Peixin Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Peixin Wang has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Min Zhang
Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China
8 shared publications - Dapeng Zhi
Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China
4 shared publications - Si Liu
ETH Zurich, Zurich, Switzerland
4 shared publications - Cheng Chen
University of Science and Technology Beijing
3 shared publications Dapeng Zhi
Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China
3 shared publications- Guanyan Li
University of Oxford, Oxford, United Kingdom
3 shared publications
Latest Publications
- 14 May 2026
- Published by Elsevier in Neural Networks
- Vol. 203, 109107
MaskCtrl: Training mask networks as self-explainable and performant controllers via deep reinforcement learning
- 14 May 2026
- Published by Elsevier in Neural Networks
- Vol. 203, 109107
MaskCtrl: Training mask networks as self-explainable and performant controllers via deep reinforcement learning
- 1 May 2026
- Published by Springer Nature
- p. 59-85
Formal Verification of Neural Network-Controlled Systems via Proof Certificates
- 1 May 2026
- Published by Springer Nature
- p. 59-85
Formal Verification of Neural Network-Controlled Systems via Proof Certificates
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 3246-3258
EchoFuzz: Empowering Smart Contract Fuzzing with Large Language Models
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 3246-3258
Open AccessEchoFuzz: Empowering Smart Contract Fuzzing with Large Language Models
- Open Access
- 10 April 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Programming Languages
- Vol. 10 (OOPSLA1) , 2073-2098
A Minimalist Proof Language for Neural Theorem Proving over Isabelle/HOL
Neural Theorem Proving (NTP) employs Large Language Models (LLMs) to automate formal proofs in proof assistants. While LLMs have achieved relatively remarkable success in informal reasoning tasks using natural languages, the transition to mechanized formal theorem proving presents persistent challenges. Mechanized proof languages often contain many syntactic constructs and diverse, specialized proof tactics, which facilitate expert use but have no direct counterpart in informal mathematical proofs. These prover-specific idioms represent an additional burden for LLM-based NTPs that might be otherwise successful in generating informal proofs. Seeking to bridge this gap between formal proof construction and informal reasoning, in order to better facilitate NTP, this work approaches these challenges from a language design perspective. We look at common reasoning patterns in informal proofs and in existing mechanized proofs, and design Minilang (formally named Isabelle/Minilang), a minimalist proof language that captures these reasoning patterns. In contrast to proof languages (informal and formal) that often feature a large collection of operations with unclear semantic boundaries, Minilang is deliberately kept minimalist --- its core design comprises only 10 proof operations, each with clear semantic distinctions. We further develop a rule-based translator from Isabelle's proof language (Isar) to Minilang, translating ~340,000 existing Isabelle proofs with an ~85% success rate. Using this translated corpus, we finetune two LLMs to compare machine learning performance on Minilang versus the original Isar language. Experiments show Minilang benefits the two LLMs by improving the pass@1 success rate on the PISA benchmark by up to 20/29 percentage points in comparison to the Isar-based LLMs w/wo Sledgehammer. The pass@1 rate reaches 69.1%, exceeding the prior work Baldur's pass@64 (65.7%); the pass@8 rate reaches 79.2%, exceeding the state-of-the-art on PISA (71.0%) achieved by Magnushammer.
- 10 April 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Programming Languages
- Vol. 10 (OOPSLA1) , 2073-2098
Open AccessA Minimalist Proof Language for Neural Theorem Proving over Isabelle/HOL
Neural Theorem Proving (NTP) employs Large Language Models (LLMs) to automate formal proofs in proof assistants. While LLMs have achieved relatively remarkable success in informal reasoning tasks using natural languages, the transition to mechanized formal theorem proving presents persistent challenges. Mechanized proof languages often contain many syntactic constructs and diverse, specialized proof tactics, which facilitate expert use but have no direct counterpart in informal mathematical proofs. These prover-specific idioms represent an additional burden for LLM-based NTPs that might be otherwise successful in generating informal proofs. Seeking to bridge this gap between formal proof construction and informal reasoning, in order to better facilitate NTP, this work approaches these challenges from a language design perspective. We look at common reasoning patterns in informal proofs and in existing mechanized proofs, and design Minilang (formally named Isabelle/Minilang), a minimalist proof language that captures these reasoning patterns. In contrast to proof languages (informal and formal) that often feature a large collection of operations with unclear semantic boundaries, Minilang is deliberately kept minimalist --- its core design comprises only 10 proof operations, each with clear semantic distinctions. We further develop a rule-based translator from Isabelle's proof language (Isar) to Minilang, translating ~340,000 existing Isabelle proofs with an ~85% success rate. Using this translated corpus, we finetune two LLMs to compare machine learning performance on Minilang versus the original Isar language. Experiments show Minilang benefits the two LLMs by improving the pass@1 success rate on the PISA benchmark by up to 20/29 percentage points in comparison to the Isar-based LLMs w/wo Sledgehammer. The pass@1 rate reaches 69.1%, exceeding the prior work Baldur's pass@64 (65.7%); the pass@8 rate reaches 79.2%, exceeding the state-of-the-art on PISA (71.0%) achieved by Magnushammer.
- Open Access
- 9 October 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Programming Languages
- Vol. 9 (OOPSLA2) , 1809-1836
Structural Abstraction and Refinement for Probabilistic Programs
In this paper, we present structural abstraction refinement, a novel framework for verifying the threshold problem of probabilistic programs. Our approach represents the structure of a Probabilistic Control-Flow Automaton (PCFA) as a Markov Decision Process (MDP) by abstracting away statement semantics. The maximum reachability of the MDP naturally provides a proper upper bound of the violation probability, termed the structural upper bound . This introduces a fresh “structural” characterization of the relationship between PCFA and MDP, contrasting with the traditional “semantical” view, where the MDP reflects semantics. The method uniquely features a clean separation of concerns between probability and computational semantics that the abstraction focuses solely on probabilistic computation and the refinement handles only the semantics aspect, where the latter allows non-random program verification techniques to be employed without modification. Building upon this feature, we propose a general counterexample-guided abstraction refinement (CEGAR) framework, capable of leveraging established non-probabilistic techniques for probabilistic verification. We explore its instantiations using trace abstraction. Our method was evaluated on a diverse set of examples against state-of-the-art tools, and the experimental results highlight its versatility and ability to handle more flexible structures swiftly.
- 9 October 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Programming Languages
- Vol. 9 (OOPSLA2) , 1809-1836
Open AccessStructural Abstraction and Refinement for Probabilistic Programs
In this paper, we present structural abstraction refinement, a novel framework for verifying the threshold problem of probabilistic programs. Our approach represents the structure of a Probabilistic Control-Flow Automaton (PCFA) as a Markov Decision Process (MDP) by abstracting away statement semantics. The maximum reachability of the MDP naturally provides a proper upper bound of the violation probability, termed the structural upper bound . This introduces a fresh “structural” characterization of the relationship between PCFA and MDP, contrasting with the traditional “semantical” view, where the MDP reflects semantics. The method uniquely features a clean separation of concerns between probability and computational semantics that the abstraction focuses solely on probabilistic computation and the refinement handles only the semantics aspect, where the latter allows non-random program verification techniques to be employed without modification. Building upon this feature, we propose a general counterexample-guided abstraction refinement (CEGAR) framework, capable of leveraging established non-probabilistic techniques for probabilistic verification. We explore its instantiations using trace abstraction. Our method was evaluated on a diverse set of examples against state-of-the-art tools, and the experimental results highlight its versatility and ability to handle more flexible structures swiftly.
- 21 June 2025
- Published by Elsevier in Neural Networks
- Vol. 190, 107749
ATA: An Abstract-Train-Abstract approach for explanation-friendly deep reinforcement learning
- 21 June 2025
- Published by Elsevier in Neural Networks
- Vol. 190, 107749
ATA: An Abstract-Train-Abstract approach for explanation-friendly deep reinforcement learning
- Open Access
- 25 July 2024
- Published by Springer Nature
- p. 401-426
Unifying Qualitative and Quantitative Safety Verification of DNN-Controlled Systems
The rapid advance of deep reinforcement learning techniques enables the oversight of safety-critical systems through the utilization of Deep Neural Networks (DNNs). This underscores the pressing need to promptly establish certified safety guarantees for such DNN-controlled systems. Most of the existing verification approaches rely on qualitative approaches, predominantly employing reachability analysis. However, qualitative verification proves inadequate for DNN-controlled systems as their behaviors exhibit stochastic tendencies when operating in open and adversarial environments. In this paper, we propose a novel framework for unifying both qualitative and quantitative safety verification problems of DNN-controlled systems. This is achieved by formulating the verification tasks as the synthesis of valid neural barrier certificates (NBCs). Initially, the framework seeks to establish almost-sure safety guarantees through qualitative verification. In cases where qualitative verification fails, our quantitative verification method is invoked, yielding precise lower and upper bounds on probabilistic safety across both infinite and finite time horizons. To facilitate the synthesis of NBCs, we introduce theirk-inductive variants. We also devise a simulation-guided approach for training NBCs, aiming to achieve tightness in computing precise certified lower and upper bounds. We prototype our approach into a tool called and showcase its efficacy on four classic DNN-controlled systems.
- 25 July 2024
- Published by Springer Nature
- p. 401-426
Open AccessUnifying Qualitative and Quantitative Safety Verification of DNN-Controlled Systems
The rapid advance of deep reinforcement learning techniques enables the oversight of safety-critical systems through the utilization of Deep Neural Networks (DNNs). This underscores the pressing need to promptly establish certified safety guarantees for such DNN-controlled systems. Most of the existing verification approaches rely on qualitative approaches, predominantly employing reachability analysis. However, qualitative verification proves inadequate for DNN-controlled systems as their behaviors exhibit stochastic tendencies when operating in open and adversarial environments. In this paper, we propose a novel framework for unifying both qualitative and quantitative safety verification problems of DNN-controlled systems. This is achieved by formulating the verification tasks as the synthesis of valid neural barrier certificates (NBCs). Initially, the framework seeks to establish almost-sure safety guarantees through qualitative verification. In cases where qualitative verification fails, our quantitative verification method is invoked, yielding precise lower and upper bounds on probabilistic safety across both infinite and finite time horizons. To facilitate the synthesis of NBCs, we introduce theirk-inductive variants. We also devise a simulation-guided approach for training NBCs, aiming to achieve tightness in computing precise certified lower and upper bounds. We prototype our approach into a tool called and showcase its efficacy on four classic DNN-controlled systems.
- Open Access
- 20 June 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Programming Languages
- Vol. 8 (PLDI) , 1361-1386
Static Posterior Inference of Bayesian Probabilistic Programming via Polynomial Solving
In Bayesian probabilistic programming, a central problem is to estimate the normalised posterior distribution (NPD) of a probabilistic program with conditioning via score (a.k.a. observe ) statements. Most previous approaches address this problem by Markov Chain Monte Carlo and variational inference, and therefore could not generate guaranteed outcomes within a finite time limit. Moreover, existing methods for exact inference either impose syntactic restrictions or cannot guarantee successful inference in general. In this work, we propose a novel automated approach to derive guaranteed bounds for NPD via polynomial solving. We first establish a fixed-point theorem for the wide class of score-at-end Bayesian probabilistic programs that terminate almost-surely and have a single bounded score statement at program termination. Then, we propose a multiplicative variant of Optional Stopping Theorem (OST) to address score-recursive Bayesian programs where score statements with weights greater than one could appear inside a loop. Bayesian nonparametric models, enjoying a renaissance in statistics and machine learning, can be represented by score-recursive Bayesian programs and are difficult to handle due to an integrability issue. Finally, we use polynomial solving to implement our fixed-point theorem and OST variant. To improve the accuracy of the polynomial solving, we further propose a truncation operation and the synthesis of multiple bounds over various program inputs. Our approach can handle Bayesian probabilistic programs with unbounded while loops and continuous distributions with infinite supports. Experiments over a wide range of benchmarks show that compared with the most relevant approach (Beutner et al. , PLDI 2022) for guaranteed NPD analysis via recursion unrolling, our approach is more time efficient and derives comparable or even tighter NPD bounds. Furthermore, our approach can handle score-recursive programs which previous approaches could not.
- 20 June 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Programming Languages
- Vol. 8 (PLDI) , 1361-1386
Open AccessStatic Posterior Inference of Bayesian Probabilistic Programming via Polynomial Solving
In Bayesian probabilistic programming, a central problem is to estimate the normalised posterior distribution (NPD) of a probabilistic program with conditioning via score (a.k.a. observe ) statements. Most previous approaches address this problem by Markov Chain Monte Carlo and variational inference, and therefore could not generate guaranteed outcomes within a finite time limit. Moreover, existing methods for exact inference either impose syntactic restrictions or cannot guarantee successful inference in general. In this work, we propose a novel automated approach to derive guaranteed bounds for NPD via polynomial solving. We first establish a fixed-point theorem for the wide class of score-at-end Bayesian probabilistic programs that terminate almost-surely and have a single bounded score statement at program termination. Then, we propose a multiplicative variant of Optional Stopping Theorem (OST) to address score-recursive Bayesian programs where score statements with weights greater than one could appear inside a loop. Bayesian nonparametric models, enjoying a renaissance in statistics and machine learning, can be represented by score-recursive Bayesian programs and are difficult to handle due to an integrability issue. Finally, we use polynomial solving to implement our fixed-point theorem and OST variant. To improve the accuracy of the polynomial solving, we further propose a truncation operation and the synthesis of multiple bounds over various program inputs. Our approach can handle Bayesian probabilistic programs with unbounded while loops and continuous distributions with infinite supports. Experiments over a wide range of benchmarks show that compared with the most relevant approach (Beutner et al. , PLDI 2022) for guaranteed NPD analysis via recursion unrolling, our approach is more time efficient and derives comparable or even tighter NPD bounds. Furthermore, our approach can handle score-recursive programs which previous approaches could not.
- Open Access
Unifying Qualitative and Quantitative Safety Verification of DNN-Controlled Systems
The rapid advance of deep reinforcement learning techniques enables the oversight of safety-critical systems through the utilization of Deep Neural Networks (DNNs). This underscores the pressing need to promptly establish certified safety guarantees for such DNN-controlled systems. Most of the existing verification approaches rely on qualitative approaches, predominantly employing reachability analysis. However, qualitative verification proves inadequate for DNN-controlled systems as their behaviors exhibit stochastic tendencies when operating in open and adversarial environments. In this paper, we propose a novel framework for unifying both qualitative and quantitative safety verification problems of DNN-controlled systems. This is achieved by formulating the verification tasks as the synthesis of valid neural barrier certificates (NBCs). Initially, the framework seeks to establish almost-sure safety guarantees through qualitative verification. In cases where qualitative verification fails, our quantitative verification method is invoked, yielding precise lower and upper bounds on probabilistic safety across both infinite and finite time horizons. To facilitate the synthesis of NBCs, we introduce their $k$-inductive variants. We also devise a simulation-guided approach for training NBCs, aiming to achieve tightness in computing precise certified lower and upper bounds. We prototype our approach into a tool called $\textsf{UniQQ}$ and showcase its efficacy on four classic DNN-controlled systems.Open AccessUnifying Qualitative and Quantitative Safety Verification of DNN-Controlled Systems
The rapid advance of deep reinforcement learning techniques enables the oversight of safety-critical systems through the utilization of Deep Neural Networks (DNNs). This underscores the pressing need to promptly establish certified safety guarantees for such DNN-controlled systems. Most of the existing verification approaches rely on qualitative approaches, predominantly employing reachability analysis. However, qualitative verification proves inadequate for DNN-controlled systems as their behaviors exhibit stochastic tendencies when operating in open and adversarial environments. In this paper, we propose a novel framework for unifying both qualitative and quantitative safety verification problems of DNN-controlled systems. This is achieved by formulating the verification tasks as the synthesis of valid neural barrier certificates (NBCs). Initially, the framework seeks to establish almost-sure safety guarantees through qualitative verification. In cases where qualitative verification fails, our quantitative verification method is invoked, yielding precise lower and upper bounds on probabilistic safety across both infinite and finite time horizons. To facilitate the synthesis of NBCs, we introduce their $k$-inductive variants. We also devise a simulation-guided approach for training NBCs, aiming to achieve tightness in computing precise certified lower and upper bounds. We prototype our approach into a tool called $\textsf{UniQQ}$ and showcase its efficacy on four classic DNN-controlled systems. - Open Access
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (18) , 19992-20000
Robustness Verification of Deep Reinforcement Learning Based Control Systems Using Reward Martingales
Deep Reinforcement Learning (DRL) has gained prominence as an effective approach for control systems. However, its practical deployment is impeded by state perturbations that can severely impact system performance. Addressing this critical challenge requires robustness verification about system performance, which involves tackling two quantitative questions: (i) how to establish guaranteed bounds for expected cumulative rewards, and (ii) how to determine tail bounds for cumulative rewards. In this work, we present the first approach for robustness verification of DRL-based control systems by introducing reward martingales, which offer a rigorous mathematical foundation to characterize the impact of state perturbations on system performance in terms of cumulative rewards. Our verified results provide provably quantitative certificates for the two questions. We then show that reward martingales can be implemented and trained via neural networks, against different types of control policies. Experimental results demonstrate that our certified bounds tightly enclose simulation outcomes on various DRL-based control systems, indicating the effectiveness and generality of the proposed approach.
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (18) , 19992-20000
Open AccessRobustness Verification of Deep Reinforcement Learning Based Control Systems Using Reward Martingales
Deep Reinforcement Learning (DRL) has gained prominence as an effective approach for control systems. However, its practical deployment is impeded by state perturbations that can severely impact system performance. Addressing this critical challenge requires robustness verification about system performance, which involves tackling two quantitative questions: (i) how to establish guaranteed bounds for expected cumulative rewards, and (ii) how to determine tail bounds for cumulative rewards. In this work, we present the first approach for robustness verification of DRL-based control systems by introducing reward martingales, which offer a rigorous mathematical foundation to characterize the impact of state perturbations on system performance in terms of cumulative rewards. Our verified results provide provably quantitative certificates for the two questions. We then show that reward martingales can be implemented and trained via neural networks, against different types of control policies. Experimental results demonstrate that our certified bounds tightly enclose simulation outcomes on various DRL-based control systems, indicating the effectiveness and generality of the proposed approach.