Searcharxiv⌕ Search

arXiv subjects

Xiao Chen

Publications and source records attributed to Xiao Chen.

At least 109 records · Page 6Linked to original sources
arXiv2025

Density of States (Gate) - Controlled Andreev Molecule and Sensor

Topological quantum computing typically relies on topological Andreev bound states (ABSs) engineered in hybrid superconductor-semiconductor devices, where gate control offers key advantages. While strong Zeeman fields can induce such states, an alternative approach emerges through Andreev molecules -- closely spaced, coupled ABSs, also key building-block for Kitaev chain -- that enable topological behavior without high magnetic fields. However, existing Andreev molecules are controlled via magnetic flux in superconducting loops, limiting scalability. Here, we introduce a gate-controlled Andreev molecule, where electrostatic tuning of the density of states in one site nonlocally enhances the critical current of another. This eliminates superconducting loops, offering superior tunability, scalability, and sensitivity. We further extend such an Andreev molecule to a multi-site Kitaev chain, and a noninvasive sensor resolving single-Cooper-pair charge for parity readout. This platform bridges the gap between scalable ABS engineering and high-sensitivity quantum sensing, advancing the development for constructing and parity-readout in topological ABSs and long Kitaev chains towards topological qubits.

cond-mat.mes-hall↗
arXiv2025

Magic transition in monitored free fermion dynamics

We investigate magic and its connection to entanglement in 1+1 dimensional random free fermion circuits, with a focus on hybrid free fermion dynamics that can exhibit an entanglement phase transition. To quantify magic, we use the Stabilizer Rényi Entropy (SRE), which we compute numerically via a perfect sampling algorithm. We show that although the SRE remains extensive as the system transitions from a critical phase to an area-law (disentangled) phase, the structure of magic itself undergoes a delocalization phase transition. This transition is characterized using the bipartite stabilizer mutual information, which exhibits the same scaling behavior as entanglement entropy: logarithmic scaling in the critical phase and a finite constant in the area-law phase. Additionally, we explore the dynamics of SRE. While the total SRE becomes extensive in $O(1)$ time, we find that in the critical phase, the relaxation time to the steady-state value is parameterically longer than that in generic random circuits. The relaxation follows a universal form, with a relaxation time that grows linearly with the system size, providing further evidence for the critical nature of the phase.

quant-ph↗
arXiv2025

Statistical inference of anomalous thermal transport with uncertainty quantification for interpretive 2-D SOL models

The critical task of inferring anomalous cross-field transport coefficients is addressed in simulations of boundary plasmas with fluid models. A workflow for parameter inference in the UEDGE fluid code is developed using Bayesian optimization with parallelized sampling and integrated uncertainty quantification. In this workflow, transport coefficients are inferred by maximizing their posterior probability distribution, which is generally multidimensional and non-Gaussian. Uncertainty quantification is integrated throughout the optimization within the Bayesian framework that combines diagnostic uncertainties and model limitations. As a concrete example, we infer the anomalous electron thermal diffusivity $χ_\perp$ from an interpretive 2-D model describing electron heat transport in the conduction-limited region with radiative power loss. The workflow is first benchmarked against synthetic data and then tested on H-, L-, and I-mode discharges to match their midplane temperature and divertor heat flux profiles. We demonstrate that the workflow efficiently infers diffusivity and its associated uncertainty, generating 2-D profiles that match 1-D measurements. Future efforts will focus on incorporating more complicated fluid models and analyzing transport coefficients inferred from a large database of experimental results.

physics.plasm-ph↗
arXiv2025

UniTEX: Universal High Fidelity Generative Texturing for 3D Shapes

We present UniTEX, a novel two-stage 3D texture generation framework to create high-quality, consistent textures for 3D assets. Existing approaches predominantly rely on UV-based inpainting to refine textures after reprojecting the generated multi-view images onto the 3D shapes, which introduces challenges related to topological ambiguity. To address this, we propose to bypass the limitations of UV mapping by operating directly in a unified 3D functional space. Specifically, we first propose that lifts texture generation into 3D space via Texture Functions (TFs)--a continuous, volumetric representation that maps any 3D point to a texture value based solely on surface proximity, independent of mesh topology. Then, we propose to predict these TFs directly from images and geometry inputs using a transformer-based Large Texturing Model (LTM). To further enhance texture quality and leverage powerful 2D priors, we develop an advanced LoRA-based strategy for efficiently adapting large-scale Diffusion Transformers (DiTs) for high-quality multi-view texture synthesis as our first stage. Extensive experiments demonstrate that UniTEX achieves superior visual quality and texture integrity compared to existing approaches, offering a generalizable and scalable solution for automated 3D texture generation. Code will available in: https://github.com/YixunLiang/UniTEX.

cs.CV↗
arXiv2025

Skip-Thinking: Chunk-wise Chain-of-Thought Distillation Enable Smaller Language Models to Reason Better and Faster

Chain-of-thought (CoT) distillation allows a large language model (LLM) to guide a small language model (SLM) in reasoning tasks. Existing methods train the SLM to learn the long rationale in one iteration, resulting in two issues: 1) Long rationales lead to a large token-level batch size during training, making gradients of core reasoning tokens (i.e., the token will directly affect the correctness of subsequent reasoning) over-smoothed as they contribute a tiny fraction of the rationale. As a result, the SLM converges to sharp minima where it fails to grasp the reasoning logic. 2) The response is slow, as the SLM must generate a long rationale before reaching the answer. Therefore, we propose chunk-wise training (CWT), which uses a heuristic search to divide the rationale into internal semantically coherent chunks and focuses SLM on learning from only one chunk per iteration. In this way, CWT naturally isolates non-reasoning chunks that do not involve the core reasoning token (e.g., summary and transitional chunks) from the SLM learning for reasoning chunks, making the fraction of the core reasoning token increase in the corresponding iteration. Based on CWT, skip-thinking training (STT) is proposed. STT makes the SLM automatically skip non-reasoning medium chunks to reach the answer, improving reasoning speed while maintaining accuracy. We validate our approach on a variety of SLMs and multiple reasoning tasks.

cs.CL↗
arXiv2025

Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets

While generative artificial intelligence has advanced significantly across text, image, audio, and video domains, 3D generation remains comparatively underdeveloped due to fundamental challenges such as data scarcity, algorithmic limitations, and ecosystem fragmentation. To this end, we present Step1X-3D, an open framework addressing these challenges through: (1) a rigorous data curation pipeline processing >5M assets to create a 2M high-quality dataset with standardized geometric and textural properties; (2) a two-stage 3D-native architecture combining a hybrid VAE-DiT geometry generator with an diffusion-based texture synthesis module; and (3) the full open-source release of models, training code, and adaptation modules. For geometry generation, the hybrid VAE-DiT component produces TSDF representations by employing perceiver-based latent encoding with sharp edge sampling for detail preservation. The diffusion-based texture synthesis module then ensures cross-view consistency through geometric conditioning and latent-space synchronization. Benchmark results demonstrate state-of-the-art performance that exceeds existing open-source methods, while also achieving competitive quality with proprietary solutions. Notably, the framework uniquely bridges the 2D and 3D generation paradigms by supporting direct transfer of 2D control techniques~(e.g., LoRA) to 3D synthesis. By simultaneously advancing data quality, algorithmic fidelity, and reproducibility, Step1X-3D aims to establish new standards for open research in controllable 3D asset generation.

cs.CV↗
arXiv2025

FIRM: Flexible Interactive Reflection reMoval

Removing reflection from a single image is challenging due to the absence of general reflection priors. Although existing methods incorporate extensive user guidance for satisfactory performance, they often lack the flexibility to adapt user guidance in different modalities, and dense user interactions further limit their practicality. To alleviate these problems, this paper presents FIRM, a novel framework for Flexible Interactive image Reflection reMoval with various forms of guidance, where users can provide sparse visual guidance (e.g., points, boxes, or strokes) or text descriptions for better reflection removal. Firstly, we design a novel user guidance conversion module (UGC) to transform different forms of guidance into unified contrastive masks. The contrastive masks provide explicit cues for identifying reflection and transmission layers in blended images. Secondly, we devise a contrastive mask-guided reflection removal network that comprises a newly proposed contrastive guidance interaction block (CGIB). This block leverages a unique cross-attention mechanism that merges contrastive masks with image features, allowing for precise layer separation. The proposed framework requires only 10\% of the guidance time needed by previous interactive methods, which makes a step-change in flexibility. Extensive results on public real-world reflection removal datasets validate that our method demonstrates state-of-the-art reflection removal performance. Code is avaliable at https://github.com/ShawnChenn/FlexibleReflectionRemoval.

cs.CV↗
arXiv2025

Learning Humanoid Standing-up Control across Diverse Postures

Standing-up control is crucial for humanoid robots, with the potential for integration into current locomotion and loco-manipulation systems, such as fall recovery. Existing approaches are either limited to simulations that overlook hardware constraints or rely on predefined ground-specific motion trajectories, failing to enable standing up across postures in real-world scenes. To bridge this gap, we present HoST (Humanoid Standing-up Control), a reinforcement learning framework that learns standing-up control from scratch, enabling robust sim-to-real transfer across diverse postures. HoST effectively learns posture-adaptive motions by leveraging a multi-critic architecture and curriculum-based training on diverse simulated terrains. To ensure successful real-world deployment, we constrain the motion with smoothness regularization and implicit motion speed bound to alleviate oscillatory and violent motions on physical hardware, respectively. After simulation-based training, the learned control policies are directly deployed on the Unitree G1 humanoid robot. Our experimental results demonstrate that the controllers achieve smooth, stable, and robust standing-up motions across a wide range of laboratory and outdoor environments. Videos and code are available at https://taohuang13.github.io/humanoid-standingup.github.io/.

cs.RO↗
arXiv2025

Systems of curves on non-orientable surfaces

We show that the order of the cardinality of maximal complete $1$-systems of loops on non-orientable surfaces is $\sim |χ|^{2}$. In particular, we determine the exact cardinality of maximal complete $1$-systems of loops on punctured projective planes. To prove these results, we show that the cardinality of maximal systems of arcs pairwise-intersecting at most once on a non-orientable surface is $2|χ|(|χ|+1)$.

math.GT↗
arXiv2025

Broad-band noises in GX 339-4 during the 2021 outburst observed with Insight-HXMT and NICER

Rapid X-ray variability of GX 339$-$4 including the low-frequency quasi-periodic oscillations (LFQPOs) and broad-band noises have been observed with the Hard X-ray Modulation Telescope (\textit{Insight}-HXMT) and Neutron star Interior Composition Explorer (\textit {NICER}) during the 2021 outburst. Here we present a systematic study of the evolution and energy dependence properties of such broad-band noises (BBN). The outburst from February to March of 2021 can be divided into three stages: the low hard state (LHS), the hard intermediate state (HIMS) and soft intermediate state (SIMS). In the PDSs of the LHS and HIMS, the broad-band noises are well fitted with three Lorentzian components: a low-frequency component $L_1$, a middle-frequency component $L_2$ and a high-frequency component $L_3$. The increasing trend of the characteristic frequencies for $L_1$ and $L_2$ and the relation between the QPO frequency and characteristic BBN frequency are reported. We found that the energies corresponding to the peaks and shapes of the rms spectra for three BBN components are different. The comparison among three BBN components indicates that energy-dominant bands of these BBN components are distinct. Our results can be explained with the truncated disc/hot flow model with a large variable disc and a small hot inner flow. A possible description of the accretion structure and its evolution from the LHS to the SIMS is proposed. Further research is still required to probe such accretion structure in GX 339--4.

astro-ph.HE↗
arXiv2025

Retrieval-augmented Few-shot Medical Image Segmentation with Foundation Models

Medical image segmentation is crucial for clinical decision-making, but the scarcity of annotated data presents significant challenges. Few-shot segmentation (FSS) methods show promise but often require training on the target domain and struggle to generalize across different modalities. Similarly, adapting foundation models like the Segment Anything Model (SAM) for medical imaging has limitations, including the need for finetuning and domain-specific adaptation. To address these issues, we propose a novel method that adapts DINOv2 and Segment Anything Model 2 (SAM 2) for retrieval-augmented few-shot medical image segmentation. Our approach uses DINOv2's feature as query to retrieve similar samples from limited annotated data, which are then encoded as memories and stored in memory bank. With the memory attention mechanism of SAM 2, the model leverages these memories as conditions to generate accurate segmentation of the target image. We evaluated our framework on three medical image segmentation tasks, demonstrating superior performance and generalizability across various modalities without the need for any retraining or finetuning. Overall, this method offers a practical and effective solution for few-shot medical image segmentation and holds significant potential as a valuable annotation tool in clinical applications.

cs.CV↗
arXiv2025

Adapting Vision Foundation Models for Real-time Ultrasound Image Segmentation

We propose a novel approach that adapts hierarchical vision foundation models for real-time ultrasound image segmentation. Existing ultrasound segmentation methods often struggle with adaptability to new tasks, relying on costly manual annotations, while real-time approaches generally fail to match state-of-the-art performance. To overcome these limitations, we introduce an adaptive framework that leverages the vision foundation model Hiera to extract multi-scale features, interleaved with DINOv2 representations to enhance visual expressiveness. These enriched features are then decoded to produce precise and robust segmentation. We conduct extensive evaluations on six public datasets and one in-house dataset, covering both cardiac and thyroid ultrasound segmentation. Experiments show that our approach outperforms state-of-the-art methods across multiple datasets and excels with limited supervision, surpassing nnUNet by over 20\% on average in the 1\% and 10\% data settings. Our method achieves $\sim$77 FPS inference speed with TensorRT on a single GPU, enabling real-time clinical applications.

cs.CV↗
arXiv2025

Leveraging Diffusion Model and Image Foundation Model for Improved Correspondence Matching in Coronary Angiography

Accurate correspondence matching in coronary angiography images is crucial for reconstructing 3D coronary artery structures, which is essential for precise diagnosis and treatment planning of coronary artery disease (CAD). Traditional matching methods for natural images often fail to generalize to X-ray images due to inherent differences such as lack of texture, lower contrast, and overlapping structures, compounded by insufficient training data. To address these challenges, we propose a novel pipeline that generates realistic paired coronary angiography images using a diffusion model conditioned on 2D projections of 3D reconstructed meshes from Coronary Computed Tomography Angiography (CCTA), providing high-quality synthetic data for training. Additionally, we employ large-scale image foundation models to guide feature aggregation, enhancing correspondence matching accuracy by focusing on semantically relevant regions and keypoints. Our approach demonstrates superior matching performance on synthetic datasets and effectively generalizes to real-world datasets, offering a practical solution for this task. Furthermore, our work investigates the efficacy of different foundation models in correspondence matching, providing novel insights into leveraging advanced image foundation models for medical imaging applications.

cs.CV↗
arXiv2025

DiffDenoise: Self-Supervised Medical Image Denoising with Conditional Diffusion Models

Many self-supervised denoising approaches have been proposed in recent years. However, these methods tend to overly smooth images, resulting in the loss of fine structures that are essential for medical applications. In this paper, we propose DiffDenoise, a powerful self-supervised denoising approach tailored for medical images, designed to preserve high-frequency details. Our approach comprises three stages. First, we train a diffusion model on noisy images, using the outputs of a pretrained Blind-Spot Network as conditioning inputs. Next, we introduce a novel stabilized reverse sampling technique, which generates clean images by averaging diffusion sampling outputs initialized with a pair of symmetric noises. Finally, we train a supervised denoising network using noisy images paired with the denoised outputs generated by the diffusion model. Our results demonstrate that DiffDenoise outperforms existing state-of-the-art methods in both synthetic and real-world medical image denoising tasks. We provide both a theoretical foundation and practical insights, demonstrating the method's effectiveness across various medical imaging modalities and anatomical structures.

eess.IV↗
arXiv2025

Free fermions under adaptive quantum dynamics

We study free fermion systems under adaptive quantum dynamics consisting of unitary gates and projective measurements followed by corrective unitary operations. We further introduce a classical flag for each site, allowing for an active or inactive status which determines whether or not the unitary gates are allowed to apply. In this dynamics, the individual quantum trajectories exhibit a measurement-induced entanglement transition from critical to area-law scaling above a critical measurement rate, similar to previously studied models of free fermions under continuous monitoring. Furthermore, we find that the corrective unitary operations can steer the system into a state characterized by charge-density-wave order. Consequently, an additional phase transition occurs, which can be observed at both the level of the quantum trajectory and the quantum channel. We establish that the entanglement transition and the steering transition are fundamentally distinct. The latter transition belongs to the parity-conserving (PC) universality class, arising from the interplay between the inherent fermionic parity and classical labelling. We demonstrate both the entanglement and the steering transitions via efficient numerical simulations of free fermion systems, which confirm the PC universality class of the latter.

quant-ph↗
arXiv2025

Reducing CT Metal Artifacts by Learning Latent Space Alignment with Gemstone Spectral Imaging Data

Metal artifacts in CT slices have long posed challenges in medical diagnostics. These artifacts degrade image quality, resulting in suboptimal visualization and complicating the accurate interpretation of tissues adjacent to metal implants. To address these issues, we introduce the Latent Gemstone Spectral Imaging (GSI) Alignment Framework, which effectively reduces metal artifacts while avoiding the introduction of noise information. Our work is based on a key finding that even artifact-affected ordinary CT sequences contain sufficient information to discern detailed structures. The challenge lies in the inability to clearly represent this information. To address this issue, we developed an Alignment Framework that adjusts the representation of ordinary CT images to match GSI CT sequences. GSI is an advanced imaging technique using multiple energy levels to mitigate artifacts caused by metal implants. By aligning the representation to GSI data, we can effectively suppress metal artifacts while clearly revealing detailed structure, without introducing extraneous information into CT sequences. To facilitate the application, we propose a new dataset, Artifacts-GSI, captured from real patients with metal implants, and establish a new benchmark based on this dataset. Experimental results show that our method significantly reduces metal artifacts and greatly enhances the readability of CT slices. All our code and data are available at: https://um-lab.github.io/GSI-MAR/

cs.CV↗
arXiv2025

EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions

GPT-4o, an omni-modal model that enables vocal conversations with diverse emotions and tones, marks a milestone for omni-modal foundation models. However, empowering Large Language Models to perceive and generate images, texts, and speeches end-to-end with publicly available data remains challenging for the open-source community. Existing vision-language models rely on external tools for speech processing, while speech-language models still suffer from limited or totally without vision-understanding capabilities. To address this gap, we propose the EMOVA (EMotionally Omni-present Voice Assistant), to enable Large Language Models with end-to-end speech abilities while maintaining the leading vision-language performance. With a semantic-acoustic disentangled speech tokenizer, we surprisingly notice that omni-modal alignment can further enhance vision-language and speech abilities compared with the bi-modal aligned counterparts. Moreover, a lightweight style module is introduced for the flexible speech style controls including emotions and pitches. For the first time, EMOVA achieves state-of-the-art performance on both the vision-language and speech benchmarks, and meanwhile, supporting omni-modal spoken dialogue with vivid emotions.

cs.CV↗