Author name cluster

Ming Xu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

15 papers

2 author rows

TCS Journal 2026 Journal Article

A quantum game designed for property partitioning with implementation on superconducting quantum processors

Hui Jiang
Jianling Fu
Ming Xu
Ji Guan
Shenggang Ying

This paper considers the partitioning property problem, which is a game between two players that determines the winner through communications. Our quantum solution seeks three goals — fairness, binding, and sealing. The latter two demonstrate the superiority of quantum computing over classical counterpart. Inspired by the BB84 protocol, we first achieve fairness by independent quantum measures. Binding or sealing follows, not both, which results in a quantum bit escrow. We implement the game respectively in a simple and in a parametric setting with the quantum programming language isQ on a quantum simulator, whose results are the benchmarks to those on quantum processors. From the experimental results, the optimal policies are synthesized for the two players in the game. Besides, an interactive game named PPT is designed to enhance the enjoyment of quantum computing. Finally, we run the simple game on two superconducting quantum processors ARCLIGHT and Quafu, by which the experimental results validate the benchmarks well. With quantum error correction in the NISQ era, the proposed quantum protocols are believed to be promising in future social and economic fields.

Details DOI

IROS Conference 2025 Conference Paper

Accelerating Inverse Kinematic Solutions for a Cable-Driven Soft Robotic Manipulator via Physics-Informed Neural Network

Rui Lin
Shuyou He
Ming Xu
Kangjia Fu
Xuesong Wu
Xiucong Sun
Qi Zhang
Sunquan Yu

Cable-driven soft manipulators, with inherent compliance and hyper-redundancy, offer significant advantages in unstructured environments but present formidable challenges in modeling of inverse kinematics due to nonlinear deformations and underactuation. In this paper, building on a modified forward kinematic model, a physics-informed neural networks (PINN) framework based on spatiotemporal data is proposed for efficient inverse kinematics computation of cable-driven soft robotic manipulators. A geometrically exact forward kinematic model is constructed under the Piecewise Constant Curvature (PCC) assumption, extended to multi-section configurations, and enhanced by cable deflection compensation to account for practical routing constraints. Experimental validation shows a 40. 11% reduction in end-effector positioning error (average 15. 98 mm) when deflection effects are included. The proposed PINN architecture takes time and section count as inputs and outputs the corresponding manipulator configuration, enabling unified spatiotemporal trajectory tracking by minimizing elastic energy while satisfying kinematic constraints. Compared to particle swarm optimization (PSO), which requires iterative computation for each trajectory sample, the proposed method reduces computational time by over 71. 9%, demonstrating superior efficiency in solving redundant inverse kinematics problems. This work bridges data-driven and mechanics-based approaches, offering a scalable solution for real-time control of soft manipulators.

Details

ICLR Conference 2025 Conference Paper

BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions

Terry Yue Zhuo
Minh Chien Vu
Jenny Chim
Han Hu 0011
Wenhao Yu 0002
Ratnadira Widyasari
Imam Nur Bani Yusuf
Haolan Zhan

Task automation has been greatly empowered by the recent advances in Large Language Models (LLMs) via Python code, where the tasks range from software engineering development to general-purpose reasoning. While current benchmarks have shown that LLMs can solve tasks using programs like human developers, the majority of their evaluations are limited to short and self-contained algorithmic tasks or standalone function calls. Solving challenging and practical tasks requires the capability of utilizing **diverse function calls as tools** to efficiently implement functionalities like data analysis and web development. In addition, using multiple tools to solve a task needs compositional reasoning by accurately understanding **complex instructions**. Fulfilling both of these characteristics can pose a great challenge for LLMs. To assess how well LLMs can solve challenging and practical tasks via programs, we introduce BigCodeBench, a benchmark that challenges LLMs to invoke multiple function calls as tools from 139 libraries and 7 domains for 1,140 fine-grained tasks. To evaluate LLMs rigorously, each task encompasses 5.6 test cases with an average branch coverage of 99%. In addition, we propose a natural-language-oriented variant of BigCodeBench, BigCodeBench-Instruct, that automatically transforms the original docstrings into short instructions containing only essential information. Our extensive evaluation of 60 LLMs shows that **LLMs are not yet capable of following complex instructions to use function calls precisely, with scores up to 60%, significantly lower than the human performance of 97%**. The results underscore the need for further advancements in this area.

Details

NeurIPS Conference 2025 Conference Paper

ObCLIP: Oblivious CLoud-Device Hybrid Image Generation with Privacy Preservation

Haoqi Wu
Wei Dai
Ming Xu
Wang Li
Qiang Yan

Diffusion Models have gained significant popularity due to their remarkable capabilities in image generation, albeit at the cost of intensive computation requirement. Meanwhile, despite their widespread deployment in inference services such as Midjourney, concerns about the potential leakage of sensitive information in uploaded user prompts have arisen. Existing solutions either fail to strike an effective balance between utility and efficiency, or lack rigorous privacy guarantees. To bridge this gap, we propose ObCLIP, a plug-and-play safeguard that enables oblivious cloud-device hybrid generation scheme. By oblivious, each input prompt is transformed into a set of semantically similar candidate prompts that differ only in sensitive attributes (e. g. , gender, ethnicity). The cloud server processes all candidate prompts without knowing which one is the real one, thus preventing any prompt leakage. To mitigate server cost, only a small portion of denoising steps is performed upon the large cloud model. The resulting intermediate latents are then transmitted back to the device, which selects the targeted latent and completes the remaining denoising using a small local model to obtain the final image. Additionally, we analyze and incorporate several cache-based accelerations that leverage temporal and batch redundancy, effectively reducing computation cost with minimal utility degradation. Extensive experiments across multiple datasets demonstrate that ObCLIP provides rigorous privacy and comparable utility to large cloud models with slightly increased server computation.

PDF Details

NeurIPS Conference 2024 Conference Paper

Molecule Design by Latent Prompt Transformer

Deqian Kong
Yuhao Huang
Jianwen Xie
Edouardo Honig
Ming Xu
Shuanghong Xue
Pei Lin
Sanping Zhou

This work explores the challenging problem of molecule design by framing it as a conditional generative modeling task, where target biological properties or desired chemical constraints serve as conditioning variables. We propose the Latent Prompt Transformer (LPT), a novel generative model comprising three components: (1) a latent vector with a learnable prior distribution modeled by a neural transformation of Gaussian white noise; (2) a molecule generation model based on a causal Transformer, which uses the latent vector as a prompt; and (3) a property prediction model that predicts a molecule's target properties and/or constraint values using the latent prompt. LPT can be learned by maximum likelihood estimation on molecule-property pairs. During property optimization, the latent prompt is inferred from target properties and constraints through posterior sampling and then used to guide the autoregressive molecule generation. After initial training on existing molecules and their properties, we adopt an online learning algorithm to progressively shift the model distribution towards regions that support desired target properties. Experiments demonstrate that LPT not only effectively discovers useful molecules across single-objective, multi-objective, and structure-constrained optimization tasks, but also exhibits strong sample efficiency.

PDF Details DOI

IJCAI Conference 2023 Conference Paper

Deep Unfolding Convolutional Dictionary Model for Multi-Contrast MRI Super-resolution and Reconstruction

Pengcheng Lei
Faming Fang
Guixu Zhang
Ming Xu

Magnetic resonance imaging (MRI) tasks often involve multiple contrasts. Recently, numerous deep learning-based multi-contrast MRI super-resolution (SR) and reconstruction methods have been proposed to explore the complementary information from the multi-contrast images. However, these methods either construct parameter-sharing networks or manually design fusion rules, failing to accurately model the correlations between multi-contrast images and lacking certain interpretations. In this paper, we propose a multi-contrast convolutional dictionary (MC-CDic) model under the guidance of the optimization algorithm with a well-designed data fidelity term. Specifically, we bulid an observation model for the multi-contrast MR images to explicitly model the multi-contrast images as common features and unique features. In this way, only the useful information in the reference image can be transferred to the target image, while the inconsistent information will be ignored. We employ the proximal gradient algorithm to optimize the model and unroll the iterative steps into a deep CDic model. Especially, the proximal operators are replaced by learnable ResNet. In addition, multi-scale dictionaries are introduced to further improve the model performance. We test our MC-CDic model on multi-contrast MRI SR and reconstruction tasks. Experimental results demonstrate the superior performance of the proposed MC-CDic model against existing SOTA methods. Code is available at https: //github. com/lpcccc-cv/MC-CDic.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Revisiting Implicit Differentiation for Learning Problems in Optimal Control

Ming Xu
Timothy L. Molloy
Stephen Gould

This paper proposes a new method for differentiating through optimal trajectories arising from non-convex, constrained discrete-time optimal control (COC) problems using the implicit function theorem (IFT). Previous works solve a differential Karush-Kuhn-Tucker (KKT) system for the trajectory derivative, and achieve this efficiently by solving an auxiliary Linear Quadratic Regulator (LQR) problem. In contrast, we directly evaluate the matrix equations which arise from applying variable elimination on the Lagrange multiplier terms in the (differential) KKT system. By appropriately accounting for the structure of the terms within the resulting equations, we show that the trajectory derivatives scale linearly with the number of timesteps. Furthermore, our approach allows for easy parallelization, significantly improved scalability with model size, direct computation of vector-Jacobian products and improved numerical stability compared to prior works. As an additional contribution, we unify prior works, addressing claims that computing trajectory derivatives using IFT scales quadratically with the number of timesteps. We evaluate our method on a both synthetic benchmark and four challenging, learning from demonstration benchmarks including a 6-DoF maneuvering quadrotor and 6-DoF rocket powered landing.

PDF Details

EAAI Journal 2023 Journal Article

Temporal transaction information-aware Ponzi scheme detection for ethereum smart contracts

Lei Wang
Hao Cheng
Zibin Zheng
Aijun Yang
Ming Xu

In recent years, the frenetic advances of blockchain techniques have promoted the large-scale application of cryptocurrency and attracted significant attention in the mushrooming applications of decentralized finance (DeFi). To guarantee the health of a DeFi ecosystem, it is critical to reduce the transaction risks in a DeFi system. In particular, as a representative DeFi ecosystem platform, Ethereum’s transaction process is mainly carried out with the help of smart contracts. Due to (pseudo)anonymity, the transaction process of Ethereum users is challenged by severe fraud threats. Ponzi scheme is the typical one. Previous studies have used machine learning methods to build Ponzi scheme detection models based on learning from the identified static smart contract samples feature data. However, in the early stage of smart contract deployment, the Ponzi scheme is difficult to detect. With the progress of transactions, Ponzi scheme will gradually show its characteristics. The existing methods are still falling short in capturing the temporal features of smart contracts for detecting Ponzi schemes in the big data environment. The recognition rate of the current approaches needs to be further improved. In this paper, we propose TTPS, a Long Short-Term Memory (LSTM) Ponzi scheme detection method considering time series transaction information of smart contracts. TTPS considers both temporal account features and code features of smart contracts. Adaptive synthetic sampling (ADASYN) is employed to effectively extend the feature data of minority class Ponzi scheme small samples. LSTM is utilized to learn from the temporal feature data of Ponzi scheme samples for TTPS model training. Experimental results verify and demonstrate the effectiveness and efficiency of TTPS.

Details DOI

AAAI Conference 2023 Conference Paper

Two Wrongs Don’t Make a Right: Combating Confirmation Bias in Learning with Label Noise

MingCai Chen
Hao Cheng
Yuntao Du
Ming Xu
Wenyu Jiang
Chongjun Wang

Noisy labels damage the performance of deep networks. For robust learning, a prominent two-stage pipeline alternates between eliminating possible incorrect labels and semi-supervised training. However, discarding part of noisy labels could result in a loss of information, especially when the corruption has a dependency on data, e.g., class-dependent or instance-dependent. Moreover, from the training dynamics of a representative two-stage method DivideMix, we identify the domination of confirmation bias: pseudo-labels fail to correct a considerable amount of noisy labels, and consequently, the errors accumulate. To sufficiently exploit information from noisy labels and mitigate wrong corrections, we propose Robust Label Refurbishment (Robust LR)—a new hybrid method that integrates pseudo-labeling and confidence estimation techniques to refurbish noisy labels. We show that our method successfully alleviates the damage of both label noise and confirmation bias. As a result, it achieves state-of-the-art performance across datasets and noise types, namely CIFAR under different levels of synthetic noise and mini-WebVision and ANIMAL-10N with real-world noise.

PDF Details DOI

TCS Journal 2022 Journal Article

An algebraic method to fidelity-based model checking over quantum Markov chains

Ming Xu
Jianling Fu
Jingyi Mei
Yuxin Deng

Fidelity is one of the most widely used quantities in quantum information that measures the distance of two quantum states through a noisy channel, a kind of quantum operations. In this paper, we consider the model of quantum Markov chain (QMC), in which transitions are weighted by super-operators to characterize quantum operations and the initial quantum state is left parametric. A quantum analogy of probabilistic computation tree logic, called QCTL, is introduced to take into account fidelity, instead of probability measure, over QMC. The key to the model checking problem lies in computing the fidelity of the super-operator valued measure specified by a path formula in QCTL. It is minimized over all initial quantum states, which is intended for analyzing the system performance in the worst case. We achieve it by a reduction to quantifier elimination in the existential theory of the reals. The method is absolutely exact, so that model checking QCTL formulas against QMCs is proved to be decidable in exponential time.

Details DOI

TCS Journal 2022 Journal Article

Model checking QCTL plus on quantum Markov chains

Ming Xu
Jianling Fu
Jingyi Mei
Yuxin Deng

Verifying temporal properties of quantum systems, including quantum Markov chains (QMCs), has attracted an increasing interest in the last decade. Typically, the properties are specified by quantum computation tree logic (QCTL), in which reachability analysis plays a central role. However, safety as the dual problem is known little. Motivated by this, we propose a more expressive logic — QCTL+ (QCTL plus), which extends QCTL by allowing the conjunction in path formulas and the negation in the top level of path formulas. The former can be adopted to express conditional events, and the latter can express safety. To deal with conjunction, we present a product construction of classical states in the QMC and the tri-valued truths of atomic path formulas; to deal with negation, we develop an algebraic approach to compute the safety of the bottom strongly connected component subspaces with respect to a super-operator under some necessary and sufficient convergence conditions. Thereby we conditionally decide QCTL+ formulas over QMCs; without the convergence conditions the safety problem still remains open. The complexity of our method is provided in terms of the size of both the input QMC and the QCTL+ formula.

Details DOI

EAAI Journal 2020 Journal Article

Refraction-learning-based whale optimization algorithm for high-dimensional problems and parameter estimation of PV model

Wen Long
Tiebin Wu
Jianjun Jiao
Mingzhu Tang
Ming Xu

Whale optimization algorithm (WOA) is a relatively new meta-heuristic optimization algorithm which mimics the hunting behavior of humpback whales. This paper presents a modified version of WOA, called RLWOA, for solving high-dimensional optimization problems. The proposed RLWOA adopts a modified conversion parameter update rule that relies on Logistic model to balance between diversity and convergence during the search process, and a new refraction-learning strategy based on the principle of refraction of light is proposed to help the population jump out of a local optimum. The experiments on a set of benchmark test functions with various features, i. e. , 12 widely used benchmark functions with 100, 1000, and 10000 dimensions, two practical engineering design problems, and parameter estimation problem of photovoltaic model. The comparisons demonstrate that the proposed RLWOA shows better or at least competitive performance against the standard WOA, WOA variants and other state-of-the-art meta-heuristic algorithms for solving high-dimensional numerical optimization, practical engineering design optimization, and photovoltaic model parameter estimation problems.

Details DOI

I&C Journal 2020 Journal Article

Time-bounded termination analysis for probabilistic programs with delays

Ming Xu
Yuxin Deng

This paper investigates the model of probabilistic program with delays (PPD) that consists of a few program blocks. Performing each block has an additional time-consumption—waiting to be executed—besides the running time. We interpret the operational semantics of PPD by Markov automata with a cost structure on transitions. Our goal is to measure those individual execution paths of a PPD that terminates within a given time bound, and to compute the minimum termination probability, i. e. the termination probability under a demonic scheduler that resolves the nondeterminism inherited from probabilistic programs. When running time plus waiting time is bounded, the demonic scheduler can be determined by comparison between a class of well-formed real numbers. The method is extended to parametric PPDs. When only the running time is bounded, the demonic scheduler can be determined by real root isolation over a class of well-formed real functions under Schanuel's conjecture. Finally we give the complexity upper bounds of the proposed methods.

Details DOI

TCS Journal 2016 Journal Article

Analyzing ultimate positivity for solvable systems

Ming Xu
Cheng-Chao Huang
Zhi-Bin Li
Zhenbing Zeng

The positivity problem is a foundational decision problem. It asks whether a dynamical system would keep the observing expression (over its states) positive. It has a derivative—the ultimate positivity problem, which allows that the observing expression is non-positive within a bounded time interval. For the two problems, most existing results are established on discrete-time dynamical systems, specifically on linear recurrence sequences. In this paper, however, we study the ultimate positivity problem for a class of continuous-time dynamical systems, called solvable systems. They subsume linear systems. For the general solvable system, we present a sufficient condition for inferring ultimate positivity. The validity of the condition can be algorithmically checked. Once it is valid, we can further find the time threshold, after which the observing expression would be always positive. On the other hand, we show that the ultimate positivity problem is decidable for some special classes of solvable systems, such as linear systems of dimension up to five.

Details DOI

TCS Journal 2016 Journal Article

Multiphase until formulas over Markov reward models: An algebraic approach

Ming Xu
Lijun Zhang
David N. Jansen
Huibiao Zhu
Zongyuan Yang

We consider the probabilistic model checking problem of continuous-time Markov chains with rewards. We first extend multiphase until formulas in continuous stochastic logic (CSL) with reward constraints. Then we present an effective integral-style algorithm to compute the probability under the assumption of harmony, and give upper and lower bounds of the probability without this assumption. Furthermore, the resulting probability value (or its upper and lower bounds) is shown to be a real number of a well-formed structure, with which we can successfully (or partially) decide whether the constraints in the CSL formula are satisfied. Our method is entirely based on algebraic manipulations and number theory. Finally, to show the practical usefulness, we apply the results to evaluate the performance of a small multi-processor system.

Details DOI