Searcharxiv⌕ Search

arXiv subjects

Yating Liu

Publications and source records attributed to Yating Liu.

At least 19 recordsLinked to original sources

Safety-Preserving Medical LLM Fine-Tuning via Bilevel Data Selection

As general large language models (LLMs) are increasingly adapted for patient-facing medical applications, improving medical capability while controlling patient-facing risks remains a critical challenge. Large-scale medical instruction data are essential for acquiring domain knowledge through supervised fine-tuning (SFT), but unsafe responses can undermine existing safety alignment. To address this problem, we propose Scalable Bilevel Data Selection (S-BDS) for safety-preserving medical SFT. By controlling selection-weight concentration, S-BDS enables reliable sample ranking over large candidate pools and identifies training examples that improve medical capability while controlling patient-facing risks. We combine clinician-validated safe data and selected data with unscreened medical instruction data for SFT, and jointly evaluate medical capability and patient-facing safety on HealthBench and PatientSafetyBench, respectively. Experiments across Llama and Qwen models show that S-BDS achieves the highest safe rates among all compared methods, outperforming the strongest baselines by 4.64 and 3.00 percentage points, respectively, while maintaining competitive medical capability. Further experiments show that varying the safety-oriented weight during SFT controls the trade-off between medical capability and patient-facing safety.

cs.CL↗

Latent Flow Matching for Arbitrage-Aware Implied Volatility Surface Generation

We propose an arbitrage-aware latent flow-matching framework for unconditional implied volatility surface generation. The method first compresses high-dimensional surfaces into a low-dimensional latent space using a variational autoencoder regularized by differentiable calendar-spread, call-spread and butterfly-arbitrage penalties. A flow-matching model then learns to transport a Gaussian prior toward the empirical latent distribution, and generated latent samples are decoded back into volatility surfaces. We evaluate the approach using marginal and surface-level Wasserstein distances, smile and skew diagnostics, pointwise quantile surfaces, financially interpretable shape metrics, and static no-arbitrage tests. The proposed model closely reproduces the empirical distribution and the main maturity-moneyness structures, achieves the best performance in the extreme Q99 regime, and generates 90.8% of surfaces satisfying all tested static no-arbitrage conditions. Overall, the results show that latent flow matching provides a favorable balance between distributional similarity, tail preservation, and financial consistency without requiring post-sampling reweighting.

q-fin.CP↗

Match the Canvas, Not Just the Answer: Predictability-Aware SFT for Diffusion Language Models

Diffusion language models (DLMs) enable flexible parallel generation by resolving tokens according to the model's evolving predictability rather than a fixed left-to-right order. This flexibility, however, introduces training choices absent from standard autoregressive teacher forcing: which reference tokens are visible when a target is supervised and how much generation space is allocated. Standard supervised fine-tuning (SFT) typically makes these choices through random masking, independently of inference. Our analysis shows how this training-inference mismatch can misdirect supervision. Random masking can conceal prediction errors or penalize uncertainty that decoding would otherwise resolve, while the attention-visible input length can change which response formulations the model favors, even when the underlying solution is unchanged. Motivated by these findings, we propose Predictability-Aware Canvas Selection and Supervision (PACS), an SFT method. PACS uses the model's own predictability to select each example's attention-visible input length and supervises reference tokens immediately before their confidence-guided revelation. Across reasoning and code-generation benchmarks, PACS consistently achieves the highest mean accuracy among the compared SFT methods, with gains of up to 12.84 percentage points over vanilla SFT on individual benchmarks. Code will be released upon publication.

cs.LG↗

Learning Transition Kernels of Jump-Diffusion Processes with Conditional Diffusion Models

We study the problem of learning transition kernels for time-homogeneous jump-diffusion processes using conditional diffusion models, with the goal of generating new sample paths from training data consisting of N independent trajectories observed on a high-frequency discrete time grid. On the theoretical side, we establish non-asymptotic bounds for the conditional score estimation error and for the KL divergence between the laws of the true and generated discretely observed paths. On the numerical side, we first evaluate our method on synthetic data to assess the theoretical findings and benchmark its performance against the approach of Gao et al. (2025). We then apply our method to real-world data and investigate its performance on a probabilistic forecasting task.

stat.ML↗

Who Drives the System? Classifying Mean-Field Particle Systems from Trajectory Data

We study the supervised classification problem for interacting particle systems (IPS) from trajectory observations. The IPS belongs to one of K classes, each characterized by a distinct interaction drift. Given a learning dataset, the goal is then to predict the class label of a newly observed system based on the trajectory of a single particle. This setting raises several statistical challenges. First, the particles within each system interact and are therefore dependent. Second, although the full particle system is Markovian, the trajectory of a single particle is not. To address these difficulties, we exploit the McKean-Vlasov limit of the IPS, which describes the dynamics of a typical particle as the number of particles tends to infinity. We propose a plug-in classification procedure based on estimating the interaction drift associated with each class from discretely observed trajectory data. Hence, for each class, we provide a new nonparametric estimator of the drifts by minimizing a ridge-regularized least-squares contrast over a B-spline basis. In particular, our theoretical findings reveal that the convergence rate of the resulting classifier is of order N -1/6+$ε$ for any $ε$ > 0, where N denotes the number of particles in each system. Numerical experiments illustrate the performance of the proposed method and show that it outperforms an end-to-end neural network baseline that does not exploit the underlying particle-system structure.

math.ST↗

ABO-Med: Accelerated Bilevel Optimization for Few-Shot Medical Image Classification

In recent years, bilevel optimization has been widely used in a variety of machine learning tasks. However, prior bilevel optimization algorithms generally require the computation of second-order information, which limits their practical scalability. Only recently has a first-order paradigm for bilevel optimization been established, attaining near-optimal theoretical guarantees for solving bilevel optimization problems. In this paper, we propose ABO-Med, a scalable instantiation of this paradigm for few-shot learning, by incorporating it into the model-agnostic meta-learning (MAML) framework and tailoring it to medical image classification. We also introduce Medical Adaptive RandomAugment (MedRAug), a modality-aware augmentation strategy designed for medical images. Theoretically, ABO-Med establishes the optimality of MAML-type meta-learning approaches. Empirically, ABO-Med outperforms prior baselines on several public medical datasets, with gains of 1.99% to 18.76%, while MedRAug further improves the average accuracy by 2.20% to 6.34%. Additional cross-domain experiments, augmentation ablation studies, backbone ablation studies, and training efficiency analysis further validate the effectiveness and efficiency of the proposed method.

cs.CV↗

Particle method for the numerical simulation of the path-dependent McKean-Vlasov equation

We present the particle method for simulating the solution to the path-dependent McKean-Vlasov equation, in which both the drift and the diffusion coefficients depend on the whole trajectory of the process up to the current time t, as well as on the corresponding marginal distributions. Our main contribution is the derivation of explicit convergence rates that capture the interplay between time and space discretization. To control the uniform-in-time convergence of empirical measures in Wasserstein distance on a fixed interval, we develop two approaches: one based on Fournier-Guillin estimates, the other extending Horowitz-Karandikar's method to general p greater or equal to 2. We then compare the respective regimes of applicability. Numerical simulations of a generalized Ornstein-Uhlenbeck process with memory provide evidence for the accuracy of our bounds. We also apply our method to an extension of the Jansen-Rit mean-field model for neural masses.

math.PR↗

Causal Clothes-Invariant Feature Learning for Cloth-Changing Person Re-ID

In cloth-changing person re-identification (CCReID), it is critical to learn clothes-invariant feature, which can provide discriminative ID features that remain robust against clothing changes. However, a spurious correlation currently limits existing ReID methods from effectively extracting these clothing-invariant features. This spurious correlation arises from clothing ownership: clothing is rarely shared across different identities, so models tend to memorize clothing cues for identity recognition, and this strategy generalizes poorly to unseen clothing. In this paper, we propose Causal Clothes-Invariant Learning (CCIL), which explicitly shifts CC-ReID from likelihood learning P (Y|X) to causal intervention learning P (Y|do(X)) to block the clothing shortcut. CCIL realizes this intervention through three modules: a Confounder Dictionary, an Intervention Module, and Disentangle Regularization. The causality-based modeling makes the entire model naturally clothes-invariant, effectively preventing the capture of spurious correlations in feature learning. Extensive experiments validate the effectiveness of CCIL. On PRCC and DeepChange datasets, CCIL achieves Rank-1 accuracies of 66.4% and 59.2%, outperforming state-of-the-art methods by 1.4 and 4.1 percentage points, respectively.

cs.CV↗

Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification

Graph-based models have achieved great success in person re-identification tasks recently, which compute the graph topology structure (affinities) among different people first and then pass the information across them to achieve stronger features. But we find existing graph-based methods in the visible-infrared person re-identification task (VI-ReID) suffer from bad generalization because of two issues: 1) train-test modality balance gap, which is a property of VI-ReID task. The number of two modalities data are balanced in the training stage, but extremely unbalanced in inference, causing the low generalization of graph-based VI-ReID methods. 2) sub-optimal topology structure caused by the end-to-end learning manner to the graph module. We analyze that the well-trained input features weaken the learning of graph topology, making it not generalized enough during the inference process. In this paper, we propose a Counterfactual Intervention Feature Transfer (CIFT) method to tackle these problems. Specifically, a Homogeneous and Heterogeneous Feature Transfer (H2FT) is designed to reduce the train-test modality balance gap by two independent types of well-designed graph modules and an unbalanced scenario simulation. Besides, a Counterfactual Relation Intervention (CRI) is proposed to utilize the counterfactual intervention and causal effect tools to highlight the role of topology structure in the whole training process, which makes the graph topology structure more reliable. Extensive experiments on standard VI-ReID benchmarks demonstrate that CIFT outperforms the state-of-the-art methods under various settings.

cs.CV↗

SpeedCP: Fast Kernel-based Conditional Conformal Prediction

Conformal prediction provides distribution-free prediction sets with finite-sample conditional guarantees. We build upon the RKHS-based framework of Gibbs et al. (2023), which leverages families of covariate shifts to provide approximate conditional conformal prediction intervals, an approach with strong theoretical promise, but with prohibitive computational cost. To bridge this gap, we develop a stable and efficient algorithm that computes the full solution path of the regularized RKHS conformal optimization problem, at essentially the same cost as a single kernel quantile fit. Our path-tracing framework simultaneously tunes hyperparameters, providing smoothness control and data-adaptive calibration. To extend the method to high-dimensional settings, we further integrate our approach with low-rank latent embeddings that capture conditional validity in a data-driven latent space. Empirically, our method provides reliable conditional coverage across a variety of modern black-box predictors, improving the interval length of Gibbs et al. (2023) by 30%, while achieving a 40-fold speedup.

stat.ME↗

Plug-In Classification of Drift Functions in Diffusion Processes Using Neural Networks

We study supervised multiclass classification for diffusion processes, where each class is characterized by a distinct drift function and trajectories are observed at discrete times. We first derive a multidimensional Bayes rule and then construct a plug-in classifier by estimating the class-specific drifts with neural networks. Under standard regularity assumptions, we establish convergence rates for the excess misclassification risk, making explicit the contributions of drift estimation, time discretization, and dimension. Our analysis also highlights the benefit of exploiting the diffusion structure: the drift is learned from all observed increments, leading to sharper guarantees than direct trajectory-based neural classifiers in the considered setting. Numerical experiments support the theory: the proposed method achieves better classification performance than Denis et al. (2024) in dimension one, remains effective in higher dimensions when the drift functions admit a compositional structure, and outperforms end-to-end neural classifiers trained directly on trajectories, as in Bos & Schmidt-Hieber (2022).

stat.ML↗

Usability as a Weapon: Attacking the Safety of LLM-Based Code Generation via Usability Requirements

Large Language Models (LLMs) are increasingly used for automated software development, making their ability to preserve secure coding practices critical. In practice, however, many security requirements are implicit or underspecified, whereas usability requirements are explicit and high-signal. This asymmetry motivates our investigation of usability pressure as a practical attack surface: realistic usability-oriented requirements (e.g., new features, performance constraints, or simplicity demands) can cause coding LLMs to satisfy explicit usability goals while silently dropping implicit security constraints -- a form of reward hacking. We formalize this threat as UPAttack and propose U-SPLOIT, an automated framework to craft UPAttack that (i) selects tasks where a model is initially secure, (ii) synthesizes usability pressures by identifying usability rewards of insecure alternatives across three vectors (Functionality, Implementation, Trade-off), and (iii) verifies security regression via both existing test cases and dynamically generated exploit payloads. Across 75 seed scenarios (25 CWEs x 3 cases), spanning multiple languages (Python, C, and JavaScript), U-SPLOIT achieves attack success rates up to 98.1% on multiple state-of-the-art models (e.g., GPT-5.2-chat and Gemini-3-Flash-Preview).

cs.CR↗

Drift Estimation for Diffusion Processes Using Neural Networks Based on Discretely Observed Independent Paths

This paper addresses the nonparametric estimation of the drift function over a compact domain for a time-homogeneous diffusion process, based on high-frequency discrete observations from $N$ independent trajectories. We propose a neural network-based estimator and derive a non-asymptotic convergence rate, decomposed into a training error, an approximation error, and a diffusion-related term scaling as ${\log N}/{N}$. For compositional drift functions, we establish an explicit rate. In the numerical experiments, we consider a drift function with local fluctuations generated by a double-layer compositional structure featuring local oscillations, and show that the empirical convergence rate becomes independent of the input dimension $d$. Compared to the $B$-spline method, the neural network estimator achieves better convergence rates and more effectively captures local features, particularly in higher-dimensional settings.

stat.ML↗

Filtering with Confidence: When Data Augmentation Meets Conformal Prediction

With promising empirical performance across a wide range of applications, synthetic data augmentation appears a viable solution to data scarcity and the demands of increasingly data-intensive models. Its effectiveness lies in expanding the training set in a way that reduces estimator variance while introducing only minimal bias. Controlling this bias is therefore critical: effective data augmentation should generate diverse samples from the same underlying distribution as the training set, with minimal shifts. In this paper, we propose conformal data augmentation, a principled data filtering framework that leverages the power of conformal prediction to produce diverse synthetic data while filtering out poor-quality generations with provable risk control. Our method is simple to implement, requires no access to internal model logits, nor large-scale model retraining. We demonstrate the effectiveness of our approach across multiple tasks, including topic prediction, sentiment analysis, image classification, and fraud detection, showing consistent performance improvements of up to 40 percentage points (pp) in $F_1$ score over unaugmented baselines, and 4~pp over other filtered augmentation baselines.

cs.LG↗

From Transactions to Exploits: Automated PoC Synthesis for Real-World DeFi Attacks

Blockchain systems are increasingly targeted by on-chain attacks that exploit contract vulnerabilities to extract value rapidly and stealthily, making systematic analysis and reproduction highly challenging. In practice, reproducing such attacks requires manually crafting proofs-of-concept (PoCs), a labor-intensive process that demands substantial expertise and scales poorly. In this work, we present the first automated framework for synthesizing verifiable PoCs directly from on-chain attack executions. Our key insight is that attacker logic can be recovered from low-level transaction traces via trace-driven reverse engineering, and then translated into executable exploits by leveraging the code-generation capabilities of large language models (LLMs). To this end, we propose TracExp, which localizes attack-relevant execution contexts from noisy, multi-contract traces and introduces a novel dual-decompiler to transform concrete executions into semantically enriched exploit pseudocode. Guided by this representation, TracExp synthesizes PoCs and refines them to preserve exploitability-relevant semantics. We evaluate TracExp on 321 real-world attacks over the past 20 months. TracExp successfully synthesizes PoCs for 93% of incidents, with 58.78% being directly verifiable, at an average cost of only \$0.07 per case. Moreover, TracExp enabled the release of a large number of previously unavailable PoCs to the community, earning a $900 bounty and demonstrating strong practical impact.

cs.CR↗

Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

Despite advances in scientific AI, a coherent framework for Scientific General Intelligence (SGI)-the ability to autonomously conceive, investigate, and reason across scientific domains-remains lacking. We present an operational SGI definition grounded in the Practical Inquiry Model (PIM: Deliberation, Conception, Action, Perception) and operationalize it via four scientist-aligned tasks: deep research, idea generation, dry/wet experiments, and experimental reasoning. SGI-Bench comprises over 1,000 expert-curated, cross-disciplinary samples inspired by Science's 125 Big Questions, enabling systematic evaluation of state-of-the-art LLMs. Results reveal gaps: low exact match (10--20%) in deep research despite step-level alignment; ideas lacking feasibility and detail; high code executability but low execution result accuracy in dry experiments; low sequence fidelity in wet protocols; and persistent multimodal comparative-reasoning challenges. We further introduce Test-Time Reinforcement Learning (TTRL), which optimizes retrieval-augmented novelty rewards at inference, enhancing hypothesis novelty without reference answer. Together, our PIM-grounded definition, workflow-centric benchmark, and empirical insights establish a foundation for AI systems that genuinely participate in scientific discovery.

cs.AI↗

Revealing Adversarial Smart Contracts through Semantic Interpretation and Uncertainty Estimation

Adversarial smart contracts, mostly on EVM-compatible chains like Ethereum and BSC, are deployed as EVM bytecode to exploit vulnerable smart contracts for financial gain. Detecting such malicious contracts at the time of deployment is an important proactive strategy to prevent losses from victim contracts. It offers a better cost-benefit ratio than detecting vulnerabilities on diverse potential victims. However, existing works are not generic with limited detection types and effectiveness due to imbalanced samples, while the emerging LLM technologies, which show their potential in generalization, have two key problems impeding its application in this task: hard digestion of compiled-code inputs, especially those with task-specific logic, and hard assessment of LLM's certainty in its binary (yes-or-no) answers. Therefore, we propose a generic adversarial smart contracts detection framework FinDet, which leverages LLM with two enhancements addressing the above two problems. FinDet takes as input only the EVM bytecode contracts and identifies adversarial ones among them with high balanced accuracy. The first enhancement extracts concise semantic intentions and high-level behavioral logic from the low-level bytecode inputs, unleashing the LLM reasoning capability restricted by the task input. The second enhancement probes and measures the LLM uncertainty to its multi-round answering to the same query, improving the LLM answering robustness for binary classifications required by the task output. Our comprehensive evaluation shows that FinDet achieves a BAC of 0.9374 and a TPR of 0.9231, significantly outperforming existing baselines. It remains robust under challenging conditions including unseen attack patterns, low-data settings, and feature obfuscation. FinDet detects all 5 public and 20+ unreported adversarial contracts in a 10-day real-world test, confirmed manually.

cs.CR↗

Consistency Change Detection Framework for Unsupervised Remote Sensing Change Detection

Unsupervised remote sensing change detection aims to monitor and analyze changes from multi-temporal remote sensing images in the same geometric region at different times, without the need for labeled training data. Previous unsupervised methods attempt to achieve style transfer across multi-temporal remote sensing images through reconstruction by a generator network, and then capture the unreconstructable areas as the changed regions. However, it often leads to poor performance due to generator overfitting. In this paper, we propose a novel Consistency Change Detection Framework (CCDF) to address this challenge. Specifically, we introduce a Cycle Consistency (CC) module to reduce the overfitting issues in the generator-based reconstruction. Additionally, we propose a Semantic Consistency (SC) module to enable detail reconstruction. Extensive experiments demonstrate that our method outperforms other state-of-the-art approaches.

cs.CV↗