arXiv subjects

Xin Wang

Publications and source records attributed to Xin Wang.

At least 577 records · Page 32Linked to original sources

arXiv2025

Parallel Application of Slitless Spectroscopy to Analyze Galaxy Evolution (PASSAGE): Survey Overview

During the second half of Cycle 1 of the James Webb Space Telescope (JWST), we conducted the Parallel Application of Slitless Spectroscopy to Analyze Galaxy Evolution (PASSAGE) program. PASSAGE received the largest allocation of JWST observing time in Cycle 1, 591 hours of NIRISS observations to obtain direct near-IR imaging and slitless spectroscopy. About two thirds of these were ultimately executed, to observe 63 high-latitude fields in Pure Parallel mode. These have provided more than ten thousand near-infrared grism spectrograms of faint galaxies. PASSAGE brings unique advantages in studying galaxy evolution: A) Unbiased spectroscopic search, without prior photometric pre-selection. By including the most numerous galaxies, with low masses and strong emission lines, slitless spectroscopy is the indispensable complement to any pre-targeted spectroscopy; B) The combination of several dozen independent fields to overcome cosmic variance; C) Near-infrared spectral coverage, often spanning the full range from 1.0--2.3 $μ$m, with minimal wavelength gaps, to measure multiple diagnostic rest-frame optical lines, minimizing sensitivity to dust reddening; D) JWST's unprecedented spatial resolution, in some cases using two orthogonal grism orientations, to overcome contamination due to blending of overlapping spectra; E) Discovery of rare bright objects especially for detailed JWST followup. PASSAGE data are public immediately, and our team plans to deliver fully-processed high-level data products. In this PASSAGE overview, we describe the survey and data quality, and present examples of these accomplishments in several areas of current interest in the evolution of emission-line galaxy properties, particularly at low masses.

astro-ph.GA↗

arXiv2025

Anderson Delocalization in Strongly Coupled Disordered Non-Hermitian Chains

Disorder and non-Hermitian effects together can upend how waves localize. In a 1D disordered chain, the non-Hermitian skin effect (NHSE) can induce Anderson delocalization, defying the usual rule that disorder in low dimensions always localizes states. While weak disorder leaves the NHSE intact, strong disorder restores Anderson localization. Here, we study a surprising twist: coupling a strongly disordered Hatano-Nelson chain to a disordered Hermitian chain with their disorder anti-symmetrically correlated. Strikingly, once the inter-chain coupling exceeds a threshold, the system undergoes Anderson delocalization irrespective of disorder strength, reinstating the NHSE with no Hermitian counterpart. This transition arises from the interplay of non-reciprocal hopping, inter-chain coupling, and engineered disorder correlations, and is captured by a real-space winding number. To confirm this, we build an electrical-circuit analog and directly observe the re-emergent NHSE via voltage measurements. Our work uncovers unexplored and experimentally accessible physics at the crossroads of non-Hermiticity and disorder.

cond-mat.dis-nn↗

arXiv2025

Experimental realization of dice-lattice flat band at the Fermi level in layered electride YCl

Flat electronic bands, where interactions among electrons overwhelm their kinetic energies, hold the promise for exotic correlation physics. The dice lattice has long been theorized as a host of flat bands with intriguing band topology. However, to date, no material has ever been found to host the characteristic flat bands of a dice lattice. Here, using angle-resolved photoemission spectroscopy (ARPES), we discover a dice-lattice flat band at $E_F$ in the van der Waals (vdW) electride [YCl]$^{2+}$: 2e-. In this system, excess valence electrons from Y deconfine from the cation framework to form an interstitial anionic electron lattice that constitutes the dice lattice. Our ARPES measurements unambiguously identify two sets of dice-lattice bands in YCl, including a nearly dispersionless band at the Fermi level. The flat bands and other dispersive bands observed in ARPES find excellent agreement with first-principles calculations, and theoretical analysis reveals that the near-$E_F$ electronic structure is well captured by a simple dice-lattice model. Our findings thus end the long quest of a real dice flat band material and establish vdW electride YCl as a prototype of dice metals. Our results further demonstrate the anionic electron lattice as a novel scheme for realizing lattice geometries and electronic structures rare to find in conventional crystalline systems.

cond-mat.str-el↗

arXiv2025

CrystalICL: Enabling In-Context Learning for Crystal Generation

Designing crystal materials with desired physicochemical properties remains a fundamental challenge in materials science. While large language models (LLMs) have demonstrated strong in-context learning (ICL) capabilities, existing LLM-based crystal generation approaches are limited to zero-shot scenarios and are unable to benefit from few-shot scenarios. In contrast, human experts typically design new materials by modifying relevant known structures which aligns closely with the few-shot ICL paradigm. Motivated by this, we propose CrystalICL, a novel model designed for few-shot crystal generation. Specifically, we introduce a space-group based crystal tokenization method, which effectively reduces the complexity of modeling crystal symmetry in LLMs. We further introduce a condition-structure aware hybrid instruction tuning framework and a multi-task instruction tuning strategy, enabling the model to better exploit ICL by capturing structure-property relationships from limited data. Extensive experiments on four crystal generation benchmarks demonstrate the superiority of CrystalICL over the leading baseline methods on conditional and unconditional generation tasks.

cs.LG↗

arXiv2025

StagFormer: Time Staggering Transformer Decoding for RunningLayers In Parallel

Decoding in a Transformer based language model is inherently sequential as a token's embedding needs to pass through all the layers in the network before the generation of the next token can begin. In this work, we propose a new architecture StagFormer (Staggered Transformer), which staggers execution along the sequence axis and thereby enables parallelizing the decoding process along the depth of the model. We achieve this by breaking the dependency of the token representation at time step $i$ in layer $l$ upon the representations of tokens until time step $i$ from layer $l-1$. Instead, we stagger the execution and only allow a dependency on token representations until time step $i-1$. The later sections of the Transformer still get access to the "rich" representations from the prior section but only from those token positions which are one time step behind. StagFormer allows for different sections of the model to be executed in parallel yielding a potential speedup in decoding while being quality neutral in our simulations. We also explore many natural extensions of this idea. We present how weight-sharing across the different sections being staggered can be more practical in settings with limited memory. We explore the efficacy of using a bounded window attention to pass information from one section to another which helps drive further latency gains for some applications. We also explore the scalability of the staggering idea over more than 2 sections of the Transformer. Finally, we show how one can approximate a recurrent model during inference using weight-sharing. This variant can lead to substantial gains in quality for short generations while being neutral in its latency impact.

cs.LG↗

arXiv2025

Can Structured Templates Facilitate LLMs in Tackling Harder Tasks? : An Exploration of Scaling Laws by Difficulty

Structured, procedural reasoning is essential for Large Language Models (LLMs), especially in mathematics. While post-training methods have improved LLM performance, they still fall short in capturing deep procedural logic on complex tasks. To tackle the issue, in this paper, we first investigate this limitation and uncover a novel finding: a Scaling Law by Difficulty, which reveals that model performance follows a U-shaped curve with respect to training data complexity -- excessive low-difficulty data impedes abstraction, while high-difficulty data significantly enhances reasoning ability. Motivated by this, we propose the Structured Solution Template (SST) framework, which uses solution templates and a curriculum of varied difficulty to explicitly teach procedural reasoning. Specifically, SST comprises (1) fine-tuning with structured solution-template chains and dynamically weighted loss to prioritize procedural logic, (2) prompt-time injection of solution templates as cognitive scaffolds to guide inference, and (3) integrated curriculum fine-tuning that explicitly teaches the model to self-plan - execute - self-correct. Experiments on GSM8K, AIME24, and new Dynamic En benchmark show that SST significantly improves both accuracy and efficiency, especially on harder problems.

cs.AI↗

arXiv2025

AI-Driven Reconstruction of Large-Scale Structure from Combined Photometric and Spectroscopic Surveys

Galaxy surveys are crucial for studying large-scale structure (LSS) and cosmology, yet they face limitations--imaging surveys provide extensive sky coverage but suffer from photo-$z$ uncertainties, while spectroscopic surveys yield precise redshifts but are sample-limited. To take advantage of both photo-$z$ and spec-$z$ data while eliminating photo-$z$ errors, we propose a deep learning framework based on a dual UNet architecture that integrates these two datasets at the field level to reconstruct the 3D photo-$z$ density field. We train the network on mock samples representative of stage-IV spectroscopic surveys, utilizing CosmicGrowth simulations with a $z=0.59$ snapshot containing $2048^3$ particles in a $(1200~h^{-1}\rm Mpc)^3$ volume. Several metrics, including correlation coefficient, MAE, MSE, PSNR, and SSIM, validate the model's accuracy. Moreover, the reconstructed power spectrum closely matches the ground truth at small scales ($k \gtrsim 0.06~h/\rm Mpc$) within the $1σ$ confidence level, while the UNet model significantly improves the estimation of photo-$z$ power spectrum multipoles. This study demonstrates the potential of deep learning to enhance LSS reconstruction by using both spectroscopic and photometric data.

astro-ph.IM↗

arXiv2025

Choice Outweighs Effort: Facilitating Complementary Knowledge Fusion in Federated Learning via Re-calibration and Merit-discrimination

Cross-client data heterogeneity in federated learning induces biases that impede unbiased consensus condensation and the complementary fusion of generalization- and personalization-oriented knowledge. While existing approaches mitigate heterogeneity through model decoupling and representation center loss, they often rely on static and restricted metrics to evaluate local knowledge and adopt global alignment too rigidly, leading to consensus distortion and diminished model adaptability. To address these limitations, we propose FedMate, a method that implements bilateral optimization: On the server side, we construct a dynamic global prototype, with aggregation weights calibrated by holistic integration of sample size, current parameters, and future prediction; a category-wise classifier is then fine-tuned using this prototype to preserve global consistency. On the client side, we introduce complementary classification fusion to enable merit-based discrimination training and incorporate cost-aware feature transmission to balance model performance and communication efficiency. Experiments on five datasets of varying complexity demonstrate that FedMate outperforms state-of-the-art methods in harmonizing generalization and adaptation. Additionally, semantic segmentation experiments on autonomous driving datasets validate the method's real-world scalability.

cs.LG↗

arXiv2025

PerPilot: Personalizing VLM-based Mobile Agents via Memory and Exploration

Vision language model (VLM)-based mobile agents show great potential for assisting users in performing instruction-driven tasks. However, these agents typically struggle with personalized instructions -- those containing ambiguous, user-specific context -- a challenge that has been largely overlooked in previous research. In this paper, we define personalized instructions and introduce PerInstruct, a novel human-annotated dataset covering diverse personalized instructions across various mobile scenarios. Furthermore, given the limited personalization capabilities of existing mobile agents, we propose PerPilot, a plug-and-play framework powered by large language models (LLMs) that enables mobile agents to autonomously perceive, understand, and execute personalized user instructions. PerPilot identifies personalized elements and autonomously completes instructions via two complementary approaches: memory-based retrieval and reasoning-based exploration. Experimental results demonstrate that PerPilot effectively handles personalized tasks with minimal user intervention and progressively improves its performance with continued use, underscoring the importance of personalization-aware reasoning for next-generation mobile agents. The dataset and code are available at: https://github.com/xinwang-nwpu/PerPilot

cs.AI↗

arXiv2025

AI-Powered Reconstruction of Dark Matter Velocity Fields from Redshift-Space Halo Distribution

We propose a UNet-based deep learning model to reconstruct the real-space dark matter (DM) velocity field from the redshift-space distribution of sparse DM halos. Using various statistical measures, we show that the reconstructed velocity components--including velocity magnitude, momentum, and divergence--closely match the ground truth, achieving better than 10% relative error and a correlation coefficient of 0.88. In the power spectrum comparison over $k \in [0.05, 0.3] h/{\rm Mpc}$, the UNet reconstruction outperforms linear theory and agrees with the true field within $2σ$. The model also effectively corrects redshift-space distortions (RSD), yielding unbiased power spectrum multipoles of DM fields within $2σ$. Notably, the UNet remains robust even with incomplete halo mass information. These results highlight the model's broad applicability to cosmological analyses, including RSD, cosmic web studies, the kinetic Sunyaev-Zel'dovich effect, and BAO reconstruction.

astro-ph.CO↗

arXiv2025

WildSpoof Challenge Evaluation Plan

The WildSpoof Challenge aims to advance the use of in-the-wild data in two intertwined speech processing tasks. It consists of two parallel tracks: (1) Text-to-Speech (TTS) synthesis for generating spoofed speech, and (2) Spoofing-robust Automatic Speaker Verification (SASV) for detecting spoofed speech. While the organizers coordinate both tracks and define the data protocols, participants treat them as separate and independent tasks. The primary objectives of the challenge are: (i) to promote the use of in-the-wild data for both TTS and SASV, moving beyond conventional clean and controlled datasets and considering real-world scenarios; and (ii) to encourage interdisciplinary collaboration between the spoofing generation (TTS) and spoofing detection (SASV) communities, thereby fostering the development of more integrated, robust, and realistic systems.

cs.SD↗

arXiv2025

Higher-order network adaptivity: co-evolution of higher-order structure and spreading dynamics

The co-evolution of structure and dynamics, known as adaptivity, is a fundamental property in various systems and drives diverse emergent behaviors. However, the adaptivity in previous works is primarily stemmed from pairwise situations, while is insufficient to capture ubiquitous higher-order characteristics of real systems. Here, we introduce higher-order network adaptivity to model the co-evolution of higher-order structure and spreading dynamics, and theoretically analyze the thresholds and spreading sizes. Results demonstrate that both pairwise-like and higher-order adaptivity consistently increase spreading thresholds, but surprisingly produce completely opposing qualitative effects. Specifically, contrary to pairwise-like adaptivity, higher-order adaptivity not only reduces or even eliminates the bistable region, but also leads to shifts of phase transitions from discontinuous to continuous. These findings are validated on both synthetic and real hypergraphs. Our work introduces an idea of higher-order adaptivity and highlights its fundamental differences from pairwise-like adaptivity, advancing further researches of adaptive higher-order systems.

physics.soc-ph↗

arXiv2025

Uhlmann and scalar Wilczek-Zee phases of degenerate quantum systems

The Wilczek-Zee (WZ) holonomy arises in degenerate states while the Uhlmann holonomy characterizes finite-temperature topology. We investigate possible relationships between the Uhlmann phase and the scalar WZ phase, which reflects the Uhlmann and WZ holonomy respectively, in an exemplary four-level model with two doubly degenerate subspaces. Through exact solutions, we contrast the behavior of the Uhlmann and WZ connections and their associated phases. In the zero-temperature limit, the Uhlmann phase may or may not agree with the scalar WZ phase of the degenerate ground states due to obstructions from the Hamiltonian manifested as Dirac points. This is in stark contrast to non-degenerate systems where the correspondence between the Uhlmann and Berry phases in general holds. Our analyses further show that for the example studied here, the Uhlmann phase catches the singular behavior at the Dirac points while the WZ connection and scalar WZ phase vanish along a zero-field axis. We also briefly discuss possible experimental implications.

quant-ph↗

arXiv2025

Deep Skin Lesion Segmentation with Transformer-CNN Fusion: Toward Intelligent Skin Cancer Analysis

This paper proposes a high-precision semantic segmentation method based on an improved TransUNet architecture to address the challenges of complex lesion structures, blurred boundaries, and significant scale variations in skin lesion images. The method integrates a transformer module into the traditional encoder-decoder framework to model global semantic information, while retaining a convolutional branch to preserve local texture and edge features. This enhances the model's ability to perceive fine-grained structures. A boundary-guided attention mechanism and multi-scale upsampling path are also designed to improve lesion boundary localization and segmentation consistency. To verify the effectiveness of the approach, a series of experiments were conducted, including comparative studies, hyperparameter sensitivity analysis, data augmentation effects, input resolution variation, and training data split ratio tests. Experimental results show that the proposed model outperforms existing representative methods in mIoU, mDice, and mAcc, demonstrating stronger lesion recognition accuracy and robustness. In particular, the model achieves better boundary reconstruction and structural recovery in complex scenarios, making it well-suited for the key demands of automated segmentation tasks in skin lesion analysis.

eess.IV↗

arXiv2025

Differentiable Forward and Back-Projector for Rigid Motion Estimation in X-ray Imaging

Objective: In this work, we propose a framework for differentiable forward and back-projector that enables scalable, accurate, and memory-efficient gradient computation for rigid motion estimation tasks. Methods: Unlike existing approaches that rely on auto-differentiation or that are restricted to specific projector types, our method is based on a general analytical gradient formulation for forward/backprojection in the continuous domain. A key insight is that the gradients of both forward and back-projection can be expressed directly in terms of the forward and back-projection operations themselves, providing a unified gradient computation scheme across different projector types. Leveraging this analytical formulation, we develop a discretized implementation with an acceleration strategy that balances computational speed and memory usage. Results: Simulation studies illustrate the numerical accuracy and computational efficiency of the proposed algorithm. Experiments demonstrates the effectiveness of this approach for multiple X-ray imaging tasks we conducted. In 2D/3D registration, the proposed method achieves ~8x speedup over an existing differentiable forward projector while maintaining comparable accuracy. In motion-compensated analytical reconstruction and cone-beam CT geometry calibration, the proposed method enhances image sharpness and structural fidelity on real phantom data while showing significant efficiency advantages over existing gradient-free and gradient-based solutions. Conclusion: The proposed differentiable projectors enable effective and efficient gradient-based solutions for X-ray imaging tasks requiring rigid motion estimation.

physics.med-ph↗

arXiv2025

SEF-MK: Speaker-Embedding-Free Voice Anonymization through Multi-k-means Quantization

Voice anonymization protects speaker privacy by concealing identity while preserving linguistic and paralinguistic content. Self-supervised learning (SSL) representations encode linguistic features but preserve speaker traits. We propose a novel speaker-embedding-free framework called SEF-MK. Instead of using a single k-means model trained on the entire dataset, SEF-MK anonymizes SSL representations for each utterance by randomly selecting one of multiple k-means models, each trained on a different subset of speakers. We explore this approach from both attacker and user perspectives. Extensive experiments show that, compared to a single k-means model, SEF-MK with multiple k-means models better preserves linguistic and emotional content from the user's viewpoint. However, from the attacker's perspective, utilizing multiple k-means models boosts the effectiveness of privacy attacks. These insights can aid users in designing voice anonymization systems to mitigate attacker threats.

cs.SD↗

arXiv2025

Defects4Log: Benchmarking LLMs for Logging Code Defect Detection and Reasoning

Logging code is written by developers to capture system runtime behavior and plays a vital role in debugging, performance analysis, and system monitoring. However, defects in logging code can undermine the usefulness of logs and lead to misinterpretations. Although prior work has identified several logging defect patterns and provided valuable insights into logging practices, these studies often focus on a narrow range of defect patterns derived from limited sources (e.g., commit histories) and lack a systematic and comprehensive analysis. Moreover, large language models (LLMs) have demonstrated promising generalization and reasoning capabilities across a variety of code-related tasks, yet their potential for detecting logging code defects remains largely unexplored. In this paper, we derive a comprehensive taxonomy of logging code defects, which encompasses seven logging code defect patterns with 14 detailed scenarios. We further construct a benchmark dataset, \dataset, consisting of 164 developer-verified real-world logging defects. Then we propose an automated framework that leverages various prompting strategies and contextual information to evaluate LLMs' capability in detecting and reasoning logging code defects. Experimental results reveal that LLMs generally struggle to accurately detect and reason logging code defects based on the source code only. However, incorporating proper knowledge (e.g., detailed scenarios of defect patterns) can lead to 10.9\% improvement in detection accuracy. Overall, our findings provide actionable guidance for practitioners to avoid common defect patterns and establish a foundation for improving LLM-based reasoning in logging code defect detection.

cs.SE↗

arXiv2025

Argus Inspection: Do Multimodal Large Language Models Possess the Eye of Panoptes?

As Multimodal Large Language Models (MLLMs) continue to evolve, their cognitive and reasoning capabilities have seen remarkable progress. However, challenges in visual fine-grained perception and commonsense causal inference persist. This paper introduces Argus Inspection, a multimodal benchmark with two levels of difficulty, emphasizing detailed visual recognition while incorporating real-world commonsense understanding to evaluate causal reasoning abilities. Expanding on it, we present the Eye of Panoptes framework, which integrates a binary parametric Sigmoid metric with an indicator function, enabling a more holistic evaluation of MLLMs' responses in opinion-based reasoning tasks. Experiments conducted on 26 mainstream MLLMs reveal that the highest performance in visual fine-grained reasoning reaches only 0.46, highlighting considerable potential for enhancement. Our research offers valuable perspectives for the continued refinement of MLLMs.

cs.CV↗