arXiv subjects

Jie Song

Publications and source records attributed to Jie Song.

At least 55 records · Page 3Linked to original sources

arXiv2026

Transition from Outside-in to Inside-Out at $z\sim 2$: Evidence from Radial Profiles of Specific Star Formation Rate based on JWST/HST

By combining high-resolution observations from JWST and HST, we have measured the stellar masses, star formation rates (SFRs), and multi-wavelength morphologies of galaxies in the CANDELS fields. Furthermore, based on rest-frame 1 $μ$m morphologies, we have derived spatially resolved stellar mass and SFR surface density ($Σ_*$ and $Σ_{\rm SFR}$) profiles for 46,313 galaxies with reliable structural measurements at $0 8$, and provide the corresponding catalogue. For star-forming galaxies (SFGs), our results show excellent consistency with previous studies in terms of the star formation main sequence and the size-mass relation, demonstrating the robustness of our stellar mass and SFR measurements. For spatially resolved profiles, we find that at higher redshifts ($z>2.5$), the median radial profile of $Σ_{\rm SFR}$ is nearly parallel to but slightly steeper than that of $Σ_*$. This results in mildly negative gradients in the specific SFR (sSFR) profiles across all stellar mass bins considered. These findings indicate that galaxies at $z>2.5$ cannot grow in size via only in-situ star formation, challenging the understanding of galaxy size evolution beyond the cosmic noon. In contrast, at $z<2.0$, the sSFR profiles transition to exhibit more and more positive gradients at lower redshifts, consistent with an inside-out growth scenario where star formation preferentially expands the galactic outskirts.

astro-ph.GA↗

arXiv2026

Hotspot-Aware Scheduling of Virtual Machines with Overcommitment for Ultimate Utilization in Cloud Datacenters

We address the problem of under-utilization of resources in datacenters during cloud operations, specifically focusing on the challenge of online virtual machine (VM) scheduling. Rather than following the traditional approach of scheduling VMs based solely on their static flavors, we take into account their dynamic CPU utilization. We employ $Γ$-robustness theory to manage the dynamic nature and introduce a novel variant of bin packing - Probabilistic k-Bins Packing (PkBP), which theoretically protects the Physical Machines (PMs) from hotspots formation within a specified probability $α$. We develop a scheduling algroithm named CloseRadiusFit and cold-start AI based prediction algorithms for the online version of PkBP. To verify the quality of our approach towards the optimal solutions, we solve the Offline PkBP problem by designing a novel Mixed Integer Linear Programming (MILP) model and a combination of numerical upper and lower bounds. Our experimental results demonstrate that CloseRadiusFit achieves narrow gaps of 1.6% and 3.1% when compared to the lower and upper bounds, respectively.

cs.DC↗

arXiv2026

Autonomous Detection and Coverage of Unknown Target Areas by Multi-Agent Systems

This paper presents a novel coverage control algorithm for multi-agent systems, where each agent has no prior knowledge of the specific region to be covered. The proposed method enables agents to autonomously detect the target area and collaboratively achieve full coverage. Once an agent detects a part of the target region within its sensor range, a dynamically constructed density function is generated to attract nearby agents. By integrating this density-driven mechanism with Centroidal Voronoi Tessellation (CVT), the agents are guided to achieve optimal spatial distribution. Additionally, Control Barrier Functions (CBFs) are employed to ensure collision avoidance and maintain non-overlapping sensor coverage, enhancing both safety and efficiency. Simulation results verify that agents can independently locate and effectively cover the target area.

eess.SY↗

arXiv2026

Cooperative Transportation Without Prior Object Knowledge via Adaptive Self-Allocation and Coordination

This work proposes a novel cooperative transportation framework for multi-agent systems that does not require any prior knowledge of cargo locations or sizes. Each agent relies on local sensing to detect cargos, recruit nearby agents, and autonomously form a transportation team with an appropriate size. The core idea is that once an agent detects a cargo within its sensing range, it generates an attraction field represented by a density function, which pulls neighboring agents toward the cargo. When multiple cargos are present, the attraction fields generated by different agents are adaptively weighted and combined with Centroidal Voronoi Tessellation (CVT), enabling agents to self-organize into balanced formations while automatically allocating more agents to larger cargos. To prevent agents from clustering on one side of a large cargo, a Control Barrier Function (CBF)-based mechanism is introduced to enforce safe inter-agent distances and promote a uniform, symmetric distribution of agents around each cargo, which is essential for stable transportation. Simulation results demonstrate that the proposed framework can simultaneously transport multiple cargos of different sizes in a coordinated and collision-free manner.

eess.SY↗

arXiv2026

From Evidence-Based Medicine to Knowledge Graph: Retrieval-Augmented Generation for Sports Rehabilitation and a Domain Benchmark

Current medical retrieval-augmented generation (RAG) approaches overlook evidence-based medicine (EBM) principles, leading to two key gaps: (1) the lack of PICO alignment between queries and retrieved evidence, and (2) the absence of evidence hierarchy considerations during reranking. We present SR-RAG, an EBM-adapted GraphRAG framework that integrates the PICO framework into knowledge graph construction and retrieval, and proposes Bayesian Evidence Tier Reranking (BETR) to calibrate ranking scores by evidence grade without predefined weights. Validated in sports rehabilitation, we release a knowledge graph (357,844 nodes, 371,226 edges) and a benchmark of 1,637 QA pairs. SR-RAG achieves 0.812 evidence recall@10, 0.830 nugget coverage, 0.819 answer faithfulness, 0.882 semantic similarity, and 0.788 PICOT match accuracy, substantially outperforming five baselines. Five expert clinicians rated the system 4.66--4.84 on a 5-point Likert scale, and system rankings are preserved on a human-verified gold subset (n=80).

cs.CL↗

arXiv2026

AMIF: Authorizable Medical Image Fusion Model with Built-in Authentication

Multimodal image fusion enables precise lesion localization and characterization for accurate diagnosis, thereby strengthening clinical decision-making and driving its growing prominence in medical imaging research. A powerful multimodal image fusion model relies on high-quality, clinically representative multimodal training data and a rigorously engineered model architecture. Therefore, the development of such professional radiomics models represents a collaborative achievement grounded in standardized acquisition, clinical-specific expertise, and algorithmic design proficiency, which necessitates protection of associated intellectual property rights. However, current multimodal image fusion models generate fused outputs without built-in mechanisms to safeguard intellectual property rights, inadvertently exposing proprietary model knowledge and sensitive training data through inference leakage. For example, malicious users can exploit fusion outputs and model distillation or other inference-based reverse engineering techniques to approximate the fusion performance of proprietary models. To address this issue, we propose AMIF, the first Authorizable Medical Image Fusion model with built-in authentication, which integrates authorization access control into the image fusion objective. For unauthorized usage, AMIF embeds explicit and visible copyright identifiers into fusion results. In contrast, high-quality fusion results are accessible upon successful key-based authentication.

cs.CV↗

arXiv2026

Rethinking Token Reduction for Large Vision-Language Models

Large Vision-Language Models (LVLMs) excel in visual understanding and reasoning, but the excessive visual tokens lead to high inference costs. Although recent token reduction methods mitigate this issue, they mainly target single-turn Visual Question Answering (VQA), leaving the more practical multi-turn VQA (MT-VQA) scenario largely unexplored. MT-VQA introduces additional challenges, as subsequent questions are unknown beforehand and may refer to arbitrary image regions, making existing reduction strategies ineffective. Specifically, current approaches fall into two categories: prompt-dependent methods, which bias toward the initial text prompt and discard information useful for subsequent turns; prompt-agnostic ones, which, though technically applicable to multi-turn settings, rely on heuristic reduction metrics such as attention scores, leading to suboptimal performance. In this paper, we propose a learning-based prompt-agnostic method, termed MetaCompress, overcoming the limitations of heuristic designs. We begin by formulating token reduction as a learnable compression mapping, unifying existing formats such as pruning and merging into a single learning objective. Upon this formulation, we introduce a data-efficient training paradigm capable of learning optimal compression mappings with limited computational costs. Extensive experiments on MT-VQA benchmarks and across multiple LVLM architectures demonstrate that MetaCompress achieves superior efficiency-accuracy trade-offs while maintaining strong generalization across dialogue turns. Our code is available at https://github.com/MArSha1147/MetaCompress.

cs.CV↗

arXiv2026

DriveFix: Spatio-Temporally Coherent Driving Scene Restoration

Recent advancements in 4D scene reconstruction, particularly those leveraging diffusion priors, have shown promise for novel view synthesis in autonomous driving. However, these methods often process frames independently or in a view-by-view manner, leading to a critical lack of spatio-temporal synergy. This results in spatial misalignment across cameras and temporal drift in sequences. We propose DriveFix, a novel multi-view restoration framework that ensures spatio-temporal coherence for driving scenes. Our approach employs an interleaved diffusion transformer architecture with specialized blocks to explicitly model both temporal dependencies and cross-camera spatial consistency. By conditioning the generation on historical context and integrating geometry-aware training losses, DriveFix enforces that the restored views adhere to a unified 3D geometry. This enables the consistent propagation of high-fidelity textures and significantly reduces artifacts. Extensive evaluations on the Waymo, nuScenes, and PandaSet datasets demonstrate that DriveFix achieves state-of-the-art performance in both reconstruction and novel view synthesis, marking a substantial step toward robust 4D world modeling for real-world deployment.

cs.CV↗

arXiv2026

$D^3$-RSMDE: 40$\times$ Faster and High-Fidelity Remote Sensing Monocular Depth Estimation

Real-time, high-fidelity monocular depth estimation from remote sensing imagery is crucial for numerous applications, yet existing methods face a stark trade-off between accuracy and efficiency. Although using Vision Transformer (ViT) backbones for dense prediction is fast, they often exhibit poor perceptual quality. Conversely, diffusion models offer high fidelity but at a prohibitive computational cost. To overcome these limitations, we propose Depth Detail Diffusion for Remote Sensing Monocular Depth Estimation ($D^3$-RSMDE), an efficient framework designed to achieve an optimal balance between speed and quality. Our framework first leverages a ViT-based module to rapidly generate a high-quality preliminary depth map construction, which serves as a structural prior, effectively replacing the time-consuming initial structure generation stage of diffusion models. Based on this prior, we propose a Progressive Linear Blending Refinement (PLBR) strategy, which uses a lightweight U-Net to refine the details in only a few iterations. The entire refinement step operates efficiently in a compact latent space supported by a Variational Autoencoder (VAE). Extensive experiments demonstrate that $D^3$-RSMDE achieves a notable 11.85% reduction in the Learned Perceptual Image Patch Similarity (LPIPS) perceptual metric over leading models like Marigold, while also achieving over a 40x speedup in inference and maintaining VRAM usage comparable to lightweight ViT models.

cs.CV↗

arXiv2026

Semi-supervised Latent Disentangled Diffusion Model for Textile Pattern Generation

Textile pattern generation (TPG) aims to synthesize fine-grained textile pattern images based on given clothing images. Although previous studies have not explicitly investigated TPG, existing image-to-image models appear to be natural candidates for this task. However, when applied directly, these methods often produce unfaithful results, failing to preserve fine-grained details due to feature confusion between complex textile patterns and the inherent non-rigid texture distortions in clothing images. In this paper, we propose a novel method, SLDDM-TPG, for faithful and high-fidelity TPG. Our method consists of two stages: (1) a latent disentangled network (LDN) that resolves feature confusion in clothing representations and constructs a multi-dimensional, independent clothing feature space; and (2) a semi-supervised latent diffusion model (S-LDM), which receives guidance signals from LDN and generates faithful results through semi-supervised diffusion training, combined with our designed fine-grained alignment strategy. Extensive evaluations show that SLDDM-TPG reduces FID by 4.1 and improves SSIM by up to 0.116 on our CTP-HD dataset, and also demonstrate good generalization on the VITON-HD dataset.

cs.CV↗

arXiv2026

Fuz-RL: A Fuzzy-Guided Robust Framework for Safe Reinforcement Learning under Uncertainty

Safe Reinforcement Learning (RL) is crucial for achieving high performance while ensuring safety in real-world applications. However, the complex interplay of multiple uncertainty sources in real environments poses significant challenges for interpretable risk assessment and robust decision-making. To address these challenges, we propose Fuz-RL, a fuzzy measure-guided robust framework for safe RL. Specifically, our framework develops a novel fuzzy Bellman operator for estimating robust value functions using Choquet integrals. Theoretically, we prove that solving the Fuz-RL problem (in Constrained Markov Decision Process (CMDP) form) is equivalent to solving distributionally robust safe RL problems (in robust CMDP form), effectively avoiding min-max optimization. Empirical analyses on safe-control-gym and safety-gymnasium scenarios demonstrate that Fuz-RL effectively integrates with existing safe RL baselines in a model-free manner, significantly improving both safety and control performance under various types of uncertainties in observation, action, and dynamics.

cs.LG↗

arXiv2026

LLM-Guided Safe Reinforcement Learning for Energy System Topology Reconfiguration

The increasing penetration of renewable generation and the growing variability of electrified demand introduce substantial operational uncertainty to modern power systems. Topology reconfiguration is widely recognized as an effective and economical means to enhance grid resilience. Due to the coexistence of AC power-flow constraints and discrete switching decisions, topology reconfiguration in large-scale systems leads to a highly nonlinear and nonconvex optimization problem, making traditional methods computationally prohibitive. Consequently, several studies have explored reinforcement learning-based approaches to improve scalability and operational efficiency. However, its practical implementation is challenged by the high-dimensional combinatorial action space and the need to ensure safety during learning-based decision-making. To address these challenges, this paper presents a safe and intelligent topology control framework that integrates Large Language Models (LLMs) with a Safety Soft Actor-Critic (Safety-SAC) architecture. Operational voltage and thermal limits are reformulated into smooth safety-cost signals, enabling risk-aware policy optimization within a constrained Markov decision process. A knowledge-based Safety-LLM module is further introduced to refine unsafe or suboptimal transitions through domain knowledge and state-informed reasoning, thus guiding the learning agent toward safer and more effective switching actions. Experiments on the IEEE 36-bus and 118-bus Grid2Op benchmarks show that the proposed method consistently improves reward, survival time, and safety metrics, achieving higher reward, longer survival, and lower safety cost compared with SAC, ACE, and their safety-enhanced variants. These results demonstrate the potential of combining LLM-based reasoning with safe reinforcement learning to achieve scalable and reliable grid topology control.

eess.SY↗

arXiv2026

Critical States Preparation With Deep Reinforcement Learning

The fast and efficient preparation of quantum critical states is a challenging yet crucial task for various quantum technologies. This difficulty is most particularly for systems near a quantum phase transition, where the closure of the energy gap fundamentally limits the timescale of adiabatic processes and thus precludes rapid state preparation. We propose a framework using deep reinforcement learning (DRL) to rapidly prepare quantum critical states, with broad extendibility to light-matter interaction systems. Specifically, a DRL agent optimizes a set of time-dependent control Hamiltonians to drive the system from an initial noncritical state to a target critical state within a finite time and over experimentally accessible parameter ranges. As a concrete application, we focus on the quantum Rabi model. The DRL-optimized time-dependent control Hamiltonian yield a final state with high-fidelity ($>0.999$) to the target critical state. The protocol can be readily extended to other quantum critical systems described by light-matter interaction models, such as quantum Dicke model. This investigation provides a powerful new framework for preparing and manipulating quantum critical states.

quant-ph↗

arXiv2026

Multi-UAV Flood Monitoring via CVT with Gaussian Mixture of Density Functions for Coverage Control

This study presents a control strategy for coordinating multiple unmanned aerial vehicles (UAVs) to monitor unknown flood regions and estimate the extent of inundation. The proposed method adopts a density-driven coverage framework based on Centroidal Voronoi Tessellation (CVT), in which the density function is modeled using a Gaussian Mixture of Density Functions (GMDF). This formulation provides a more accurate characterization of inundated areas compared to conventional axis-aligned Gaussian models. The performance of the two density modeling approaches is systematically evaluated under different UAV fleet sizes (16, 20, and 24), with multiple simulation trials conducted in the ROS/Gazebo environment. The results show that the GMDF-based formulation consistently achieves higher coverage rates, demonstrating its effectiveness in enhancing flood monitoring and improving UAV spatial distribution.

eess.SY↗

arXiv2026

Gaussian Wardrobe: Compositional 3D Gaussian Avatars for Free-Form Virtual Try-On

We introduce Gaussian Wardrobe, a novel framework to digitalize compositional 3D neural avatars from multi-view videos. Existing methods for 3D neural avatars typically treat the human body and clothing as an inseparable entity. However, this paradigm fails to capture the dynamics of complex free-form garments and limits the reuse of clothing across different individuals. To overcome these problems, we develop a novel, compositional 3D Gaussian representation to build avatars from multiple layers of free-form garments. The core of our method is decomposing neural avatars into bodies and layers of shape-agnostic neural garments. To achieve this, our framework learns to disentangle each garment layer from multi-view videos and canonicalizes it into a shape-independent space. In experiments, our method models photorealistic avatars with high-fidelity dynamics, achieving new state-of-the-art performance on novel pose synthesis benchmarks. In addition, we demonstrate that the learned compositional garments contribute to a versatile digital wardrobe, enabling a practical virtual try-on application where clothing can be freely transferred to new subjects. Project page: https://ait.ethz.ch/gaussianwardrobe

cs.CV↗

arXiv2026

Query-Efficient Zeroth-Order Algorithms for Nonconvex Constrained Optimization

Zeroth-order optimization (ZO) has been a powerful framework for solving black-box problems, which estimates gradients using zeroth-order data to update variables iteratively. The practical applicability of ZO critically depends on the efficiency of single-step gradient estimation and the overall query complexities. However, existing constrained ZO algorithms cannot achieve efficiency on both simultaneously. In this work, we consider a general constrained optimization model with black-box objective and constraint functions. To solve it, we propose novel algorithms that can achieve the best-known overall query complexity bound of $\mathcal{O}(d/ε^4)$ to find an $ε$-stationary solution ($d$ is the dimension of variables), while reducing the queries for estimating a single-step gradient from $\mathcal{O}(d)$ to $\mathcal{O}(1)$. Specifically, we integrate block gradient estimators with gradient descent ascent, which leads to two algorithms, ZOB-GDA and ZOB-SGDA, respectively. Instead of constructing full gradients, they estimate only partial gradients along random blocks of dimensions, where the adjustable block sizes enable high single-step efficiency without sacrificing convergence guarantees. Our theoretical results establish the finite-sample convergence of the proposed algorithms for nonconvex optimization. Finally, numerical experiments demonstrate the superior performance of our algorithms compared to existing methods.

math.OC↗

arXiv2026

First Statistical Detection of MgII-traced Cool Gas Outflows with JWST Towards Cosmic Dawn

Galactic-scale outflows are a crucial component of galaxy evolution, yet their properties in the early universe remain poorly constrained. We present the first statistical investigation of \ion{Mg}{2}-traced cool gas outflows in galaxies spanning a wide cosmic timeline from $z \approx 1$ to $z > 6$ (with sample coverage extending to $z \sim 10$). Using thousands of public JWST/NIRSpec spectra, we employ a signal-to-noise weighted spectral stacking technique on the \ion{Mg}{2} $λ\lambda2796, 2803$ absorption doublet. We robustly detect blueshifted \ion{Mg}{2} absorption in nearly all stellar mass and redshift bins, with the exception of the lowest-mass systems at $z \sim 1-2$. The outflow equivalent width exhibits a positive correlation with stellar mass ($M_*$) at all epochs, with the fitted slope of $1.21 \pm 0.35$. Our work provides the first statistical constraints on \ion{Mg}{2}-traced cool outflows in the low-mass ($M_* \lesssim 10^{9.5} \, \mathrm{M}_\odot$), high-redshift ($z > 3$) regime. We also find that the outflow velocities generally remain below the host halo escape velocities, consistent with a galactic fountain scenario. The consistency of the stellar mass-outflow equivalent width relation across $z \sim 2-6$ suggests a persistent, unevolving feedback mechanism governing the baryon cycle towards cosmic dawn.

astro-ph.GA↗

arXiv2026

SpatiaLQA: A Benchmark for Evaluating Spatial Logical Reasoning in Vision-Language Models

Vision-Language Models (VLMs) have been increasingly applied in real-world scenarios due to their outstanding understanding and reasoning capabilities. Although VLMs have already demonstrated impressive capabilities in common visual question answering and logical reasoning, they still lack the ability to make reasonable decisions in complex real-world environments. We define this ability as spatial logical reasoning, which not only requires understanding the spatial relationships among objects in complex scenes, but also the logical dependencies between steps in multi-step tasks. To bridge this gap, we introduce Spatial Logical Question Answering (SpatiaLQA), a benchmark designed to evaluate the spatial logical reasoning capabilities of VLMs. SpatiaLQA consists of 9,605 question answer pairs derived from 241 real-world indoor scenes. We conduct extensive experiments on 41 mainstream VLMs, and the results show that even the most advanced models still struggle with spatial logical reasoning. To address this issue, we propose a method called recursive scene graph assisted reasoning, which leverages visual foundation models to progressively decompose complex scenes into task-relevant scene graphs, thereby enhancing the spatial logical reasoning ability of VLMs, outperforming all previous methods. Code and dataset are available at https://github.com/xieyc99/SpatiaLQA.

cs.CV↗