forms of clinical prior knowledge: (1) Brain-Region-Relevance-Prior (Relevance-Prior), which specifies brain regions strongly associated with PD; and (2) Brain-Region-Aging-Prior (Aging-Prior), which reflects the accelerated aging typically observed in PD-associated regions. Building on these priors, we design two dedicated modules: the Relevance-Prior Guided Feature Aggregation Module (Aggregator), which guides the model to focus on PD-associated regions at the inter-subject level, and the Age-Prior Guided Diagnosis Module (Diagnoser), which leverages brain age gaps as auxiliary constraints at the intra-subject level to enhance diagnostic accuracy and clinical interpretability. Furthermore, we collected external test data from our collaborating hospital. Experimental results show that PD-Diag-Net achieves 86\% accuracy on external tests and over 96% accuracy in early-stage diagnosis, outperforming existing advanced methods by more than 20%.

cs.CV↗
arXiv2026

DOPD: A Dynamic PD-Disaggregation Architecture for Maximizing Goodput in LLM Inference Serving

To meet strict Service-Level Objectives (SLOs),contemporary Large Language Models (LLMs) decouple the prefill and decoding stages and place them on separate GPUs to mitigate the distinct bottlenecks inherent to each phase. However, the heterogeneity of LLM workloads causes producerconsumer imbalance between the two instance types in such disaggregated architecture. To address this problem, we propose DOPD (Dynamic Optimal Prefill/Decoding), a dynamic LLM inference system that adjusts instance allocations to achieve an optimal prefill-to-decoding (P/D) ratio based on real-time load monitoring. Combined with an appropriate request-scheduling policy, DOPD effectively resolves imbalances between prefill and decoding instances and mitigates resource allocation mismatches due to mixed-length requests under high concurrency. Experimental evaluations show that, compared with vLLM and DistServe (representative aggregation-based and disaggregationbased approaches), DOPD improves overall system goodput by up to 1.5X, decreases P90 time-to-first-token (TTFT) by up to 67.5%, and decreases P90 time-per-output-token (TPOT) by up to 22.8%. Furthermore, our dynamic P/D adjustment technique performs proactive reconfiguration based on historical load, achieving over 99% SLOs attainment while using less additional resources.

cs.DC↗
arXiv2026

SAMoE-VLA: A Scene Adaptive Mixture-of-Experts Vision-Language-Action Model for Autonomous Driving

Recent advances in Vision-Language-Action (VLA) models have shown promising capabilities in autonomous driving by leveraging the understanding and reasoning strengths of Large Language Models(LLMs).However, our empirical analysis reveals that directly applying existing token-level MoE mechanisms--which are inherited from LLM architectures--to VLA models results in unstable performance and safety degradation in autonomous driving, highlighting a misalignment between token-based expert specialization and scene-level decision-making.To address this, we propose SAMoE-VLA, a scene-adaptive Vision-Language-Action framework that conditions expert selection on structured scene representations instead of token embeddings. Our key idea is to derive the MoE routing signal from bird's-eye-view (BEV) features that encapsulates traffic scene context, enabling scenario-dependent expert weighting and merging tailored to distinct driving conditions. Furthermore, to support temporally consistent reasoning across world-knowledge, perception, language, and action, we introduce a Conditional Cross-Modal Causal Attention mechanism that integrates world state, linguistic intent, and action history into a unified causal reasoning process. Extensive experiments on the nuScenes open loop planning dataset and LangAuto closed-loop benchmark demonstrate that SAMoE-VLA achieves state-of-the-art performance, outperforming prior VLA-based and world-model-based approaches with fewer parameters.Our code will be released soon.

cs.CV↗
arXiv2026

Devil is in Narrow Policy: Unleashing Exploration in Driving VLA Models

We identify a fundamental Narrow Policy limitation undermining the performance of autonomous VLA models, where driving Imitation Learning (IL) tends to collapse exploration and limit the potential of subsequent Reinforcement Learning (RL) stages, which often saturate prematurely due to insufficient feedback diversity. Thereby, we propose Curious-VLA, a framework that alleviates the exploit-explore dilemma through a two-stage design. During IL, we introduce a Feasible Trajectory Expansion (FTE) strategy to generate multiple physically valid trajectories and a step-wise normalized trajectory representation to adapt this diverse data. In the RL stage, we present Adaptive Diversity-Aware Sampling (ADAS) that prioritizes high-diversity samples and introduce Spanning Driving Reward (SDR) with a focal style weighting to amplify reward's value span for improving sensitivity to driving quality. On the Navsim benchmark, Curious-VLA achieves SoTA results (PDMS 90.3, EPDMS 85.4) and a Best-of-N PDMS of 94.8, demonstrating its effectiveness in unlocking the exploratory potential of VLA models. Code: https://github.com/Mashiroln/curious_vla.git.

cs.CV↗
arXiv2026

Probing Boron Vacancy Defects in hBN via Single Spin Relaxometry

Spin defects in solids offer promising platforms for quantum sensing and memory due to their long coherence times and optical addressability. Here, we integrate a single nitrogen-vacancy (NV) center in diamond with scanning probe microscopy to discover, read out, and spatially map arbitrary spin-based quantum sensors at the nanoscale. Using the boron vacancy ($\mathrm{V}_\mathrm{B}^-$) center in hexagonal boron nitride$\unicode{x2013}$an emerging two-dimensional spin system$\unicode{x2013}$as a model, we detect its electron spin resonance indirectly via changes in the spin relaxation time ($T_1$) of a nearby NV center, eliminating the need for optical excitation or fluorescence detection of the $\mathrm{V}_\mathrm{B}^-$. Cross-relaxation between NV and $\mathrm{V}_\mathrm{B}^-$ ensembles significantly reduces NV $T_1$, enabling quantitative nanoscale mapping of defect densities beyond the optical diffraction limit and clear resolution of hyperfine splitting in isotopically enriched h$^{10}$B$^{15}$N. Our method demonstrates interactions between 3D and 2D spin sensors, establishing NV centers as versatile probes for characterizing otherwise inaccessible spin defects.

cond-mat.mtrl-sci↗