Author name cluster

Minghao Liu

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.

18 papers

2 author rows

FM Conference 2026 Conference Paper

Exact Verification of Graph Neural Networks with Incremental Constraint Solving

Minghao Liu
Chia-Hsuan Lu
Marta Kwiatkowska

Abstract Graph neural networks (GNNs) are increasingly often employed in high-stakes applications, such as fraud detection or healthcare, but are susceptible to adversarial attacks. A number of techniques have been proposed to provide adversarial robustness guarantees, but support for commonly used aggregation functions in message-passing GNNs is lacking. In this paper, we develop an exact (sound and complete) verification method for GNNs to compute guarantees against attribute and structural perturbations that involve edge addition or deletion, subject to budget constraints. Our method employs constraint solving with bound tightening, and iteratively solves a sequence of relaxed constraint satisfaction problems while relying on incremental solving capabilities of solvers to improve efficiency. We implement GNNev, a versatile exact verifier for message-passing neural networks, which supports three aggregation functions – sum, max and mean – with the latter two considered here for the first time. Extensive experimental evaluation of GNNev on real-world fraud datasets (Amazon and Yelp) and biochemical datasets (MUTAG and ENZYMES) demonstrates its usability and effectiveness, as well as superior performance on node classification and competitiveness on graph classification compared to existing exact verification tools on sum-aggregated GNNs.

DOI

AAAI Conference 2025 Conference Paper

A Complete Algorithm for Optimization Modulo Nonlinear Real Arithmetic

Fuqi Jia
Yuhang Dong
Rui Han
Pei Huang
Minghao Liu
Feifei Ma
Jian Zhang

Optimization Modulo Nonlinear Real Arithmetic, abbreviated as OMT(NRA), generally focuses on optimizing a given objective subject to quantifier-free Boolean combinations of primitive constraints, including Boolean variables, polynomial equations, and inequalities. It is widely applicable in areas like program verification, analysis, planning, and so on. The existing solver, OptiMathSAT, officially supporting OMT(NRA), employs an incomplete algorithm. We present a sound and complete algorithm, Optimization Cylindrical Algebraic Covering (OCAC), integrated within the Conflict-Driven Clause Learning (CDCL) framework, specifically tailored for OMT(NRA) problems. We establish the correctness and termination of CDCL(OCAC) and explore alternative approaches using cylindrical algebraic decomposition (CAD) and first-order formulations. Our work includes the development of the first complete OMT solver for NRA, demonstrating significant performance improvements. In benchmarks generated from SMT-LIB instances, our algorithm finds the optimum value in about 150% more instances compared to the current leading solver, OptiMathSAT.

PDF Details DOI

ICML Conference 2025 Conference Paper

Falcon: Fast Visuomotor Policies via Partial Denoising

Haojun Chen
Minghao Liu
Chengdong Ma
Xiaojian Ma 0001
Zailin Ma
Huimin Wu 0001
Yuanpei Chen
Yifan Zhong

Diffusion policies are widely adopted in complex visuomotor tasks for their ability to capture multimodal action distributions. However, the multiple sampling steps required for action generation significantly harm real-time inference efficiency, which limits their applicability in real-time decision-making scenarios. Existing acceleration techniques either require retraining or degrade performance under low sampling steps. Here we propose Falcon, which mitigates this speed-performance trade-off and achieves further acceleration. The core insight is that visuomotor tasks exhibit sequential dependencies between actions. Falcon leverages this by reusing partially denoised actions from historical information rather than sampling from Gaussian noise at each step. By integrating current observations, Falcon reduces sampling steps while preserving performance. Importantly, Falcon is a training-free algorithm that can be applied as a plug-in to further improve decision efficiency on top of existing acceleration techniques. We validated Falcon in 48 simulated environments and 2 real-world robot experiments. demonstrating a 2-7x speedup with negligible performance degradation, offering a promising direction for efficient visuomotor policy design.

Details

NeurIPS Conference 2025 Conference Paper

GenIR: Generative Visual Feedback for Mental Image Retrieval

Diji Yang
Minghao Liu
Chung-Hsiang Lo
Yi Zhang
James Davis

Vision-language models (VLMs) have shown strong performance on text-to-image retrieval benchmarks. However, bridging this success to real-world applications remains a challenge. In practice, human search behavior is rarely a one-shot action. Instead, it is often a multi-round process guided by clues in mind. That is, a mental image ranging from vague recollections to vivid mental representations of the target image. Motivated by this gap, we study the task of Mental Image Retrieval (MIR), which targets the realistic yet underexplored setting where users refine their search for a mentally envisioned image through multi-round interactions with an image search engine. Central to successful interactive retrieval is the capability of machines to provide users with clear, actionable feedback; however, existing methods rely on indirect or abstract verbal feedback, which can be ambiguous, misleading, or ineffective for users to refine the query. To overcome this, we propose GenIR, a generative multi-round retrieval paradigm leveraging diffusion-based image generation to explicitly reify the AI system's understanding at each round. These synthetic visual representations provide clear, interpretable feedback, enabling users to refine their queries intuitively and effectively. We further introduce a fully automated pipeline to generate a high-quality multi-round MIR dataset. Experimental results demonstrate that GenIR significantly outperforms existing interactive methods in the MIR scenario. This work establishes a new task with a dataset and an effective generative retrieval method, providing a foundation for future research in this direction

PDF Details

AAAI Conference 2025 Conference Paper

Human and AI Perceptual Differences in Image Classification Errors

Minghao Liu
Jiaheng Wei
Yang Liu
James Davis

Artificial intelligence (AI) models for computer vision trained with supervised machine learning are assumed to solve classification tasks by imitating human behavior learned from training labels. Most efforts in recent vision research focus on measuring the model task performance using standardized benchmarks such as accuracy. However limited work has sought to understand the perceptual difference between humans and machines. To fill this gap, this study first analyzes the statistical distributions of mistakes from the two sources, and then explores how task difficulty level affects these distributions. We find that even when AI learns an excellent model from the training data, one that outperforms humans in overall accuracy, these AI models have significant and consistent differences from human perception. We demonstrate the importance of studying these differences with a simple human-AI teaming algorithm that outperforms humans alone, AI alone, or AI-AI teaming.

PDF Details DOI

IROS Conference 2025 Conference Paper

Kalib: Easy Hand-Eye Calibration with Reference Point Tracking

Tutian Tang
Minghao Liu
Wenqiang Xu
Cewu Lu

Hand-eye calibration aims to estimate the transformation between a camera and a robot. Traditional methods rely on fiducial markers, which require considerable manual effort and precise setup. Recent advances in deep learning have introduced markerless techniques but come with more prerequisites, such as retraining networks for each robot, and accessing accurate mesh models for data generation. In this paper, we propose Kalib, an automatic and easy-to-setup hand-eye calibration method that leverages the generalizability of visual foundation models to overcome these challenges. It features only two basic prerequisites, the robot’s kinematic chain and a predefined reference point on the robot. During calibration, the reference point is tracked in the camera space. Its corresponding 3D coordinates in the robot coordinate can be inferred by forward kinematics. Then, a PnP solver directly estimates the transformation between the camera and the robot without training new networks or accessing mesh models. Evaluations in simulated and real-world benchmarks show that Kalib achieves good accuracy with a lower manual workload compared with recent baseline methods. We also demonstrate its application in multiple real-world settings with various robot arms and grippers. Kalib’s user-friendly design and minimal setup requirements make it a possible solution for continuous operation in unstructured environments. The code, data, and supplementary materials are available at https://sites.google.com/view/hand-eye-kalib.

Details

NeurIPS Conference 2025 Conference Paper

MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix

Ziyang Ma
Yinghao Ma
Yanqiao Zhu
Chen Yang
Yi-Wen Chao
Ruiyang Xu
Wenxi Chen
Yuanzhe Chen

We introduce MMAR, a new benchmark designed to evaluate the deep reasoning capabilities of Audio-Language Models (ALMs) across massive multi-disciplinary tasks. MMAR comprises 1, 000 meticulously curated audio-question-answer triplets, collected from real-world internet videos and refined through iterative error corrections and quality checks to ensure high quality. Unlike existing benchmarks that are limited to specific domains of sound, music, or speech, MMAR extends them to a broad spectrum of real-world audio scenarios, including mixed-modality combinations of sound, music, and speech. Each question in MMAR is hierarchically categorized across four reasoning layers: Signal, Perception, Semantic, and Cultural, with additional sub-categories within each layer to reflect task diversity and complexity. To further foster research in this area, we annotate every question with a Chain-of-Thought (CoT) rationale to promote future advancements in audio reasoning. Each item in the benchmark demands multi-step deep reasoning beyond surface-level understanding. Moreover, a part of the questions requires graduate-level perceptual and domain-specific knowledge, elevating the benchmark's difficulty and depth. We evaluate MMAR using a broad set of models, including Large Audio-Language Models (LALMs), Large Audio Reasoning Models (LARMs), Omni Language Models (OLMs), Large Language Models (LLMs), and Large Reasoning Models (LRMs), with audio caption inputs. The performance of these models on MMAR highlights the benchmark's challenging nature, and our analysis further reveals critical limitations of understanding and reasoning capabilities among current models. These findings underscore the urgent need for greater research attention in audio-language reasoning, including both data and algorithm innovation. We hope MMAR will serve as a catalyst for future advances in this important but little-explored area.

PDF Details

AAAI Conference 2025 Conference Paper

Scalable Knowledge Refactoring Using Constrained Optimisation

Minghao Liu
David M. Cerna
Filipe Gouveia
Andrew Cropper

Knowledge refactoring compresses logic programs by replacing them with new rules. Current approaches struggle to scale to large programs. To overcome this limitation, we introduce a constrained optimisation refactoring approach. Our first key idea is to encode the problem with decision variables based on literals rather than rules. Our second key idea is to focus on linear invented rules. Our empirical results on multiple domains show that our approach can refactor programs quicker and with more compression than the previous state-of-the-art approach, sometimes by 60%.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

Xeron Du
Yifan Yao
Kaijing Ma
Bingli Wang
Tianyu Zheng
Minghao Liu
Yiming Liang
Xiaolong Jin

Large language models (LLMs) have demonstrated remarkable proficiency in mainstream academic disciplines such as mathematics, physics, and computer science. However, human knowledge encompasses over 200 specialized disciplines, far exceeding the scope of existing benchmarks. The capabilities of LLMs in many of these specialized fields-particularly in light industry, agriculture, and service-oriented disciplines-remain inadequately evaluated. To address this gap, we present SuperGPQA, a comprehensive benchmark that evaluates graduate-level knowledge and reasoning capabilities across 285 disciplines. Our benchmark employs a novel Human-LLM collaborative filtering mechanism to eliminate trivial or ambiguous questions through iterative refinement based on both LLM responses and expert feedback. Our experimental results reveal significant room for improvement in the performance of current state-of-the-art LLMs across diverse knowledge domains (e. g. , the reasoning-focused model Gemini-2. 5-Pro achieved the highest accuracy of 63. 56% on SuperGPQA), highlighting the considerable gap between current model capabilities and artificial general intelligence. Additionally, we present comprehensive insights from our management of a large-scale annotation process, involving over 80 expert annotators and an interactive Human-LLM collaborative system, offering valuable methodological guidance for future research initiatives of comparable scope.

PDF Details

AAAI Conference 2025 Conference Paper

UP-Restorer: When Unrolling Meets Prompts for Unified Image Restoration

Minghao Liu
Wenhan Yang
Jinyi Luo
Jiaying Liu

All-in-one restoration needs to implicitly distinguish between different degradation conditions and apply specific prior constraints accordingly. To fulfill this goal, our work makes the first effort to create an all-in-one restoration via unrolling from the typical maximum a-posterior optimization function. This unrolling framework naturally leads to the construction of progressively solving models, which are equivalent to a diffusion enhancer taking as input dynamically generated prompts. Under a score-based diffusion model, the prompts are integrated for propogating and updating several context-related variables, i.e. transmission map, atmospheric light map and noise or rain map progressively. Such learned prompt generation process, which simulates the nonlinear operations in the unrolled solution, is combined with linear operations owning clear physics implications to make the diffusion models well reguarlized and more effective in learning degradation-related visual priors. Experimental results demonstrate that our method achieves significant performance improvements across various image restoration tasks, realizing true all-in-one image restoration.

PDF Details DOI

EAAI Journal 2024 Journal Article

Regularized joint self-training: A cross-domain generalization method for image classification

Changlin Chen
Yukun Yang
Minghao Liu
Zhaomin Rong
Shuangbao Shu

Unsupervised domain adaptive (UDA) is a widely used approach in machine learning strategies that helps move information from a source domain with rich supervised data to a target domain with limited supervised data. In recent years, self-training derived from semi-supervised learning provides a powerful tool for unsupervised domain adaptive by training unlabeled target domain data using pseudo-tags. However, in the case of domain shift, the pseudo-labels generated by standard self-training are no longer reliable due to the influence of the class-distribution shift in a specific domain, resulting in the noise of the pseudo-label error blocking the upper bound of the accuracy. To solve these problems, a domain adaptive method based on regularization joint self-training (RJS) is proposed in this paper. RJS consists of two key steps: First, the generation and optimization of pseudo-tags are trained jointly on the source domain to achieve automatic cross-domain generalization of pseudo-tags. Secondly, the regularization method is introduced as a confidence rule for false labels in initial model training, which implicitly prevents the model from remembering false labels. To verify the effectiveness of the proposed method, experiments were performed on VisDA-2017, Office-31, Office-Home, and DomainNet datasets, and the accuracy rates reached 87. 1%, 89. 3%, 76. 9%, and 57. 3%, respectively. In addition, the average classification performance of RJS on VisDA-2017 improved by about 12. 6% compared to FixMatch, the standard self-training method. Experimental results demonstrate that RJS achieves state-of-the-art performance on multiple standard UDA benchmarks and confirm its effectiveness in the presence of domain-specific class distribution shifts.

Details DOI

ICML Conference 2024 Conference Paper

UP2ME: Univariate Pre-training to Multivariate Fine-tuning as a General-purpose Framework for Multivariate Time Series Analysis

Yunhao Zhang
Minghao Liu
Shengyang Zhou
Junchi Yan

Despite the success of self-supervised pre-training in texts and images, applying it to multivariate time series (MTS) falls behind tailored methods for tasks like forecasting, imputation and anomaly detection. We propose a general-purpose framework, named UP2ME ( U nivariate P re-training to M ultivariate Fin e -tuning). It conducts task-agnostic pre-training when downstream tasks are unspecified. Once the task and setting (e. g. forecasting length) are determined, it gives sensible solutions with frozen pre-trained parameters, which has not been achieved before. UP2ME is further refined by fine-tuning. A univariate-to-multivariate paradigm is devised to address the heterogeneity of temporal and cross-channel dependencies. In univariate pre-training, univariate instances with diverse lengths are generated for Masked AutoEncoder (MAE) pre-training, discarding cross-channel dependency. The pre-trained model handles downstream tasks by formulating them into specific mask-reconstruction problems. In multivariate fine-tuning, it constructs a dependency graph among channels using the pre-trained encoder to enhance cross-channel dependency capture. Experiments on eight real-world datasets show its SOTA performance in forecasting and imputation, approaching task-specific performance in anomaly detection. Our code is available at https: //github. com/Thinklab-SJTU/UP2ME.

Details

AAAI Conference 2023 Short Paper

Can Graph Neural Networks Learn to Solve the MaxSAT Problem? (Student Abstract)

Minghao Liu
Pei Huang
Fuqi Jia
Fan Zhang
Yuchen Sun
Shaowei Cai
Feifei Ma
Jian Zhang

The paper presents an attempt to bridge the gap between machine learning and symbolic reasoning. We build graph neural networks (GNNs) to predict the solution of the Maximum Satisfiability (MaxSAT) problem, an optimization variant of SAT. Two closely related graph representations are adopted, and we prove their theoretical equivalence. We also show that GNNs can achieve attractive performance to solve hard MaxSAT problems in certain distributions even compared with state-of-the-art solvers through experimental evaluation.

PDF Details DOI

IJCAI Conference 2023 Conference Paper

Dual Prompt Learning for Continual Rain Removal from Single Images

Minghao Liu
Wenhan Yang
Yuzhang Hu
Jiaying Liu

Recent efforts have achieved remarkable progress on single image deraining on the stationary distributed data. However, catastrophic forgetting raises practical concerns when applying these methods to real applications, where the data distributions change constantly. In this paper, we investigate the continual learning issue for rain removal and develop a novel efficient continual learned deraining transformer. Different from the typical replay or regularization-based methods that increase overall training time or parameter space, our method relies on compact prompts which are learnable parameters, to maintain both task-invariant and task-specific knowledge. Our prompts are applied at both image and feature levels to leverage effectively transferred knowledge of images and features among different tasks. We conduct comprehensive experiments under widely-used rain removal datasets, where our proposed dual prompt learning consistently outperforms prior state-of-the-art methods. Moreover, we observe that, even though our method is designed for continual learning, it still achieves superior results on the stationary distributed data, which further demonstrates the effectiveness of our method. Our website is available at: http: //liuminghao. com. cn/DPL/.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Suggesting Variable Order for Cylindrical Algebraic Decomposition via Reinforcement Learning

Fuqi Jia
Yuhang Dong
Minghao Liu
Pei Huang
Feifei Ma
Jian Zhang

Cylindrical Algebraic Decomposition (CAD) is one of the pillar algorithms of symbolic computation, and its worst-case complexity is double exponential to the number of variables. Researchers found that variable order dramatically affects efficiency and proposed various heuristics. The existing learning-based methods are all supervised learning methods that cannot cope with diverse polynomial sets. This paper proposes two Reinforcement Learning (RL) approaches combined with Graph Neural Networks (GNN) for Suggesting Variable Order (SVO). One is GRL-SVO(UP), a branching heuristic integrated with CAD. The other is GRL-SVO(NUP), a fast heuristic providing a total order directly. We generate a random dataset and collect a real-world dataset from SMT-LIB. The experiments show that our approaches outperform state-of-the-art learning-based heuristics and are competitive with the best expert-based heuristics. Interestingly, our models show a strong generalization ability, working well on various datasets even if they are only trained on a 3-var random dataset. The source code and data are available at https: //github. com/dongyuhang22/GRL-SVO.

PDF Details

JAIR Journal 2022 Journal Article

Improving Simulated Annealing for Clique Partitioning Problems

Jian Gao
Yiqi Lv
Minghao Liu
Shaowei Cai
Feifei Ma

The Clique Partitioning Problem (CPP) is essential in graph theory with a number of important applications. Due to its NP-hardness, efficient algorithms for solving this problem are very crucial for practical purposes, and simulated annealing is proved to be effective in state-of-the-art CPP algorithms. However, to make simulated annealing more efficient to solve large-scale CPPs, in this paper, we propose a new iterated simulated annealing algorithm. Several methods are proposed in our algorithm to improve simulated annealing. First, a new configuration checking strategy based on timestamp is presented and incorporated into simulated annealing to avoid search cycles. Afterwards, to enhance the local search ability of simulated annealing and speed up convergence, we combine our simulated annealing with a descent search method to solve the CPP. This method further improves solutions found by simulated annealing, and thus compensates for the local search effect. To further accelerate the convergence speed, we introduce a shrinking factor to decline initial temperature and then propose an iterated local search algorithm based on simulated annealing. Additionally, a restart strategy is adopted when the search procedure converges. Extensive experiments on benchmark instances of the CPP were carried out, and the results suggest that the proposed simulated annealing algorithm outperforms all the existing heuristic algorithms, including five state-of-the-art algorithms. Thus the best-known solutions for 34 instances out of 94 are updated. We also conduct comparative analyses of the proposed strategies and show their effectiveness.

PDF Details DOI

AAAI Conference 2022 Conference Paper

Word Level Robustness Enhancement: Fight Perturbation with Perturbation

Pei Huang
Yuting Yang
Fuqi Jia
Minghao Liu
Feifei Ma
Jian Zhang

State-of-the-art deep NLP models have achieved impressive improvements on many tasks. However, they are found to be vulnerable to some perturbations. In this paper, we design a robustness enhancement method to defend against word substitution perturbation, whose basic idea is to fight perturbation with perturbation. We find that: although many welltrained deep models are not robust in the setting of the presence of adversarial samples, they satisfy weak robustness. That means they can handle most non-crafted perturbations well. Taking advantage of the weak robustness property of deep models, we utilize non-crafted perturbations to resist the adversarial perturbations crafted by attackers. Our method contains two main stages. The first stage is using randomized perturbation to conform the input to the data distribution. The second stage is using randomized perturbation to eliminate the instability of prediction results and enhance the robustness guarantee. Experimental results show that our method can significantly improve the ability of deep models to resist the state-of-the-art adversarial attacks while maintaining the prediction performance on the original clean data.

PDF Details

IJCAI Conference 2019 Conference Paper

Solving the Satisfiability Problem of Modal Logic S5 Guided by Graph Coloring

Pei Huang
Minghao Liu
Ping Wang
Wenhui Zhang
Feifei Ma
Jian Zhang

Modal logic S5 has found various applications in artificial intelligence. With the advances in modern SAT solvers, SAT-based approach has shown great potential in solving the satisfiability problem of S5. The scale of the SAT encoding for S5 is strongly influenced by the upper bound on the number of possible worlds. In this paper, we present a novel SAT-based approach for S5 satisfiability problem. We show a normal form for S5 formulas. Based on this normal form, a conflict graph can be derived whose chromatic number provides an upper bound of the possible worlds and a lot of unnecessary search spaces can be eliminated in this process. A heuristic graph coloring algorithm is adopted to balance the efficiency and optimality. The number of possible worlds can be significantly reduced for many practical instances. Extensive experiments demonstrate that our approach outperforms state-of-the-art S5-SAT solvers.

PDF Details