arXiv subjects

Zhuo Chen

Publications and source records attributed to Zhuo Chen.

At least 163 records · Page 9Linked to original sources

arXiv2025

Kinematical Modeling of the Resolved Stellar Outskirts of M32: Constraints on Tidal Stripping Scenarios

As the only compact elliptical close enough to resolve into individual stars, the satellite dwarf galaxy M32 provides a unique opportunity for exploring the origins of such rare galaxies. In this work, we combined archival and novel Keck/DEIMOS spectroscopy from a southern extension of the Spectroscopic and Photometric Landscape of Andromeda's Stellar Halo (SPLASH) survey with optical HST imaging from the Panchromatic Hubble Andromeda Southern Treasury (PHAST) survey. The resulting sample of 2525 giant stars is unprecedented both in size and spatial coverage (0.9-15.5 arcmin, or out to $\sim$23$r_{\rm eff}$ and $\sim$30$r_{\rm eff}$ along M32's major and minor axes) for probing the resolved stellar outskirts of M32. Given the structurally complex region near M32 on the sky, we modeled M32's line-of-sight kinematics simultaneously alongside M31's rotating stellar disk and potential outliers corresponding to M31's kinematically hot stellar halo and/or tidal substructure. Inside the radius corresponding to the observed twisting of isophotal contours in M32's surface brightness profile ($R_{\rm iso} \sim$ 5$r_{\rm eff}$ $\sim$ 150'' or 0.56 kpc), M32 exhibits a line-of-sight velocity distribution characteristic of ordered rotation, transitioning to a distribution with heavier outliers beyond this radius. Within $R_{\rm iso}$, the rotational direction is aligned with M32's major-axis rotation, but shifts to become roughly aligned with M32's minor axis beyond $R_{\rm iso}$. We interpret these kinematical signatures in the stellar outskirts of M32 as evidence of tidal distortion from interactions with M31 and discuss their implications for M32 formation pathways.

astro-ph.GA↗

arXiv2025

Microscopic Fingerprint of Chiral Superconductivity

Chiral superconductors have long been theorized to break time-reversal symmetry and support exotic topological features such as Majorana modes and spontaneous edge currents, promising ingredients for quantum technologies. Although several unconventional superconductors may exhibit time-reversal symmetry breaking, clear microscopic evidence of chiral pairing has remained out of reach. In this work, we demonstrate direct real-space signatures of chiral superconductivity in a single atomic layer of tin on Si(111). Using quasiparticle interference imaging, we detected symmetry-locked nodal and antinodal points in the Bogoliubov quasiparticle wavefunction, tightly bound to atomic point defects in the tin lattice. These nodal features, along with their surrounding texture, form a distinct real-space pattern exhibiting a clear and exclusive hallmark of chiral superconductivity. Our findings, reinforced by analytical theory and numerical simulations, offer unambiguous evidence of chiral pairing in a two-dimensional material.

cond-mat.supr-con↗

arXiv2025

Dataset Distillation as Data Compression: A Rate-Utility Perspective

Driven by the ``scale-is-everything'' paradigm, modern machine learning increasingly demands ever-larger datasets and models, yielding prohibitive computational and storage requirements. Dataset distillation mitigates this by compressing an original dataset into a small set of synthetic samples, while preserving its full utility. Yet, existing methods either maximize performance under fixed storage budgets or pursue suitable synthetic data representations for redundancy removal, without jointly optimizing both objectives. In this work, we propose a joint rate-utility optimization method for dataset distillation. We parameterize synthetic samples as optimizable latent codes decoded by extremely lightweight networks. We estimate the Shannon entropy of quantized latents as the rate measure and plug any existing distillation loss as the utility measure, trading them off via a Lagrange multiplier. To enable fair, cross-method comparisons, we introduce bits per class (bpc), a precise storage metric that accounts for sample, label, and decoder parameter costs. On CIFAR-10, CIFAR-100, and ImageNet-128, our method achieves up to $170\times$ greater compression than standard distillation at comparable accuracy. Across diverse bpc budgets, distillation losses, and backbone architectures, our approach consistently establishes better rate-utility trade-offs.

cs.LG↗

arXiv2025

One-for-More: Continual Diffusion Model for Anomaly Detection

With the rise of generative models, there is a growing interest in unifying all tasks within a generative framework. Anomaly detection methods also fall into this scope and utilize diffusion models to generate or reconstruct normal samples when given arbitrary anomaly images. However, our study found that the diffusion model suffers from severe ``faithfulness hallucination'' and ``catastrophic forgetting'', which can't meet the unpredictable pattern increments. To mitigate the above problems, we propose a continual diffusion model that uses gradient projection to achieve stable continual learning. Gradient projection deploys a regularization on the model updating by modifying the gradient towards the direction protecting the learned knowledge. But as a double-edged sword, it also requires huge memory costs brought by the Markov process. Hence, we propose an iterative singular value decomposition method based on the transitive property of linear representation, which consumes tiny memory and incurs almost no performance loss. Finally, considering the risk of ``over-fitting'' to normal images of the diffusion model, we propose an anomaly-masked network to enhance the condition mechanism of the diffusion model. For continual anomaly detection, ours achieves first place in 17/18 settings on MVTec and VisA. Code is available at https://github.com/FuNz-0/One-for-More

cs.CV↗

arXiv2025

Dens3R: A Foundation Model for 3D Geometry Prediction

Recent advances in dense 3D reconstruction have led to significant progress, yet achieving accurate unified geometric prediction remains a major challenge. Most existing methods are limited to predicting a single geometry quantity from input images. However, geometric quantities such as depth, surface normals, and point maps are inherently correlated, and estimating them in isolation often fails to ensure consistency, thereby limiting both accuracy and practical applicability. This motivates us to explore a unified framework that explicitly models the structural coupling among different geometric properties to enable joint regression. In this paper, we present Dens3R, a 3D foundation model designed for joint geometric dense prediction and adaptable to a wide range of downstream tasks. Dens3R adopts a two-stage training framework to progressively build a pointmap representation that is both generalizable and intrinsically invariant. Specifically, we design a lightweight shared encoder-decoder backbone and introduce position-interpolated rotary positional encoding to maintain expressive power while enhancing robustness to high-resolution inputs. By integrating image-pair matching features with intrinsic invariance modeling, Dens3R accurately regresses multiple geometric quantities such as surface normals and depth, achieving consistent geometry perception from single-view to multi-view inputs. Additionally, we propose a post-processing pipeline that supports geometrically consistent multi-view inference. Extensive experiments demonstrate the superior performance of Dens3R across various dense 3D prediction tasks and highlight its potential for broader applications.

cs.CV↗

arXiv2025

Multimodal Latent Diffusion Model for Complex Sewing Pattern Generation

Generating sewing patterns in garment design is receiving increasing attention due to its CG-friendly and flexible-editing nature. Previous sewing pattern generation methods have been able to produce exquisite clothing, but struggle to design complex garments with detailed control. To address these issues, we propose SewingLDM, a multi-modal generative model that generates sewing patterns controlled by text prompts, body shapes, and garment sketches. Initially, we extend the original vector of sewing patterns into a more comprehensive representation to cover more intricate details and then compress them into a compact latent space. To learn the sewing pattern distribution in the latent space, we design a two-step training strategy to inject the multi-modal conditions, \ie, body shapes, text prompts, and garment sketches, into a diffusion model, ensuring the generated garments are body-suited and detail-controlled. Comprehensive qualitative and quantitative experiments show the effectiveness of our proposed method, significantly surpassing previous approaches in terms of complex garment design and various body adaptability. Our project page: https://shengqiliu1.github.io/SewingLDM.

cs.CV↗

arXiv2025

Iterative Camera-LiDAR Extrinsic Optimization via Surrogate Diffusion

Cameras and LiDAR are essential sensors for autonomous vehicles. Camera-LiDAR data fusion compensate for deficiencies of stand-alone sensors but relies on precise extrinsic calibration. Many learning-based calibration methods predict extrinsic parameters in a single step. Driven by the growing demand for higher accuracy, a few approaches utilize multi-range models or integrate multiple methods to improve extrinsic parameter predictions, but these strategies incur extended training times and require additional storage for separate models. To address these issues, we propose a single-model iterative approach based on surrogate diffusion to significantly enhance the capacity of individual calibration methods. By applying a buffering technique proposed by us, the inference time of our surrogate diffusion is 43.7% less than that of multi-range models. Additionally, we create a calibration network as our denoiser, featuring both projection-first and encoding-first branches for effective point feature extraction. Extensive experiments demonstrate that our diffusion model outperforms other single-model iterative methods and delivers competitive results compared to multi-range models. Our denoiser exceeds state-of-the-art calibration methods, reducing the rotation error by 24.5% compared to the second-best method. Furthermore, with the proposed diffusion applied, it achieves 20.4% less rotation error and 9.6% less translation error.

cs.CV↗

arXiv2025

Iterative Camera-LiDAR Extrinsic Optimization via Surrogate Diffusion

Cameras and LiDAR are essential sensors for autonomous vehicles. The fusion of camera and LiDAR data addresses the limitations of individual sensors but relies on precise extrinsic calibration. Recently, numerous end-to-end calibration methods have been proposed; however, most predict extrinsic parameters in a single step and lack iterative optimization capabilities. To address the increasing demand for higher accuracy, we propose a versatile iterative framework based on surrogate diffusion. This framework can enhance the performance of any calibration method without requiring architectural modifications. Specifically, the initial extrinsic parameters undergo iterative refinement through a denoising process, in which the original calibration method serves as a surrogate denoiser to estimate the final extrinsics at each step. For comparative analysis, we selected four state-of-the-art calibration methods as surrogate denoisers and compared the results of our diffusion process with those of two other iterative approaches. Extensive experiments demonstrate that when integrated with our diffusion model, all calibration methods achieve higher accuracy, improved robustness, and greater stability compared to other iterative techniques and their single-step counterparts.

cs.CV↗

arXiv2025

Atiyah constructions for Lie algebroid connections on fiber bundles

To address the need for a unified framework that incorporates Lie algebroid connections on both vector and principal bundles, this paper investigates a generalized Atiyah algebroid structure and its short exact sequence. Building on this generalization, we describe Atiyah-type extensions and sequences that represent Atiyah classes through three explicit constructions designed to encode Lie algebroid connections compatible with specified sub-structures. As illustrative examples, we work out an enriched Atiyah algebroid construct, providing a systematic tool to characterize certain key properties of holomorphic connections and invariant connections.

math.DG↗

arXiv2025

Auto-Regressive Surface Cutting

Surface cutting is a fundamental task in computer graphics, with applications in UV parameterization, texture mapping, and mesh decomposition. However, existing methods often produce technically valid but overly fragmented atlases that lack semantic coherence. We introduce SeamGPT, an auto-regressive model that generates cutting seams by mimicking professional workflows. Our key technical innovation lies in formulating surface cutting as a next token prediction task: sample point clouds on mesh vertices and edges, encode them as shape conditions, and employ a GPT-style transformer to sequentially predict seam segments with quantized 3D coordinates. Our approach achieves exceptional performance on UV unwrapping benchmarks containing both manifold and non-manifold meshes, including artist-created, and 3D-scanned models. In addition, it enhances existing 3D segmentation tools by providing clean boundaries for part decomposition.

cs.GR↗

arXiv2025

Efficient Blockchain-based Steganography via Backcalculating Generative Adversarial Network

Blockchain-based steganography enables data hiding via encoding the covert data into a specific blockchain transaction field. However, previous works focus on the specific field-embedding methods while lacking a consideration on required field-generation embedding. In this paper, we propose a generic blockchain-based steganography framework (GBSF). The sender generates the required fields such as amount and fees, where the additional covert data is embedded to enhance the channel capacity. Based on GBSF, we design a reversible generative adversarial network (R-GAN) that utilizes the generative adversarial network with a reversible generator to generate the required fields and encode additional covert data into the input noise of the reversible generator. We then explore the performance flaw of R-GAN. To further improve the performance, we propose R-GAN with Counter-intuitive data preprocessing and Custom activation functions, namely CCR-GAN. The counter-intuitive data preprocessing (CIDP) mechanism is used to reduce decoding errors in covert data, while it incurs gradient explosion for model convergence. The custom activation function named ClipSigmoid is devised to overcome the problem. Theoretical justification for CIDP and ClipSigmoid is also provided. We also develop a mechanism named T2C, which balances capacity and concealment. We conduct experiments using the transaction amount of the Bitcoin mainnet as the required field to verify the feasibility. We then apply the proposed schemes to other transaction fields and blockchains to demonstrate the scalability. Finally, we evaluate capacity and concealment for various blockchains and transaction fields and explore the trade-off between capacity and concealment. The results demonstrate that R-GAN and CCR-GAN are able to enhance the channel capacity effectively and outperform state-of-the-art works.

cs.CR↗

arXiv2025

Subthreshold Swing Behavior in Amorphous Indium-Gallium-Zinc-Oxide Transistors from Room to Cryogenic Temperatures

While cryogenic-temperature subthreshold swing (SS) in crystalline semiconductors has been widely studied, a careful study on the temperature-dependent SS in amorphous oxide semiconductors remains lacking. In this paper, a comprehensive analysis of the SS in thin-film transistors with an amorphous indium gallium zinc oxide (IGZO) channel at temperatures from 300 K down to 4 K is presented. Main observations include: 1) At room temperature (300 K), the devices exhibit a SS of 61 mV/dec, and a low interface trap density (<1011 cm-2), among the best reported values for IGZO devices. 2) A SS saturation around 40 mV/dec is observed between 200 K and 100 K. It is well explained by the electron transport via band tail states with exponential decay (Wt) of 13 meV. 3) At deep-cryogenic temperature, SS increase significantly exceeding 200 mV/dec at 4 K. Such high SS values are actually limited by the measurement current range, confirmed by Id-Vg simulations based on the variable range hopping (VRH) model. This work not only elucidates the SS behavior in amorphous IGZO devices but also provides a deep understanding of the physical mechanisms of electron transport in amorphous semiconductors.

cond-mat.mtrl-sci↗

arXiv2025

The impact of process steps on nearly ideal subthreshold slope in 300-mm compatible InGaZnO TFT

While we demonstrate a back-gated (BG) amorphous Indium-Gallium-Zinc-Oxide (a-IGZO) transistors with a nearly ideal subthreshold slope (SS) ~ 60 mV/dec. However, SS degrades when a top-gated (TG) configuration is implemented. The energy distribution of traps inferred from temperature-dependent (T = 4 K - 300 K) and multi-frequency (f = 1 kHz - 100 kHz) admittance measurements, reveals a much higher trap density in TG devices. By analyzing the impact of each process step and conducting forming gas anneal (FGA) experiments, we reveal the role of hydrogen in the deterioration of the SS in the IGZO-based transistors.

physics.app-ph↗

arXiv2025

KnowCoder-V2: Deep Knowledge Analysis

Deep knowledge analysis tasks always involve the systematic extraction and association of knowledge from large volumes of data, followed by logical reasoning to discover insights. However, to solve such complex tasks, existing deep research frameworks face three major challenges: 1) They lack systematic organization and management of knowledge; 2) They operate purely online, making it inefficient for tasks that rely on shared and large-scale knowledge; 3) They cannot perform complex knowledge computation, limiting their abilities to produce insightful analytical results. Motivated by these, in this paper, we propose a \textbf{K}nowledgeable \textbf{D}eep \textbf{R}esearch (\textbf{KDR}) framework that empowers deep research with deep knowledge analysis capability. Specifically, it introduces an independent knowledge organization phase to preprocess large-scale, domain-relevant data into systematic knowledge offline. Based on this knowledge, it extends deep research with an additional kind of reasoning steps that perform complex knowledge computation in an online manner. To enhance the abilities of LLMs to solve knowledge analysis tasks in the above framework, we further introduce \textbf{\KCII}, an LLM that bridges knowledge organization and reasoning via unified code generation. For knowledge organization, it generates instantiation code for predefined classes, transforming data into knowledge objects. For knowledge computation, it generates analysis code and executes on the above knowledge objects to obtain deep analysis results. Experimental results on more than thirty datasets across six knowledge analysis tasks demonstrate the effectiveness of \KCII. Moreover, when integrated into the KDR framework, \KCII can generate high-quality reports with insightful analytical results compared to the mainstream deep research framework.

cs.AI↗

arXiv2025

Advancing Zero-shot Text-to-Speech Intelligibility across Diverse Domains via Preference Alignment

Modern zero-shot text-to-speech (TTS) systems, despite using extensive pre-training, often struggle in challenging scenarios such as tongue twisters, repeated words, code-switching, and cross-lingual synthesis, leading to intelligibility issues. To address these limitations, this paper leverages preference alignment techniques, which enable targeted construction of out-of-pretraining-distribution data to enhance performance. We introduce a new dataset, named the Intelligibility Preference Speech Dataset (INTP), and extend the Direct Preference Optimization (DPO) framework to accommodate diverse TTS architectures. After INTP alignment, in addition to intelligibility, we observe overall improvements including naturalness, similarity, and audio quality for multiple TTS models across diverse domains. Based on that, we also verify the weak-to-strong generalization ability of INTP for more intelligible models such as CosyVoice 2 and Ints. Moreover, we showcase the potential for further improvements through iterative alignment based on Ints. Audio samples are available at https://intalign.github.io/.

cs.SD↗

arXiv2025

RoboOS: A Hierarchical Embodied Framework for Cross-Embodiment and Multi-Agent Collaboration

The dawn of embodied intelligence has ushered in an unprecedented imperative for resilient, cognition-enabled multi-agent collaboration across next-generation ecosystems, revolutionizing paradigms in autonomous manufacturing, adaptive service robotics, and cyber-physical production architectures. However, current robotic systems face significant limitations, such as limited cross-embodiment adaptability, inefficient task scheduling, and insufficient dynamic error correction. While End-to-end VLA models demonstrate inadequate long-horizon planning and task generalization, hierarchical VLA models suffer from a lack of cross-embodiment and multi-agent coordination capabilities. To address these challenges, we introduce RoboOS, the first open-source embodied system built on a Brain-Cerebellum hierarchical architecture, enabling a paradigm shift from single-agent to multi-agent intelligence. Specifically, RoboOS consists of three key components: (1) Embodied Brain Model (RoboBrain), a MLLM designed for global perception and high-level decision-making; (2) Cerebellum Skill Library, a modular, plug-and-play toolkit that facilitates seamless execution of multiple skills; and (3) Real-Time Shared Memory, a spatiotemporal synchronization mechanism for coordinating multi-agent states. By integrating hierarchical information flow, RoboOS bridges Embodied Brain and Cerebellum Skill Library, facilitating robust planning, scheduling, and error correction for long-horizon tasks, while ensuring efficient multi-agent collaboration through Real-Time Shared Memory. Furthermore, we enhance edge-cloud communication and cloud-based distributed inference to facilitate high-frequency interactions and enable scalable deployment. Extensive real-world experiments across various scenarios, demonstrate RoboOS's versatility in supporting heterogeneous embodiments. Project website: https://github.com/FlagOpen/RoboOS

cs.RO↗

arXiv2025

Sounding that Object: Interactive Object-Aware Image to Audio Generation

Generating accurate sounds for complex audio-visual scenes is challenging, especially in the presence of multiple objects and sound sources. In this paper, we propose an {\em interactive object-aware audio generation} model that grounds sound generation in user-selected visual objects within images. Our method integrates object-centric learning into a conditional latent diffusion model, which learns to associate image regions with their corresponding sounds through multi-modal attention. At test time, our model employs image segmentation to allow users to interactively generate sounds at the {\em object} level. We theoretically validate that our attention mechanism functionally approximates test-time segmentation masks, ensuring the generated audio aligns with selected objects. Quantitative and qualitative evaluations show that our model outperforms baselines, achieving better alignment between objects and their associated sounds. Project page: https://tinglok.netlify.app/files/avobject/

cs.CV↗

arXiv2025

Abstractive Visual Understanding of Multi-modal Structured Knowledge: A New Perspective for MLLM Evaluation

Multi-modal large language models (MLLMs) incorporate heterogeneous modalities into LLMs, enabling a comprehensive understanding of diverse scenarios and objects. Despite the proliferation of evaluation benchmarks and leaderboards for MLLMs, they predominantly overlook the critical capacity of MLLMs to comprehend world knowledge with structured abstractions that appear in visual form. To address this gap, we propose a novel evaluation paradigm and devise M3STR, an innovative benchmark grounded in the Multi-Modal Map for STRuctured understanding. This benchmark leverages multi-modal knowledge graphs to synthesize images encapsulating subgraph architectures enriched with multi-modal entities. M3STR necessitates that MLLMs not only recognize the multi-modal entities within the visual inputs but also decipher intricate relational topologies among them. We delineate the benchmark's statistical profiles and automated construction pipeline, accompanied by an extensive empirical analysis of 26 state-of-the-art MLLMs. Our findings reveal persistent deficiencies in processing abstractive visual information with structured knowledge, thereby charting a pivotal trajectory for advancing MLLMs' holistic reasoning capacities. Our code and data are released at https://github.com/zjukg/M3STR

cs.CV↗