arXiv subjects

Cheng Xu

Publications and source records attributed to Cheng Xu.

At least 37 records · Page 2Linked to original sources

arXiv2026

COLE$^+$: Towards Practical Column-based Learned Storage for Blockchain Systems

Blockchain provides a decentralized and tamper-resistant ledger for securely recording transactions across a network of untrusted nodes. While its transparency and integrity are beneficial, the substantial storage requirements for maintaining a complete transaction history present significant challenges. For example, Ethereum nodes require around 23TB of storage, with an annual growth rate of 4TB. Prior studies have employed various strategies to mitigate the storage challenges. Notably, COLE significantly reduces storage size and improves throughput by adopting a column-based design that incorporates a learned index, effectively eliminating data duplication in the storage layer. However, this approach has limitations in supporting chain reorganization during blockchain forks and state pruning to minimize storage overhead. In this paper, we propose COLE$^+$, an enhanced storage solution designed to address these limitations. COLE$^+$ incorporates a novel rewind-supported in-memory tree structure for handling chain reorganization, leveraging content-defined chunking (CDC) to maintain a consistent hash digest for each block. For on-disk storage, a new two-level Merkle Hash Tree (MHT) structure, called prunable version tree, is developed to facilitate efficient state pruning. Both theoretical and empirical analyses show the effectiveness of COLE$^+$ and its potential for practical application in real-world blockchain systems.

cs.DB↗

arXiv2026

Hydrostatic Pressure-enhanced correlated magnetism and Chern insulator in moir'e WSe2

Moiré semiconductors offer flat bands where Coulomb interactions and band topology intertwine, while interlayer coupling plays a central role in forming the moiré potential. However, limited interlayer coupling strength and the lack of efficient tuning methods hinder further exploration of correlated phenomena in moiré semiconductors. Here we introduce a cryogenic dual-gated diamond-anvil platform using helium as a pressure medium, enabling reversible hydrostatic tuning together with magneto-optical spectroscopy in twisted bilayer WSe2. Pressure enhances the moiré potential, redshifts excitons, and stabilizes Stoner ferromagnetism otherwise absent at a 3.1-degree twist. Simultaneously, the half-filled C = 1 Chern insulating state strengthens, exhibiting a reduced saturation field. Moreover, we observe a topological phase transition from a Chern insulator to a Mott insulator at around 2 GPa. First-principles calculations reveal that a Gamma-to-K valence-band-maximum switching drives this transition by converting an Ising-like topological K-valley miniband into a spin-degenerate trivial Gamma miniband. Our findings demonstrate hydrostatic pressure as a powerful, continuous control axis for correlated magnetism and topological band engineering in moiré materials.

cond-mat.mtrl-sci↗

arXiv2025

From fractional Chern insulators to topological electronic crystals in moiré MoTe2: quantum geometry tuning via remote layer

The quantum geometry of Bloch wavefunctions,encoded in the Berry curvature and quantum metric, is believed to be a decisive ingredient in stabilizing fractional quantum anomalous Hall (FQAH) effect(i.e., fractional Chern insulator, FCI, at zero magnetic field), against competing symmetry-breaking phases.A direct experimental demonstration of quantum geometry-driven switching between distinct correlated topological phases, however, has been lacking. Here, we report experimental evidence of such a switch in a high-quality 3.7 twisted MoTe2 (tMoTe2) device consisting of both A-A bilayer and A-AB trilayer regions. While composite Fermi liquid CFL/FQAH phases are established in A-A tMoTe2,the A-AB region-effectively an A-A moire bilayer proximitized by a remote B layer-develops a series of topological electronic crystal (TEC, also referred to as generalized QAH crystal, QAHC) states with integer quantized Hall conductance at commensurate fractional fillings v=1/2, 2/3, and an incommensurate filling factor v=0.53.The electrostatic phase diagram is mapped out by combined transport and optical measurements, showing that these TEC states emerge within the first moir'e valence band prior to any charge transfer to the B layer. Exact diagonalization (ED) incorporating the remote-layer-induced intralayer potential demonstrates a transition from a CFL-like manifold in the A-A limit to a Chern number C=1 ground-state consistent with a TEC at v=1/2 , accompanied by the further breakdown of ideal band geometry. Our results provide experimental evidence of quantum geometry-tuned competition between FQAH/CFL and TEC phases in a moiré Chern band and pave the way for further exploring correlation-driven topological phenomena by tuning quantum geometry.

cond-mat.mes-hall↗

arXiv2025

Beyond Inference Intervention: Identity-Decoupled Diffusion for Face Anonymization

Face anonymization aims to conceal identity information while preserving non-identity attributes. Mainstream diffusion models rely on inference-time interventions such as negative guidance or energy-based optimization, which are applied post-training to suppress identity features. These interventions often introduce distribution shifts and entangle identity with non-identity attributes, degrading visual fidelity and data utility. To address this, we propose \textbf{ID\textsuperscript{2}Face}, a training-centric anonymization framework that removes the need for inference-time optimization. The rationale of our method is to learn a structured latent space where identity and non-identity information are explicitly disentangled, enabling direct and controllable anonymization at inference. To this end, we design a conditional diffusion model with an identity-masked learning scheme. An Identity-Decoupled Latent Recomposer uses an Identity Variational Autoencoder to model identity features, while non-identity attributes are extracted from same-identity pairs and aligned through bidirectional latent alignment. An Identity-Guided Latent Harmonizer then fuses these representations via soft-gating conditioned on noisy feature prediction. The model is trained with a recomposition-based reconstruction loss to enforce disentanglement. At inference, anonymization is achieved by sampling a random identity vector from the learned identity space. To further suppress identity leakage, we introduce an Orthogonal Identity Mapping strategy that enforces orthogonality between sampled and source identity vectors. Experiments demonstrate that ID\textsuperscript{2}Face outperforms existing methods in visual quality, identity suppression, and utility preservation.

cs.CV↗

arXiv2025

NTIRE 2025 Challenge on Low Light Image Enhancement: Methods and Results

This paper presents a comprehensive review of the NTIRE 2025 Low-Light Image Enhancement (LLIE) Challenge, highlighting the proposed solutions and final outcomes. The objective of the challenge is to identify effective networks capable of producing brighter, clearer, and visually compelling images under diverse and challenging conditions. A remarkable total of 762 participants registered for the competition, with 28 teams ultimately submitting valid entries. This paper thoroughly evaluates the state-of-the-art advancements in LLIE, showcasing the significant progress.

cs.CV↗

arXiv2025

ProstaTD: Bridging Surgical Triplet from Classification to Fully Supervised Detection

Surgical triplet detection is a critical task in surgical video analysis. However, existing datasets like CholecT50 lack precise spatial bounding box annotations, rendering triplet classification at the image level insufficient for practical applications. The inclusion of bounding box annotations is essential to make this task meaningful, as they provide the spatial context necessary for accurate analysis and improved model generalizability. To address these shortcomings, we introduce ProstaTD, a large-scale, multi-institutional dataset for surgical triplet detection, developed from the technically demanding domain of robot-assisted prostatectomy. ProstaTD offers clinically defined temporal boundaries and high-precision bounding box annotations for each structured triplet activity. The dataset comprises 71,775 video frames and 196,490 annotated triplet instances, collected from 21 surgeries performed across multiple institutions, reflecting a broad range of surgical practices and intraoperative conditions. The annotation process was conducted under rigorous medical supervision and involved more than 60 contributors, including practicing surgeons and medically trained annotators, through multiple iterative phases of labeling and verification. To further facilitate future general-purpose surgical annotation, we developed two tailored labeling tools to improve efficiency and scalability in our annotation workflows. In addition, we created a surgical triplet detection evaluation toolkit that enables standardized and reproducible performance assessment across studies. ProstaTD is the largest and most diverse surgical triplet dataset to date, moving the field from simple classification to full detection with precise spatial and temporal boundaries and thereby providing a robust foundation for fair benchmarking.

cs.CV↗

arXiv2025

StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Models

The advancement of diffusion models has enhanced the realism of AI-generated content but also raised concerns about misuse, necessitating robust copyright protection and tampering localization. Although recent methods have made progress toward unified solutions, their reliance on post hoc processing introduces considerable application inconvenience and compromises forensic reliability. We propose StableGuard, a novel framework that seamlessly integrates a binary watermark into the diffusion generation process, ensuring copyright protection and tampering localization in Latent Diffusion Models through an end-to-end design. We develop a Multiplexing Watermark VAE (MPW-VAE) by equipping a pretrained Variational Autoencoder (VAE) with a lightweight latent residual-based adapter, enabling the generation of paired watermarked and watermark-free images. These pairs, fused via random masks, create a diverse dataset for training a tampering-agnostic forensic network. To further enhance forensic synergy, we introduce a Mixture-of-Experts Guided Forensic Network (MoE-GFN) that dynamically integrates holistic watermark patterns, local tampering traces, and frequency-domain cues for precise watermark verification and tampered region detection. The MPW-VAE and MoE-GFN are jointly optimized in a self-supervised, end-to-end manner, fostering a reciprocal training between watermark embedding and forensic accuracy. Extensive experiments demonstrate that StableGuard consistently outperforms state-of-the-art methods in image fidelity, watermark verification, and tampering localization.

cs.CV↗

arXiv2025

DCR: Quantifying Data Contamination in LLMs Evaluation

The rapid advancement of large language models (LLMs) has heightened concerns about benchmark data contamination (BDC), where models inadvertently memorize evaluation data during the training process, inflating performance metrics, and undermining genuine generalization assessment. This paper introduces the Data Contamination Risk (DCR) framework, a lightweight, interpretable pipeline designed to detect and quantify BDC risk across four granular levels: semantic, informational, data, and label. By synthesizing contamination scores via a fuzzy inference system, DCR produces a unified DCR Factor that adjusts raw accuracy to reflect contamination-aware performance. Validated on 9 LLMs (0.5B-72B) across sentiment analysis, fake news detection, and arithmetic reasoning tasks, the DCR framework reliably diagnoses contamination severity and with accuracy adjusted using the DCR Factor to within 4% average error across the three benchmarks compared to the uncontaminated baseline. Emphasizing computational efficiency and transparency, DCR provides a practical tool for integrating contamination assessment into routine evaluations, fostering fairer comparisons and enhancing the credibility of LLM benchmarking practices.

cs.CL↗

arXiv2025

Think2Sing: Orchestrating Structured Motion Subtitles for Singing-Driven 3D Head Animation

Singing-driven 3D head animation is a challenging yet promising task with applications in virtual avatars, entertainment, and education. Unlike speech, singing involves richer emotional nuance, dynamic prosody, and lyric-based semantics, requiring the synthesis of fine-grained, temporally coherent facial motion. Existing speech-driven approaches often produce oversimplified, emotionally flat, and semantically inconsistent results, which are insufficient for singing animation. To address this, we propose Think2Sing, a diffusion-based framework that leverages pretrained large language models to generate semantically coherent and temporally consistent 3D head animations, conditioned on both lyrics and acoustics. A key innovation is the introduction of motion subtitles, an auxiliary semantic representation derived through a novel Singing Chain-of-Thought reasoning process combined with acoustic-guided retrieval. These subtitles contain precise timestamps and region-specific motion descriptions, serving as interpretable motion priors. We frame the task as a motion intensity prediction problem, enabling finer control over facial regions and improving the modeling of expressive motion. To support this, we create a multimodal singing dataset with synchronized video, acoustic descriptors, and motion subtitles, enabling diverse and expressive motion learning. Extensive experiments show that Think2Sing outperforms state-of-the-art methods in realism, expressiveness, and emotional fidelity, while also offering flexible, user-controllable animation editing.

cs.GR↗

arXiv2025

StarPose: 3D Human Pose Estimation via Spatial-Temporal Autoregressive Diffusion

Monocular 3D human pose estimation remains a challenging task due to inherent depth ambiguities and occlusions. Compared to traditional methods based on Transformers or Convolutional Neural Networks (CNNs), recent diffusion-based approaches have shown superior performance, leveraging their probabilistic nature and high-fidelity generation capabilities. However, these methods often fail to account for the spatial and temporal correlations across predicted frames, resulting in limited temporal consistency and inferior accuracy in predicted 3D pose sequences. To address these shortcomings, this paper proposes StarPose, an autoregressive diffusion framework that effectively incorporates historical 3D pose predictions and spatial-temporal physical guidance to significantly enhance both the accuracy and temporal coherence of pose predictions. Unlike existing approaches, StarPose models the 2D-to-3D pose mapping as an autoregressive diffusion process. By synergically integrating previously predicted 3D poses with 2D pose inputs via a Historical Pose Integration Module (HPIM), the framework generates rich and informative historical pose embeddings that guide subsequent denoising steps, ensuring temporally consistent predictions. In addition, a fully plug-and-play Spatial-Temporal Physical Guidance (STPG) mechanism is tailored to refine the denoising process in an iterative manner, which further enforces spatial anatomical plausibility and temporal motion dynamics, rendering robust and realistic pose estimates. Extensive experiments on benchmark datasets demonstrate that StarPose outperforms state-of-the-art methods, achieving superior accuracy and temporal consistency in 3D human pose estimation. Code is available at https://github.com/wileychan/StarPose.

cs.CV↗

arXiv2025

SCJD: Sparse Correlation and Joint Distillation for Efficient 3D Human Pose Estimation

Existing 3D Human Pose Estimation (HPE) methods achieve high accuracy but suffer from computational overhead and slow inference, while knowledge distillation methods fail to address spatial relationships between joints and temporal correlations in multi-frame inputs. In this paper, we propose Sparse Correlation and Joint Distillation (SCJD), a novel framework that balances efficiency and accuracy for 3D HPE. SCJD introduces Sparse Correlation Input Sequence Downsampling to reduce redundancy in student network inputs while preserving inter-frame correlations. For effective knowledge transfer, we propose Dynamic Joint Spatial Attention Distillation, which includes Dynamic Joint Embedding Distillation to enhance the student's feature representation using the teacher's multi-frame context feature, and Adjacent Joint Attention Distillation to improve the student network's focus on adjacent joint relationships for better spatial understanding. Additionally, Temporal Consistency Distillation aligns the temporal correlations between teacher and student networks through upsampling and global supervision. Extensive experiments demonstrate that SCJD achieves state-of-the-art performance. Code is available at https://github.com/wileychan/SCJD.

cs.CV↗

arXiv2025

Taming Vision-Language Models for Medical Image Analysis: A Comprehensive Review

Modern Vision-Language Models (VLMs) exhibit unprecedented capabilities in cross-modal semantic understanding between visual and textual modalities. Given the intrinsic need for multi-modal integration in clinical applications, VLMs have emerged as a promising solution for a wide range of medical image analysis tasks. However, adapting general-purpose VLMs to medical domain poses numerous challenges, such as large domain gaps, complicated pathological variations, and diversity and uniqueness of different tasks. The central purpose of this review is to systematically summarize recent advances in adapting VLMs for medical image analysis, analyzing current challenges, and recommending promising yet urgent directions for further investigations. We begin by introducing core learning strategies for medical VLMs, including pretraining, fine-tuning, and prompt learning. We then categorize five major VLM adaptation strategies for medical image analysis. These strategies are further analyzed across eleven medical imaging tasks to illustrate their current practical implementations. Furthermore, we analyze key challenges that impede the effective adaptation of VLMs to clinical applications and discuss potential directions for future research. We also provide an open-access repository of related literature to facilitate further research, available at https://github.com/haonenglin/Awesome-VLM-for-MIA. It is anticipated that this article can help researchers who are interested in harnessing VLMs in medical image analysis tasks have a better understanding on their capabilities and limitations, as well as current technical barriers, to promote their innovative, robust, and safe application in clinical practice.

eess.IV↗

arXiv2025

Finite-momentum superconductivity from chiral bands in twisted MoTe$_2$

A recent experiment has reported unconventional superconductivity in twisted bilayer MoTe$_2$, emerging from a normal state that exhibits a finite anomalous Hall effect -- a signature of intrinsic chirality. Motivated by this discovery, we construct a continuum model for twisted MoTe$_2$ constrained by lattice symmetries from first-principles calculations that captures the moiré-induced inversion symmetry breaking even in the absence of a displacement field. Building on this model, we show that repulsive interactions give rise to finite-momentum superconductivity via the Kohn-Luttinger mechanism in this chiral moiré system. Remarkably, the finite-momentum superconducting state can arise solely from internal symmetry breaking of the moiré superlattice, differentiating it from previously studied cases that require external fields. It further features a nonreciprocal quasiparticle dispersion and an intrinsic superconducting diode effect. Our results highlight a novel route to unconventional superconducting states in twisted transition metal dichalcogenides moiré systems, driven entirely by intrinsic symmetry-breaking effects.

cond-mat.supr-con↗

arXiv2025

Scalable Complexity Control Facilitates Reasoning Ability of LLMs

The reasoning ability of large language models (LLMs) has been rapidly advancing in recent years, attracting interest in more fundamental approaches that can reliably enhance their generalizability. This work demonstrates that model complexity control, conveniently implementable by adjusting the initialization rate and weight decay coefficient, improves the scaling law of LLMs consistently over varying model sizes and data sizes. This gain is further illustrated by comparing the benchmark performance of 2.4B models pretrained on 1T tokens with different complexity hyperparameters. Instead of fixing the initialization std, we found that a constant initialization rate (the exponent of std) enables the scaling law to descend faster in both model and data sizes. These results indicate that complexity control is a promising direction for the continual advancement of LLMs.

cs.LG↗

arXiv2025

PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy

This paper introduces PreP-OCR, a two-stage pipeline that combines document image restoration with semantic-aware post-OCR correction to enhance both visual clarity and textual consistency, thereby improving text extraction from degraded historical documents. First, we synthesize document-image pairs from plaintext, rendering them with diverse fonts and layouts and then applying a randomly ordered set of degradation operations. An image restoration model is trained on this synthetic data, using multi-directional patch extraction and fusion to process large images. Second, a ByT5 post-OCR model, fine-tuned on synthetic historical text pairs, addresses remaining OCR errors. Detailed experiments on 13,831 pages of real historical documents in English, French, and Spanish show that the PreP-OCR pipeline reduces character error rates by 63.9-70.3% compared to OCR on raw images. Our pipeline demonstrates the potential of integrating image restoration with linguistic error correction for digitizing historical archives.

cs.CL↗

arXiv2025

Evidence of competing ground states between fractional Chern insulator and antiferromagnetism in moiré MoTe2

Two-dimensional moire materials present unprecedented opportunities to explore quantum phases of matter arising from the interplay of band topology and strong correlations.One of the most striking examples is the recent observation of fractional quantum anomalous Hall (FQAH) effect in twisted bilayer MoTe$_2$ (tMoTe2) with relatively large twist angles(~3.7deg-3.9deg). The electronic ground states are usually expected to be sensitive to the twist angle, as the twist angle determines the electron bandwidth and correlation strength in the moire system. Here, we report the observation of unexpected competing magnetic ground states in tMoTe2 moire superlattice, on which balance can be tipped by both twist angle and electric field (E). Specifically, we observed anomalous antiferromagnetic (AFM) ground states with zero Hall resistance at both v_h=1 and 2/3, at intermediate twist angles ~3deg. The AFM orders are suppressed by applying vertical E, and emergent ferromagnetism accompanied by integer Chern insulator (ICI) or fractional Chern insulator (FCI) states are observed near the critical E (E_c) of moire superlattice symmetry transition. Our results demonstrate tMoTe2 as a fascinating platform for exploring unexpected correlated phases with nontrivial topology and fractional excitations and point to electric-field-controlled ultralow-power spin-valleytronic devices.

cond-mat.mes-hall↗

arXiv2025

Grey-Box Fuzzing in Constrained Ultra-Large Systems: Lessons for SE Community

Testing ultra-large microservices-based FinTech systems presents significant challenges, including restricted access to production environments, complex dependencies, and stringent security constraints. We propose SandBoxFuzz, a scalable grey-box fuzzing technique that addresses these limitations by leveraging aspect-oriented programming and runtime reflection to enable dynamic specification mining, generating targeted inputs for constrained environments. SandBoxFuzz also introduces a log-based coverage mechanism, seamlessly integrated into the build pipeline, eliminating the need for runtime coverage agents that are often infeasible in industrial settings. SandBoxFuzz has been successfully deployed to Ant Group's production line and, compared to an initial solution built on a state-of-the-art fuzzing framework, it demonstrates superior performance in their microservices software. SandBoxFuzz achieves a 7.5% increase in branch coverage, identifies 1,850 additional exceptions, and reduces setup time from hours to minutes, highlighting its effectiveness and practical utility in a real-world industrial environment. By open-sourcing SandBoxFuzz, we provide a practical and effective tool for researchers and practitioners to test large-scale microservices systems.

cs.SE↗

arXiv2025

Universal giant spin Hall effect in moire metal

While moiré phenomena have been extensively studied in low-carrier-density systems such as graphene and semiconductors, their implications for metallic systems with large Fermi surfaces remain largely unexplored. Using GPU-accelerated large-scale ab-initio quantum transport simulations, we investigate spin transport in two distinct platforms: twisted bilayer MoTe$_2$ (semiconductor, from lightly to heavily doping) and NbX$_2$ ($X$ = S, Se; metals). In twisted MoTe$_2$, the spin Hall conductivity (SHC) evolves from $4\tfrac{e}{4π}$ at $5.09^\circ$ to $10\tfrac{e}{4π}$ at $1.89^\circ$, driven by the emergence of multiple isolated Chern bands. Remarkably, in heavily doped metallic regimes--without isolated Chern bands--we observe a universal amplification of the spin Hall effect from Fermi surface reconstruction under long-wavelength potential, with the peak SHC tripling from $6\tfrac{e}{4π}$ at $5.09^\circ$ to $17\tfrac{e}{4π}$ at $3.89^\circ$. For prototypical moiré metals like twisted NbX$_2$, we identify a record SHC of $-17\tfrac{e}{4π}$ (-5200 $(\hbar / e)S/cm$ in 3D units), surpassing all known bulk materials. These results establish moiré engineering as a powerful strategy for enhancing spin-dependent transport, and advancing ab-initio methodologies to bridge atomic-scale precision with device-scale predictions in transport simulations.

cond-mat.mes-hall↗