arXiv subjects

Jin Yang

Publications and source records attributed to Jin Yang.

At least 55 records · Page 3Linked to original sources

arXiv2026

WaveComm: Lightweight Communication for Collaborative Perception via Wavelet Feature Distillation

In multi-agent collaborative sensing systems, substantial communication overhead from information exchange significantly limits scalability and real-time performance, especially in bandwidth-constrained environments. This often results in degraded performance and reduced reliability. To address this challenge, we propose WaveComm, a wavelet-based communication framework that drastically reduces transmission loads while preserving sensing performance in low-bandwidth scenarios. The core innovation of WaveComm lies in decomposing feature maps using Discrete Wavelet Transform (DWT), transmitting only compact low-frequency components to minimize communication overhead. High-frequency details are omitted, and their effects are reconstructed at the receiver side using a lightweight generator. A Multi-Scale Distillation (MSD) Loss is employed to optimize the reconstruction quality across pixel, structural, semantic, and distributional levels. Experiments on the OPV2V and DAIR-V2X datasets for LiDAR-based and camera-based perception tasks demonstrate that WaveComm maintains state-of-the-art performance even when the communication volume is reduced to 86.3% and 87.0% of the original, respectively. Compared to existing approaches, WaveComm achieves competitive improvements in both communication efficiency and perception accuracy. Ablation studies further validate the effectiveness of its key components.

cs.CV↗

arXiv2026

Spin-polarized scanning tunneling microscopy measurement scheme for determining the quantum geometric tensor

The quantum geometric tensor (QGT) embodies the geometry of the eigenstates of a system's Hamiltonian, and its full characterization across diverse quantum systems is essential. However, it is challenging to characterize the QGT of solid-state systems. Here we present an electric scheme to measure the complete QGT of two-dimensional solid-state systems by using spin-polarized scanning tunneling microscopy (STM), in which the spin texture is extracted from geometric amplitudes of Friedel oscillations induced by the intentionally introduced magnetic impurity, and then the QGT is derived from the momentum differential of spin texture. As a canonical spin model, the surface states of a topological insulator offer a promising way to demonstrate the scheme. In a slab of topological insulator, the gapped surface states host complete QGT, i.e., nonvanishing quantum metric and Berry curvature as its symmetric real part and the antisymmetric imaginary part. Thus, a detailed derivation guides the use of the developed scheme to measure the QGT of gapped surface states, even with an external magnetic field. This study opens a new avenue to directly measure the complete QGT of two-dimensional solid-state systems by using spin-polarized STM.

cond-mat.mes-hall↗

arXiv2026

A building block of quantum repeaters for scalable quantum networks

Quantum networks, integrating quantum communication, quantum metrology, and distributed quantum computing, could provide secure and efficient information transfer, high-resolution sensing, and an exponential speed-up in information processing. Deterministic entanglement distribution over long distances is a prerequisite for scalable quantum networks, enabling the utilization of device-independent quantum key distribution (DI-QKD) and quantum teleportation to achieve secure and efficient information transfer. However, the exponential photon loss in optical fibres prohibits efficient and deterministic entanglement distribution. Quantum repeaters, incorporating entanglement swapping and entanglement purification with quantum memories, offer the most promising means to overcome this limitation in fibre-based quantum networks. Despite numerous pioneering efforts toward realizing quantum repeaters, a critical bottleneck remains, as remote memory-memory entanglement suffers from decoherence more rapidly than it can be established and purified over long distances. We overcome this by developing long-lived trapped-ion memories, an efficient telecom interface, and a high-visibility single-photon entanglement protocol. This allows us to establish and maintain memory-memory entanglement over a 10 km fibre within the average entanglement establishment time for the same distance. As a direct application, we demonstrate metropolitan-scale DI-QKD, distilling 1,917 secret keys out of 4.05*10^5 Bell pairs over 10 km. We further report a positive key rate over 101 km in the asymptotic limit, extending the achievable distance by more than two orders of magnitude. Our work provides a critical building block for quantum repeaters and marks an important step toward scalable quantum networks.

quant-ph↗

arXiv2026

U-Harmony: Enhancing Joint Training for Segmentation Models with Universal Harmonization

In clinical practice, medical segmentation datasets are often limited and heterogeneous, with variations in modalities, protocols, and anatomical targets across institutions. Existing deep learning models struggle to jointly learn from such diverse data, often sacrificing either generalization or domain-specific knowledge. To overcome these challenges, we propose a joint training method called Universal Harmonization (U-Harmony), which can be integrated into deep learning-based architectures with a domain-gated head, enabling a single segmentation model to learn from heterogeneous datasets simultaneously. By integrating U-Harmony, our approach sequentially normalizes and then denormalizes feature distributions to mitigate domain-specific variations while preserving original dataset-specific knowledge. More appealingly, our framework also supports universal modality adaptation, allowing the seamless learning of new imaging modalities and anatomical classes. Extensive experiments on cross-institutional brain lesion datasets demonstrate the effectiveness of our approach, establishing a new benchmark for robust and adaptable 3D medical image segmentation models in real-world clinical settings.

cs.CV↗

arXiv2026

Microbubble surface instabilities in a strain stiffening viscoelastic material

Understanding the dynamics of instabilities along fluid-solid interfaces is critical for the efficacy of focused ultrasound therapy tools (e.g., histotripsy) and microcavitation rheometry techniques. Non-uniform pressure fields generated by either ultrasound or a focused laser can cause non-spherical microcavitation bubbles. Previous perturbation amplitude evolution models in viscoelastic materials either assume pure radial deformation or have inconsistent kinematic fields between the fluid and solid contributions. We derive a kinematically-consistent theoretical model for the evolution of surface perturbations. The model captures the non-linear kinematics of a strain-stiffening viscoelastic material surrounding a non-spherical bubble. The model is validated for (i) small, approximately linear radial oscillations and (ii) large inertial oscillations using laser-induced microcavitation experiments in a soft hydrogel. For the former, the bubble is allowed to reach mechanical equilibrium, and then surface perturbations are excited using ultrasound forcing. For the latter, the microbubble forms small bubble surface perturbations at its maximum radius that grow during collapse. The model's dominant surface perturbation mode scales linearly with equilibrium radius and matches experiments. Similarly, the model's perturbation amplitude evolution sufficiently constrains the rheometry problem and is experimentally validated.

physics.flu-dyn↗

arXiv2025

TransLK-Net: Entangling Transformer and Large Kernel for Progressive and Collaborative Feature Encoding and Decoding in Medical Image Segmentation

Convolutional neural networks (CNNs) and vision transformers (ViTs) are widely employed for medical image segmentation, but they are still challenged by their intrinsic characteristics. CNNs are limited from capturing varying-scaled features and global contextual information due to the employment of fixed-sized kernels. In contrast, ViTs employ self-attention and MLP for global information modeling, but they lack mechanisms to learn spatial-wise local information. Additionally, self-attention leads the network to show high computational complexity. To tackle these limitations, we propose Progressively Entangled Transformer Large Kernel (PTLK) and Collaboratively Entangled Transformer Large Kernel (CTLK) modules to leverage the benefits of self-attention and large kernel convolutions and overcome shortcomings. Specifically, PTLK and CTLK modules employ the Multi-head Large Kernel to capture multi-scale local features and the Efficient Decomposed Self-attention to model global information efficiently. Subsequently, they employ the Attention Entanglement mechanism to enable local and global features to enhance and calibrate each other progressively and collaboratively. Additionally, an Attention-gated Channel MLP (AG-MLP) module is proposed to equip the standard MLP module with the capabilities of modeling spatial information. PTLK and CTLK modules are further incorporated as a Cross Entanglement Decoding (CED) block for efficient feature fusion and decoding. Finally, we propose a novel network for volumetric medical image segmentation that employs an encoder-decoder architecture, termed TransLK-Net. The encoder employs a hierarchical ViT architecture whose block is built by incorporating PTLK and CTLK with AG-MLP into a ViT block, and the decoder employs the CED block.

eess.IV↗

arXiv2025

Hierarchical Bayesian constitutive model selection for high-strain-rate soft material characterization

The high-fidelity characterization of soft, tissue-like materials under ultra-high-strain-rate conditions is critical in engineering and medicine. Still, it remains challenging due to limited optical access, sensitivity to initial conditions, and experimental variability. Microcavitation techniques (e.g., laser-induced microcavitation) have emerged as a viable method for determining the mechanical properties of soft materials in the ultra-high-strain-rate regime (higher than 10^3 s^{-1}); however, they are limited by measurement noise and uncertainty in parameter estimation. A hierarchical Bayesian model selection method is employed using the Inertial Microcavitation Rheometry (IMR) technique to address these limitations. With this method, the parameter space of different constitutive models is explored to determine the most credible constitutive model that describes laser-induced microcavitation bubble oscillations in soft, viscoelastic, transparent hydrogels. The target data/evidence is computed using a weighted Gaussian likelihood with a hierarchical noise scale, which enables the quantification of uncertainty in model plausibility. Physically informed priors, including range-invariant, stress-based parameter priors, a model-redundancy prior, and a Bayesian Information Criterion motivated model prior, penalize complex models to enforce Occam's razor. Using a precomputed grid of simulations, the probabilistic model selection process enables an initial guess for the Maximum A Posteriori (MAP) material parameter values. Synthetic tests recover the ground-truth models and expected parameters. Using experimental data for gelatin, fibrin, polyacrylamide, and agarose, MAP simulations of credible models reproduce the data. Moreover, a cross-institutional comparison of 10% gelatin indicates consistent constitutive model selection.

physics.flu-dyn↗

arXiv2025

Long-term behavior of nonlocal reaction-diffusion equation under small random perturbations

In this paper, we investigate the nonlocal reaction-diffusion equation driven by stationary noise, which is a regular approximation to white noise and satisfies certain properties. We show the existence of random attractor for the equation. When stochastic nonlocal reaction-diffusion equation is driven by additive and multiplicative noise, we prove that the solution converges to the corresponding deterministic equation and establish the upper semicontinuity of the attractors as the perturbation parameter δand εboth approaches zero.

math.DS↗

arXiv2025

Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model

We present Ring-1T, the first open-source, state-of-the-art thinking model with a trillion-scale parameter. It features 1 trillion total parameters and activates approximately 50 billion per token. Training such models at a trillion-parameter scale introduces unprecedented challenges, including train-inference misalignment, inefficiencies in rollout processing, and bottlenecks in the RL system. To address these, we pioneer three interconnected innovations: (1) IcePop stabilizes RL training via token-level discrepancy masking and clipping, resolving instability from training-inference mismatches; (2) C3PO++ improves resource utilization for long rollouts under a token budget by dynamically partitioning them, thereby obtaining high time efficiency; and (3) ASystem, a high-performance RL framework designed to overcome the systemic bottlenecks that impede trillion-parameter model training. Ring-1T delivers breakthrough results across critical benchmarks: 93.4 on AIME-2025, 86.72 on HMMT-2025, 2088 on CodeForces, and 55.94 on ARC-AGI-1. Notably, it attains a silver medal-level result on the IMO-2025, underscoring its exceptional reasoning capabilities. By releasing the complete 1T parameter MoE model to the community, we provide the research community with direct access to cutting-edge reasoning capabilities. This contribution marks a significant milestone in democratizing large-scale reasoning intelligence and establishes a new baseline for open-source model performance.

cs.CL↗

arXiv2025

Unraveling longitudinal field mediated versatile Stokes polarimetry

Stokes polarimetry has been considered as an alluring platform that enables a plethora of applications ranging from single-molecule orientation to deep-space sensing. Existing polarimetry avenues, however, rely primarily on the transversely polarized field reconstruction, thus suffering from several challenges such as multiple time sequenced detections, complex demodulation algorithms, and intricate engineering procedures. To circumvent these challenges, here we first demonstrate a longitudinally polarized field mediated recipe for the realization of efficacious and refined Stokes polarimetry in situ. This is achieved by unraveling the spin-to-orbit momentum conversion under non-paraxial focusing conditions enabling the direct mapping of the polarization ellipse. Leveraging this mechanism, we reveal an analytical solution of polarization ellipse via the local sampling of longitudinal field, in which the robustness can be fairly reinforced by relevant global retrieval based on convolutional neural network. The resultant Stokes polarimetry is shown to simultaneously exhibit in-situ signal acquisition (direct discernment), unparalleled demodulation time (up tomicrosecond level), superior detection efficiency (no need of troublesome design), and ultra-high retrieved accuracy (less than 1%), which is fundamentally inaccessible with traditional polarimetry methods. Our work holds great promise for empowering an allin-one versatile vector polarimeter, which opens up a host of applications relevant to polarization control.

physics.optics↗

arXiv2025

Intelligent Prediction and Optimization of Open-Hole Wellbore Multiphysics Stability: A Synergistic PINN-DRL Approach

To address the dual challenge of predicting multiphysics-induced instability and optimizing drilling fluid parameters for open-hole wellbores under long-term exposure, a high-fidelity system of coupled governing equations was developed. This system integrates seepage, hydration-induced softening, thermal diffusion, and elasto-plastic response to capture the nonlinear dynamics of wellbore stability evolution. A two-dimensional numerical model in a polar coordinate system was established using COMSOL Multiphysics to simulate multi-lithology and multi-parameter perturbations. This process generated a high-dimensional dataset characterizing the evolution of Von Mises stress, plastic strain, pore pressure, temperature, and water content, and its physical consistency was examined. Subsequently, the Seepage-Thermal-Water-Mechanical Physics-Informed Neural Network (STWM-PINN) is proposed. This model embeds governing equation residuals and initial-boundary constraints to achieve high-precision, physically consistent predictions of the wellbore's spatio-temporal evolution under the supervision of finite observational data, laying a foundation for parameter control. Building on this, a Double-Noise Soft Actor-Critic (DN-SAC) algorithm is integrated. A reward function was designed to minimize the probability of instability while considering control smoothness and physical boundary constraints, enabling continuous-space optimization of drilling fluid parameters. A case study demonstrates that the proposed method delays the onset of instability by an average of 32.33% and a maximum of 53.35%, significantly reducing instability risk. This study provides a decision-support framework with engineering application potential for intelligent wellbore instability prediction and drilling fluid control.

physics.geo-ph↗

arXiv2025

On MCMC mixing for predictive inference under unidentified transformation models

Reliable Bayesian predictive inference has long been an open problem under unidentified transformation models, since the Markov Chain Monte Carlo (MCMC) chains of posterior predictive distribution (PPD) values are generally poorly mixed. We address the poorly mixed PPD value chains under unidentified transformation models through an adaptive scheme for prior adjustment. Specifically, we originate a conception of sufficient informativeness, which explicitly quantifies the information level provided by nonparametric priors, and assesses MCMC mixing by comparison with the within-chain MCMC variance. We formulate the prior information level by a set of hyperparameters induced from the nonparametric prior elicitation with an analytic expression, which is guaranteed by asymptotic theory for the posterior variance under unidentified transformation models. The analytic prior information level consequently drives a hyperparameter tuning procedure to achieve MCMC mixing. The proposed method is general enough to cover various data domains through a multiplicative error working model. Comprehensive simulations and real-world data analysis demonstrate that our method successfully achieves MCMC mixing and outperforms state-of-the-art competitors in predictive capability.

stat.ME↗

arXiv2025

Step-Audio 2 Technical Report

This paper presents Step-Audio 2, an end-to-end multi-modal large language model designed for industry-strength audio understanding and speech conversation. By integrating a latent audio encoder and reasoning-centric reinforcement learning (RL), Step-Audio 2 achieves promising performance in automatic speech recognition (ASR) and audio understanding. To facilitate genuine end-to-end speech conversation, Step-Audio 2 incorporates the generation of discrete audio tokens into language modeling, significantly enhancing its responsiveness to paralinguistic information such as speaking styles and emotions. To effectively leverage the rich textual and acoustic knowledge in real-world data, Step-Audio 2 integrates retrieval-augmented generation (RAG) and is able to call external tools such as web search to mitigate hallucination and audio search to switch timbres. Trained on millions of hours of speech and audio data, Step-Audio 2 delivers intelligence and expressiveness across diverse conversational scenarios. Evaluation results demonstrate that Step-Audio 2 achieves state-of-the-art performance on various audio understanding and conversational benchmarks compared to other open-source and commercial solutions. Please visit https://github.com/stepfun-ai/Step-Audio2 for more information.

cs.CL↗

arXiv2025

MixGAN: A Hybrid Semi-Supervised and Generative Approach for DDoS Detection in Cloud-Integrated IoT Networks

The proliferation of cloud-integrated IoT systems has intensified exposure to Distributed Denial of Service (DDoS) attacks due to the expanded attack surface, heterogeneous device behaviors, and limited edge protection. However, DDoS detection in this context remains challenging because of complex traffic dynamics, severe class imbalance, and scarce labeled data. While recent methods have explored solutions to address class imbalance, many still struggle to generalize under limited supervision and dynamic traffic conditions. To overcome these challenges, we propose MixGAN, a hybrid detection method that integrates conditional generation, semi-supervised learning, and robust feature extraction. Specifically, to handle complex temporal traffic patterns, we design a 1-D WideResNet backbone composed of temporal convolutional layers with residual connections, which effectively capture local burst patterns in traffic sequences. To alleviate class imbalance and label scarcity, we use a pretrained CTGAN to generate synthetic minority-class (DDoS attack) samples that complement unlabeled data. Furthermore, to mitigate the effect of noisy pseudo-labels, we introduce a MixUp-Average-Sharpen (MAS) strategy that constructs smoothed and sharpened targets by averaging predictions over augmented views and reweighting them towards high-confidence classes. Experiments on NSL-KDD, BoT-IoT, and CICIoT2023 demonstrate that MixGAN achieves up to 2.5% higher accuracy and 4% improvement in both TPR and TNR compared to state-of-the-art methods, confirming its robustness in large-scale IoT-cloud environments. The source code is publicly available at https://github.com/0xCavaliers/MixGAN.

cs.CR↗

arXiv2025

Quality-of-Service Aware LLM Routing for Edge Computing with Multiple Experts

Large Language Models (LLMs) have demonstrated remarkable capabilities, leading to a significant increase in user demand for LLM services. However, cloud-based LLM services often suffer from high latency, unstable responsiveness, and privacy concerns. Therefore, multiple LLMs are usually deployed at the network edge to boost real-time responsiveness and protect data privacy, particularly for many emerging smart mobile and IoT applications. Given the varying response quality and latency of LLM services, a critical issue is how to route user requests from mobile and IoT devices to an appropriate LLM service (i.e., edge LLM expert) to ensure acceptable quality-of-service (QoS). Existing routing algorithms fail to simultaneously address the heterogeneity of LLM services, the interference among requests, and the dynamic workloads necessary for maintaining long-term stable QoS. To meet these challenges, in this paper we propose a novel deep reinforcement learning (DRL)-based QoS-aware LLM routing framework for sustained high-quality LLM services. Due to the dynamic nature of the global state, we propose a dynamic state abstraction technique to compactly represent global state features with a heterogeneous graph attention network (HAN). Additionally, we introduce an action impact estimator and a tailored reward function to guide the DRL agent in maximizing QoS and preventing latency violations. Extensive experiments on both Poisson and real-world workloads demonstrate that our proposed algorithm significantly improves average QoS and computing resource efficiency compared to existing baselines.

cs.NI↗

arXiv2025

PEVLM: Parallel Encoding for Vision-Language Models

Vision-Language Models (VLMs) have demonstrated strong capabilities in multimodal understanding and generation tasks. However, their application to long video understanding remains hindered by the quadratic complexity of standard attention mechanisms. In this work, we introduce \textbf{PEVLM}, a fine-tuning-free parallel encoding method designed to enhance the prefilling efficiency of VLMs in long video scenarios. PEVLM partitions the input video into context blocks with a shared sink block, while preserving sequential position embeddings to align the attention weight distribution with that of Full-Attention. This design reduces attention complexity from $O((T \times N)^2)$ to $O(T \times N)$ where $T$ is the number of frames and $N$ the number of tokens per frame, without sacrificing accuracy. Extensive experiments across multiple state-of-the-art models and benchmarks demonstrate that PEVLM consistently outperforms existing parallel encoding approaches, achieving up to \textbf{7.47x} speedup in attention computation and reducing end-to-end latency by \textbf{40\%}. Remarkably, PEVLM not only maintains high accuracy, but in some settings even surpasses Full-Attention performance. Under strict latency constraints, it achieves substantial gains, improving accuracy from \textbf{23.26\%} to \textbf{61.03\%}. These results underscore the effectiveness of PEVLM for low-latency, long-context video understanding, making it a promising solution for real-world applications.

cs.CV↗

arXiv2025

Benchmarking Generalizable Bimanual Manipulation: RoboTwin Dual-Arm Collaboration Challenge at CVPR 2025 MEIS Workshop

Embodied Artificial Intelligence (Embodied AI) is an emerging frontier in robotics, driven by the need for autonomous systems that can perceive, reason, and act in complex physical environments. While single-arm systems have shown strong task performance, collaborative dual-arm systems are essential for handling more intricate tasks involving rigid, deformable, and tactile-sensitive objects. To advance this goal, we launched the RoboTwin Dual-Arm Collaboration Challenge at the 2nd MEIS Workshop, CVPR 2025. Built on the RoboTwin Simulation platform (1.0 and 2.0) and the AgileX COBOT-Magic Robot platform, the competition consisted of three stages: Simulation Round 1, Simulation Round 2, and a final Real-World Round. Participants totally tackled 17 dual-arm manipulation tasks, covering rigid, deformable, and tactile-based scenarios. The challenge attracted 64 global teams and over 400 participants, producing top-performing solutions like SEM and AnchorDP3 and generating valuable insights into generalizable bimanual policy learning. This report outlines the competition setup, task design, evaluation methodology, key findings and future direction, aiming to support future research on robust and generalizable bimanual manipulation policies. The Challenge Webpage is available at https://robotwin-benchmark.github.io/cvpr-2025-challenge/.

cs.RO↗

arXiv2025

Bose-Hubbard Model on a Honeycomb Superlattice: Quantum Phase Transitions and Lattice Effects

We investigate the ground-state and finite-temperature phase diagrams of the Bose-Hubbard model on a honeycomb superlattice. The interplay between the superlattice potential depth $Δ/t$ and the onsite interaction $U/t$ gives rise to three distinct quantum phases at zero temperature: a superfluid phase, a Mott insulator I phase with unit filling on each site, and a Mott insulator II phase characterized by density imbalance-double occupancy on one sublattice and vacancy on the other at unit filling. The SF-MI transitions are found to be continuous, consistent with second-order quantum phase transitions. We further extend our analysis to finite temperatures within the superfluid regime. Our work highlights how a honeycomb superlattice geometry enables access to interaction- and lattice-modulation-driven quantum phases, including a density-imbalanced Mott insulator and a robust superfluid regime, offering concrete theoretical predictions for cold-atom experiments.

cond-mat.quant-gas↗