arXiv subjects

Yu Ouyang

Publications and source records attributed to Yu Ouyang.

5 recordsLinked to original sources

arXiv2026

MedDDC-Eval: Diagnosis-Decoupled Evaluation of Multi-Turn Medical Consultation Agents

Evaluating multi-turn medical consultation agents requires judging the diagnostic support provided by the histories they elicit through interaction. Yet coupled evaluation lets each policy both elicit the history and generate the terminal diagnosis, so a diagnosis score confounds the elicited history with the policy's own terminal diagnosis generator. We introduce MedDDC-Eval, a diagnosis-decoupled evaluation testbed over held-out cases derived from medical records and online consultations. It applies the same frozen shared diagnostic reader to every policy-elicited history, holding terminal diagnosis generation fixed across policies and enabling comparison under the shared diagnostic reader. It reports diagnostic support, information-acquisition coverage, and efficiency. LLM-assisted semantic matching followed by deterministic one-to-one assignment makes the diagnosis-trajectory-efficiency (D/T/E) scores auditable. In a fixed-history audit across eight policies, replacing each policy's own generator with the shared diagnostic reader shifts diagnosis F1 by 2.2-19.0 points and reverses 18% and 36% of pairwise orderings on the Record and Dialogue splits. To examine downstream utility, we use standard Group Relative Policy Optimization (GRPO) with a separate training-time reward that targets the same diagnosis and trajectory dimensions. Relative to its Qwen3-32B initialization, the trained policy gains 9.6 and 4.6 aggregate-score points on the held-out Record and Dialogue splits, respectively, and ablating either feedback signal reduces the aggregate score on both. Together, MedDDC-Eval supports comparison under a shared diagnostic reader and evaluation-informed policy development, while complementing end-to-end evaluation when terminal diagnosis generation is also part of the target capability.

cs.CL↗

arXiv2026

AppFlow: Memory Scheduling for Cold Launch of Large Apps on Mobile and Vehicle Systems

GB-scale large apps like on-device LLMs and rich media editors are becoming the next-generation trend, but their heavy memory and I/O demands, especially during multitasking, cause devices to reclaim or kill processes, turning warm apps into cold launches. The challenge lies not in storing them, but in fast, accurate launching. For users, 1s is the usability cliff, yet our measurements show 86.6\% of GB-scale cold launches exceed it. Also, Android Vitals flags only $\geq$ 5s as slow, exposing a large satisfaction gap. Existing optimizations are designed in isolation and conflict. For example, preloading reduces I/O stalls but consumes scarce memory and is undone by reclamation, while reclamation and killing free memory but sacrifice background survivability, leading to repeated cold relaunches. Our key insight is that, although multitasking makes runtime behavior complex, each app's file access pattern remains predictable. The challenge lies in exploiting this predictability, i.e., preloading without exhausting memory, reclaiming without undoing gains, and killing selectively to preserve background survivability. We introduce AppFlow, a prediction-based system-wide scheduler that integrates a Selective File Preloader, an Adaptive Memory Reclaimer, and a Context-Aware Process Killer. Implemented across the Android framework and Linux kernel without app changes, AppFlow cuts GB-scale cold-launch latency by 66.5\% (e.g., 2s$\rightarrow$690ms) and sustains 95\% of launches within 1s over a 100-day test, significantly improving responsiveness and multitasking experience.

cs.OS↗

arXiv2023

An extreme value statistics model of heterogeneous ice nucleation for quantifying the stability of supercooled aqueous systems

The propensity of water to remain in a metastable liquid state at temperatures below its equilibrium melting point holds significant potential for cryopreserving biological material such as tissues and organs. The benefits conferred are a direct result of progressively reducing metabolic expenditure due to colder temperatures while simultaneously avoiding the irreversible damage caused by the crystallization of ice. Unfortunately, the freezing of water in bulk systems of clinical relevance is dominated by random heterogeneous nucleation initiated by uncharacterized trace impurities, and the marked unpredictability of this behavior has prevented implementation of supercooling outside of controlled laboratory settings and in volumes larger than a few milliliters. Here, we develop a statistical model that jointly captures both the inherent stochastic nature of nucleation using conventional Poisson statistics as well as the random variability of heterogeneous nucleation catalysis through bivariate extreme value statistics. Individually, these two classes of models cannot account for both the time-dependent nature of nucleation and the sample-to-sample variability associated with heterogeneous catalysis, and traditional extreme value models have only considered variation of the characteristic nucleation temperature. We conduct a series of constant cooling rate and isothermal nucleation experiments with physiological saline solutions and leverage the statistical model to evaluate the natural variability of kinetic and thermodynamic nucleation parameters. By quantifying freezing probability as a function of temperature, supercooled duration, and system volume, while accounting for nucleation site variability, this study also provides a basis for the rational design of stable supercooled biopreservation protocols.

cond-mat.mtrl-sci↗

arXiv2023

ODDFUZZ: Discovering Java Deserialization Vulnerabilities via Structure-Aware Directed Greybox Fuzzing

Java deserialization vulnerability is a severe threat in practice. Researchers have proposed static analysis solutions to locate candidate vulnerabilities and fuzzing solutions to generate proof-of-concept (PoC) serialized objects to trigger them. However, existing solutions have limited effectiveness and efficiency. In this paper, we propose a novel hybrid solution ODDFUZZ to efficiently discover Java deserialization vulnerabilities. First, ODDFUZZ performs lightweight static taint analysis to identify candidate gadget chains that may cause deserialization vulner-abilities. In this step, ODDFUZZ tries to locate all candidates and avoid false negatives. Then, ODDFUZZ performs directed greybox fuzzing (DGF) to explore those candidates and generate PoC testcases to mitigate false positives. Specifically, ODDFUZZ applies a structure-aware seed generation method to guarantee the validity of the testcases, and adopts a novel hybrid feedback and a step-forward strategy to guide the directed fuzzing. We implemented a prototype of ODDFUZZ and evaluated it on the popular Java deserialization repository ysoserial. Results show that, ODDFUZZ could discover 16 out of 34 known gadget chains, while two state-of-the-art baselines only identify three of them. In addition, we evaluated ODDFUZZ on real-world applications including Oracle WebLogic Server, Apache Dubbo, Sonatype Nexus, and protostuff, and found six previously unreported exploitable gadget chains with five CVEs assigned.

cs.CR↗

arXiv2023

Improving Java Deserialization Gadget Chain Mining via Overriding-Guided Object Generation

Java (de)serialization is prone to causing security-critical vulnerabilities that attackers can invoke existing methods (gadgets) on the application's classpath to construct a gadget chain to perform malicious behaviors. Several techniques have been proposed to statically identify suspicious gadget chains and dynamically generate injection objects for fuzzing. However, due to their incomplete support for dynamic program features (e.g., Java runtime polymorphism) and ineffective injection object generation for fuzzing, the existing techniques are still far from satisfactory. In this paper, we first performed an empirical study to investigate the characteristics of Java deserialization vulnerabilities based on our manually collected 86 publicly known gadget chains. The empirical results show that 1) Java deserialization gadgets are usually exploited by abusing runtime polymorphism, which enables attackers to reuse serializable overridden methods; and 2) attackers usually invoke exploitable overridden methods (gadgets) via dynamic binding to generate injection objects for gadget chain construction. Based on our empirical findings, we propose a novel gadget chain mining approach, \emph{GCMiner}, which captures both explicit and implicit method calls to identify more gadget chains, and adopts an overriding-guided object generation approach to generate valid injection objects for fuzzing. The evaluation results show that \emph{GCMiner} significantly outperforms the state-of-the-art techniques, and discovers 56 unique gadget chains that cannot be identified by the baseline approaches.

cs.CR↗