Searcharxiv⌕ Search

arXiv subjects

Zhuo Zhang

Publications and source records attributed to Zhuo Zhang.

At least 37 records · Page 2Linked to original sources
arXiv2026

VDSB-GWSyn: Diffusion Schrödinger Bridge for Controllable and Anatomically Feasible Guidewire Synthesis in Coronary Angiography

Coronary guidewire endpoint localization is a fundamental capability for computer-assisted PCI, and its importance increases as robot-assisted PCI is progressively adopted to reduce operator radiation exposure. However, the scarcity of annotated CAG images with guidewires and the limited adaptability of existing guidewire synthesis models remain key bottlenecks for guidewire endpoint localization. To address this issue, we propose VDSB-GWSyn, a Diffusion Schrödinger Bridge (DSB) model-based framework, enabling synthesis of controllable, high-fidelity guidewire samples under complex anatomical backgrounds. VDSB-GWSyn first uses our shape prior algorithm to learn the basic guidewire geometry. It then generates guidewire masks under constraints imposed by the vessel segmentation masks and outputs the corresponding endpoint coordinates. Finally, it synthesizes realistic guidewire samples on real CAG images using DSB conditioned with SPADE. Experimental results show that the guidewire samples synthesized by VDSB-GWSyn achieve favorable ROI-FID and ROI-KID, as well as high IPR scores. In addition, incorporating our synthesized data for synthetic pre-training followed by real fine-tuning substantially improves downstream guidewire endpoint localization, reducing MPE from 16.01~px to 7.71~px and increasing PCK at 3~px from 52.63\% to 86.27\%, leading to more clinically reliable deployment of robot-assisted guidewire delivery systems. Moreover, the core design philosophy of controllable device synthesis with strict background preservation and anatomical feasibility constraints has the potential to transfer to other interventional device perception tasks where annotated data are scarce.

cs.CV↗
arXiv2026

Voting with the Graph: Stable RLAIF via Topological Consistency Maximization

Reinforcement Learning from AI Feedback (RLAIF) relies on LLM judges as preference measurement instruments, yet these instruments are fundamentally limited by random measurement errors -- stochastic fluctuations that manifest as preference cycles (e.g., $A \succ B \succ C \succ A$), occurring in 5-9% of evaluations across state-of-the-art models. While repeated sampling mitigates noise by averaging multiple judgments, it treats each comparison in isolation and fails to exploit the structural constraints that distinguish systematic signals from random noise. We introduce Topological Consensus Rewards (TCR), a framework that leverages transitivity as a denoising mechanism via topological majority voting: systematic signals reinforce each other through transitive chains, while random errors cluster into topologically exposed cycles. TCR approximates the Maximum Acyclic Subgraph to filter stochastic noise from preference signals. We also propose Cycle Incidence Rate (CIR) as a diagnostic metric that measures the proportion of samples containing preference cycles. Under our noise model, these cycles arise primarily from stochastic measurement errors rather than genuine intransitivity. Experiments on Arena-Hard, MT-Bench, and WritingBench demonstrate that TCR consistently outperforms pairwise baselines and classical ranking algorithms, while exhibiting robust performance across different judge models.

cs.AI↗
arXiv2026

TimeSRL: Generalizable Time-Series Behavioral Modeling via Semantic RL-Tuned LLMs -- A Case Study in Mental Health

Longitudinal passive sensing enables continuous health prediction, yet models often fail under cross-dataset distribution shifts. Traditional ML overfits cohort-specific artifacts, while Large Language Models (LLMs) struggle to reason reliably over long, heterogeneous time-series. We introduce TimeSRL, a two-stage LLM framework that routes predictions through an explicit semantic bottleneck. The model first abstracts raw signals into high-level natural language, then predicts behavioral outcomes from these abstractions alone. This forces the model to reason over semantic concepts that we argue generalize better than raw numbers. We optimize this process end-to-end using Group Relative Policy Optimization (GRPO) with Reinforcement Learning from Verifiable Rewards (RLVR), learning outcome-aligned abstractions without gold intermediate annotations. Instantiated on mental-health prediction, TimeSRL achieves state-of-the-art performance on a benchmark designed to stress-test cross-cohort generalization under a rigorous leave-one-dataset-out (LOSO) protocol, reducing mean absolute error (MAE) over strong non-LLM ML and LLM baselines by 3.1--10.1% and 9.5--44.1% for anxiety, and 3.2--9.6% and 27.4--57.6% for depression (all $p$s<0.05). TimeSRL significantly outperforms prior methods in cross-benchmark transfer across different sensing pipelines, rivaling its own within-domain performance without target-domain fine-tuning. These results demonstrate that semantic abstractions are reusable and point to a new direction for generalizable behavior modeling via RL-tuned LLMs.

cs.LG↗
arXiv2026

Geometrically Constrained Stenosis Editing in Coronary Angiography via Entropic Optimal Transport

The scarcity of high-quality imaging data for coronary angiography (CAG) stenosis limits the clinical translation of automated stenosis detection. Synthetic stenosis data provides a practical avenue to augment training sets, improving data quality, diversity, and distributional coverage, and enhancing detection precision and generalization. However, diffusion-based editing commonly relies on soft guidance in a noise-initialized reverse process, offering limited pixel-level precision and structure preservation. We propose the OT-Bridge Editor, which reframes localized editing as a constrained entropic optimal transport (OT) problem and leverages geometric information to steer the generation path, enabling stronger geometric control. Extensive experiments show that our synthesized angiograms consistently improve downstream stenosis detection, yielding substantial relative gains of 27.8% on the public ARCADE benchmark and 23.0% on our multi-center dataset, supported by consistent qualitative results.

cs.CV↗
arXiv2026

TRUST: A Framework for Decentralized AI Service v.0.1

Large Reasoning Models (LRMs) and Multi-Agent Systems (MAS) in high-stakes domains demand reliable verification, yet centralized approaches suffer four limitations: (1) Robustness, with single points of failure vulnerable to attacks and bias; (2) Scalability, as reasoning complexity creates bottlenecks; (3) Opacity, as hidden auditing erodes trust; and (4) Privacy, as exposed reasoning traces risk model theft. We introduce TRUST (Transparent, Robust, and Unified Services for Trustworthy AI), a decentralized framework with three innovations: (i) Hierarchical Directed Acyclic Graphs (HDAGs) that decompose Chain-of-Thought reasoning into five abstraction levels for parallel distributed auditing; (ii) the DAAN protocol, which projects multi-agent interactions into Causal Interaction Graphs (CIGs) for deterministic root-cause attribution; and (iii) a multi-tier consensus mechanism among computational checkers, LLM evaluators, and human experts with stake-weighted voting that guarantees correctness under 30% adversarial participation. We prove a Safety-Profitability Theorem ensuring honest auditors profit while malicious actors incur losses. All decisions are recorded on-chain, while privacy-by-design segmentation prevents reconstruction of proprietary logic. Across multiple LLMs and benchmarks, TRUST attains 72.4% accuracy (4-18% above baselines) and remains resilient against 20% corruption. DAAN reaches 70% root-cause attribution (vs. 54-63% for standard methods) with 60% token savings. Human studies validate the design (F1 = 0.89, Brier = 0.074). The framework supports (A1) decentralized auditing, (A2) tamper-proof leaderboards, (A3) trustless data annotation, and (A4) governed autonomous agents, pioneering decentralized AI auditing for safe, accountable deployment of reasoning-capable systems.

cs.AI↗
arXiv2026

CoTEvol: Self-Evolving Chain-of-Thoughts for Data Synthesis in Mathematical Reasoning

Large Language Models (LLMs) exhibit strong mathematical reasoning when trained on high-quality Chain-of-Thought (CoT) that articulates intermediate steps, yet costly CoT curation hinders further progress. While existing remedies such as distillation from stronger LLMs and self-synthesis based on test-time search alleviate this issue, they often suffer from diminishing returns or high computing overhead.In this work, we propose CoTEvol, a genetic evolutionary framework that casts CoT generation as a population-based search over reasoning trajectories.Candidate trajectories are iteratively evolved through reflective global crossover at the trajectory level and local mutation guided by uncertainty at the step level, enabling holistic recombination and fine-grained refinement. Lightweight, task-aware fitness functions are designed to guide the evolutionary process toward accurate and diverse reasoning. Empirically, CoTEvol improves correct-CoT synthesis success by over 30% and enhances structural diversity, with markedly improved efficiency. LLMs trained on these evolutionary CoT data achieve an average gain of 6.6% across eight math benchmarks, outperforming previous distillation and self-synthesis approaches. These results underscore the promise of evolutionary CoT synthesis as a scalable and effective method for mathematical reasoning tasks.

cs.AI↗
arXiv2026

BugScope: Learn to Find Bugs Like Human

Software auditing is an increasingly critical task in the era of rapid code generation. While LLM-based auditors have demonstrated strong potential, their effectiveness remains limited by misalignment with the highly complex, domain-specific nature of bug detection. In this work, we introduce BugScope, a framework that mirrors how human auditors learn specific bug patterns from representative examples and apply this knowledge during code auditing. BugScope structures auditing into three steps: seed identification, context retrieval, and bug detection, and aligns LLMs to each step by analyzing real bug reports and mutated examples, and distilling concise, reusable guidelines. On a curated dataset of 33 real-world bugs from 21 widely used open-source projects, BugScope achieves 86.05\% precision and 87.88\% recall, corresponding to an F1 score of 0.87. By comparison, leading industrial tools such as Claude Code (with Claude Opus 4.6) and Cursor BugBot achieve F1 scores of only 0.51 and 0.43, respectively. Beyond benchmarks, large-scale evaluation on real-world projects such as the Linux kernel uncovered 184 previously unknown bugs, of which 78 have already been fixed and 7 explicitly confirmed by developers. Our code is available at https://github.com/jinyaoguo/BugScope

cs.SE↗
arXiv2026

Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale

We introduce Intern-S1-Pro, the first one-trillion-parameter scientific multimodal foundation model. Scaling to this unprecedented size, the model delivers a comprehensive enhancement across both general and scientific domains. Beyond stronger reasoning and image-text understanding capabilities, its intelligence is augmented with advanced agent capabilities. Simultaneously, its scientific expertise has been vastly expanded to master over 100 specialized tasks across critical science fields, including chemistry, materials, life sciences, and earth sciences. Achieving this massive scale is made possible by the robust infrastructure support of XTuner and LMDeploy, which facilitates highly efficient Reinforcement Learning (RL) training at the 1-trillion parameter level while ensuring strict precision consistency between training and inference. By seamlessly integrating these advancements, Intern-S1-Pro further fortifies the fusion of general and specialized intelligence, working as a Specializable Generalist, demonstrating its position in the top tier of open-source models for general capabilities, while outperforming proprietary models in the depth of specialized scientific tasks.

cs.LG↗
arXiv2026

Study of neutrinophilic low-mass dark matter mediated by pseudoscalar

In this work, we investigate a neutrinophilic low-mass dark matter model mediated by a pseudoscalar particle. Since dark matter lacks Standard Model gauge charges, new interactions are required to connect it to the visible sector. Traditional indirect detection searches for annihilation products, such as cosmic rays, become ineffective when the annihilation predominantly yields invisible neutrinos. In our model, the present-day annihilation cross section into neutrinos (manifesting as a neutrino line) falls below current indirect detection limits. We therefore constrain the model using complementary probes: the Lyman-$α$ forest, high-energy astrophysical neutrinos from active galactic nuclei and supernovae, direct detection via nucleon and electron scattering, and invisible Higgs decays. These observables provide stringent and multifaceted constraints on neutrinophilic dark matter interactions in the low-mass regime. Our results indicate that searches for the neutrino line from dark matter annihilations, neutrino self-interactions from supernovae and collider signatures, and invisible Higgs decays offer critical tests for the model's parameter space.

hep-ph↗
arXiv2026

CLAIM: Camera-LiDAR Alignment with Intensity and Monodepth

In this paper, we unleash the potential of the powerful monodepth model in camera-LiDAR calibration and propose CLAIM, a novel method of aligning data from the camera and LiDAR. Given the initial guess and pairs of images and LiDAR point clouds, CLAIM utilizes a coarse-to-fine searching method to find the optimal transformation minimizing a patched Pearson correlation-based structure loss and a mutual information-based texture loss. These two losses serve as good metrics for camera-LiDAR alignment results and require no complicated steps of data processing, feature extraction, or feature matching like most methods, rendering our method simple and adaptive to most scenes. We validate CLAIM on public KITTI, Waymo, and MIAS-LCEC datasets, and the experimental results demonstrate its superior performance compared with the state-of-the-art methods. The code is available at https://github.com/Tompson11/claim.

cs.RO↗
arXiv2026

SecP-Tuning: Efficient Privacy-Preserving Prompt Tuning for Large Language Models via MPC

Large Language Models (LLMs) have revolutionized numerous fields, yet their adaptation to specialized tasks in privacy-sensitive domains such as healthcare and finance remains constrained due to the scarcity of accessible training data caused by stringent privacy requirements. Secure Multi-party Computation (MPC)-based privacy-preserving machine learning provides theoretical guarantees for the privacy of model parameters and data. However, its application to LLMs has been predominantly limited to inference, as fine-tuning introduces significant efficiency challenges, particularly in backward propagation, optimizer, and self-attention operations. To address these challenges, we propose SecP-Tuning, the first MPC-based framework designed for efficient, privacy-preserving prompt tuning of LLMs. SecP-Tuning innovatively integrates Forward-only Tuning (FoT) through the ``data owner-server interaction" paradigm, effectively removing the need for privacy-preserving computations in backward propagation and optimization processes. Furthermore, it devises an efficient privacy-preserving Random Feature Attention (RFA), effectively mitigating the computational complexity of softmax-based self-attention and circumventing MPC-incompatible nonlinear operations. Experimental results demonstrate that, compared to full-Parameter Supervised Fine-Tuning (SFT) and gradient-based prompt tuning, SecP-Tuning achieves approximately 12x and 16x end-to-end acceleration, as well as 17x and 20x reductions in communication overhead, respectively. Moreover, it delivers performance comparable to gradient-based methods across multiple few-shot tasks.

cs.LG↗
arXiv2026

Simple Yet Effective: Extracting Private Data Across Clients in Federated Fine-Tuning of Large Language Models

Federated large language models (FedLLMs) enable cross-silo collaborative training among institutions while preserving data locality, making them appealing for privacy-sensitive domains such as law, finance, and healthcare. However, the memorization behavior of LLMs can lead to privacy risks that may cause cross-client data leakage. In this work, we study the threat of cross-client data extraction, where a semi-honest participant attempts to recover personally identifiable information (PII) memorized from other clients' data. We propose three simple yet effective extraction strategies that leverage contextual prefixes from the attacker's local data, including frequency-based prefix sampling and local fine-tuning to amplify memorization. To evaluate these attacks, we construct a Chinese legal-domain dataset with fine-grained PII annotations consistent with CPIS, GDPR, and CCPA standards, and assess extraction performance using two metrics: coverage and efficiency. Experimental results show that our methods can recover up to 56.6% of victim-exclusive PII, where names, addresses, and birthdays are particularly vulnerable. These findings highlight concrete privacy risks in FedLLMs and establish a benchmark and evaluation framework for future research on privacy-preserving federated learning. Code and data are available at https://github.com/SMILELab-FL/FedPII.

cs.CL↗
arXiv2026

Auto-Rubric: Learning From Implicit Weights to Explicit Rubrics for Reward Modeling

Conventional reward modeling relies on gradient descent over neural weights, creating opaque, data-hungry "black boxes." We propose a paradigm shift from implicit to explicit reward parameterization, recasting optimization from continuous weight spaces to the discrete space of natural language rubrics. We introduce a training-free framework based on iterative rubric learning: it locally induces discriminative criteria via verification-driven refinement, and globally compresses the candidate criteria pool into a compact core set by maximizing an information-theoretic coding rate objective. We organize the compressed core set into a hierarchical rubric structure -- high-level evaluation dimensions supported by concrete verification checks -- serving as an interpretable, portable reward function. Empirically, our approach challenges prevailing data scaling assumptions: using only 70 preference pairs, our rubric-guided judges outperform fully trained reward models on diverse benchmarks. For instance, Qwen3-8B equipped with our learned rubrics achieves 80.91% on RewardBench2, surpassing the specialized Skywork-Reward-V2-Qwen3-8B (78.20%). These results demonstrate that alignment signals are highly compressible and can be effectively captured through explicit symbolic search.

cs.LG↗
arXiv2026

Physics-Informed Neural Networks and Neural Operators for Parametric PDEs

PDEs arise ubiquitously in science and engineering, where solutions depend on parameters (physical properties, boundary conditions, geometry). Traditional numerical methods require re-solving the PDE for each parameter, making parameter space exploration prohibitively expensive. Recent machine learning advances, particularly physics-informed neural networks (PINNs) and neural operators, have revolutionized parametric PDE solving by learning solution operators that generalize across parameter spaces. We critically analyze two main paradigms: (1) PINNs, which embed physical laws as soft constraints and excel at inverse problems with sparse data, and (2) neural operators (e.g., DeepONet, Fourier Neural Operator), which learn mappings between infinite-dimensional function spaces and achieve unprecedented generalization. Through comparisons across fluid dynamics, solid mechanics, heat transfer, and electromagnetics, we show neural operators can achieve computational speedups of $10^3$ to $10^5$ times faster than traditional solvers for multi-query scenarios, while maintaining comparable accuracy. We provide practical guidance for method selection, discuss theoretical foundations (universal approximation, convergence), and identify critical open challenges: high-dimensional parameters, complex geometries, and out-of-distribution generalization. This work establishes a unified framework for understanding parametric PDE solvers via operator learning, offering a comprehensive, incrementally updated resource for this rapidly evolving field

stat.ML↗
arXiv2026

GEPO: Group Expectation Policy Optimization for Stable Heterogeneous Reinforcement Learning

As single-center computing approaches power constraints, decentralized training becomes essential. However, traditional Reinforcement Learning (RL) methods, crucial for enhancing large model post-training, cannot adapt to decentralized distributed training due to the tight coupling between parameter learning and rollout sampling. For this, we propose HeteroRL, a heterogeneous RL architecture that decouples these processes, enabling stable training across geographically distributed nodes connected via the Internet. The core component is Group Expectation Policy Optimization (GEPO), an asynchronous RL algorithm robust to latency caused by network delays or heterogeneity in computational resources. Our study reveals that high latency significantly increases KL divergence, leading to higher variance of importance weights and training instability. GEPO mitigates this issue by using group expectation weighting to exponentially reduce the variance of importance weights, with theoretical guarantees. Experiments show GEPO achieves superior stability - only a 3% performance drop from online to 1800s latency-and reduces the best-to-last gap by 85% versus GSPO (1.8 vs. 12.0) while attaining the highest scores, highlighting its effectiveness in decentralized, resource-heterogeneous environments.

cs.LG↗
arXiv2026

Approximate Graph Propagation Revisited: Dynamic Parameterized Queries, Tighter Bounds and Dynamic Updates

We revisit Approximate Graph Propagation (AGP), a unified framework which captures various graph propagation tasks, such as PageRank, feature propagation in Graph Neural Networks (GNNs), and graph-based Retrieval-Augmented Generation (RAG). Our work focuses on the settings of dynamic graphs and dynamic parameterized queries, where the underlying graphs evolve over time (updated by edge insertions or deletions) and the input query parameters are specified on the fly to fit application needs. Our first contribution is an interesting observation that the SOTA solution, AGP-Static, can be adapted to support dynamic parameterized queries; however several challenges remain unresolved. Firstly, the query time complexity of AGP-Static is based on an assumption of using an optimal algorithm for subset sampling in its query algorithm. Unfortunately, back to that time, such an algorithm did not exist; without such an optimal algorithm, an extra $O(\log^2 n)$ factor is required in the query complexity, where $n$ is the number of vertices in the graphs. Secondly, AGP-Static performs poorly on dynamic graphs, taking $O(n\log n)$ time to process each update. To address these challenges, we propose a new algorithm, AGP-Static++, which is simpler yet reduces roughly a factor of $O(\log^2 n)$ in the query complexity while preserving the approximation guarantees of AGP-Static. However, AGP-Static++ still requires $O(n)$ time to process each update. To better support dynamic graphs, we further propose AGP-Dynamic, which achieves $O(1)$ amortized time per update, significantly improving the aforementioned $O(n)$ per-update bound, while still preserving the query complexity and approximation guarantees. Last, our comprehensive experiments validate the theoretical improvements: compared to the baselines, our algorithm achieves speedups of up to $177\times$ on update time and $10\times$ on query efficiency.

cs.DS↗
arXiv2025

An Elementary Characterization of the Gauss--Kuzmin Measure in the Theory of Continued Fractions

By a classical result of Gauss and Kuzmin, the frequency with which a string $\mathbf{a}=(a_1,\dots,a_n)$ of positive integers appears in the continued fraction expansion of a random real number is given by $μ_{GK}({I(\mathbf{a})})$, where $I(\mathbf{a})$ is the set of real numbers in $[0,1)$ whose continued fraction expansion begins with the string $\mathbf{a}$ and $μ_{GK}$ is the \emph{Gauss--Kuzmin measure}, defined by $μ_{GK}(I)= \frac{1}{\log 2}\int_I \frac{1}{1+x} dx$, for any interval $I\subseteq[0,1]$. % It is known that the Gauss--Kuzmin measure satisfies the symmetry property $(*)$ $μ_{GK}(I(\mathbf{a}))=μ_{GK}(I(\overleftarrow{\mathbf{a}}))$, where $\overleftarrow{\mathbf{a}}=(a_n,\dots,a_1)$ is the reverse of the string $\mathbf{a}$. We show that this property in fact characterizes the Gauss--Kuzmin measure: If $μ$ is any probability measure with continuous density function on $[0,1]$ satisfying $μ(I(\mathbf{a}))=μ(I(\overleftarrow{\mathbf{a}}))$ for all finite strings $\mathbf{a}$, then $μ=μ_{GK}$. % We also consider the question whether symmetries analogous to $(*)$ hold for permutations of $\mathbf{a}$ other than the reverse $\overleftarrow{\mathbf{a}}$; we call such a symmetry \emph{nontrivial}. We show that strings $\mathbf{a}$ of length $3$ have no nontrivial symmetries, while for each $n\ge 4$ there exists an infinite family of strings $\mathbf{a}$ of length $n$ that do have nontrivial symmetries. Finally we present numerical data supporting the conjecture that, in an appropriate asymptotic sense, ``almost all'' strings $\mathbf{a}$ have no nontrivial symmetries.

math.NT↗
arXiv2025

TRUST: A Decentralized Framework for Auditing Large Language Model Reasoning

Large Language Models generate complex reasoning chains that reveal their decision-making, yet verifying the faithfulness and harmlessness of these intermediate steps remains a critical unsolved problem. Existing auditing methods are centralized, opaque, and hard to scale, creating significant risks for deploying proprietary models in high-stakes domains. We identify four core challenges: (1) Robustness: Centralized auditors are single points of failure, prone to bias or attacks. (2) Scalability: Reasoning traces are too long for manual verification. (3) Opacity: Closed auditing undermines public trust. (4) Privacy: Exposing full reasoning risks model theft or distillation. We propose TRUST, a transparent, decentralized auditing framework that overcomes these limitations via: (1) A consensus mechanism among diverse auditors, guaranteeing correctness under up to $30\%$ malicious participants. (2) A hierarchical DAG decomposition of reasoning traces, enabling scalable, parallel auditing. (3) A blockchain ledger that records all verification decisions for public accountability. (4) Privacy-preserving segmentation, sharing only partial reasoning steps to protect proprietary logic. We provide theoretical guarantees for the security and economic incentives of the TRUST framework. Experiments across multiple LLMs (GPT-OSS, DeepSeek-r1, Qwen) and reasoning tasks (math, medical, science, humanities) show TRUST effectively detects reasoning flaws and remains robust against adversarial auditors. Our work pioneers decentralized AI auditing, offering a practical path toward safe and trustworthy LLM deployment.

cs.AI↗