Author name cluster

Hongbo Li

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.

13 papers

2 author rows

AAAI Conference 2026 Conference Paper

Right Branches Matter in Failure-based Variable Ordering Heuristics

Yang Zhang
Hongbo Li

Failure-based variable ordering heuristics (VOH) are efficient general-purpose search heuristics for solving constraint satisfaction problems (CSP). They learn from the failures detected during the search and select the variables that are most likely to fail. The current failure-based VOHs, i.e. the failure-rate-based (FRBA) and failure-length-based (FLBA), focus on only the failures detected in left branches. In this paper, we investigate how the failure information from right branches affects the performance of the failure-based VOHs. Four strategies utilizing the failure information of right branches are proposed to refine the failure-based VOHs. Our experiments performed with the benchmark instances used in the recent MiniZinc challenges show that utilizing the failures detected in right branches enhances the performance of the failure-based VOHs. The refined version combining all the proposed strategies generally gets the best performance. It demonstrates remarkable superiority over several general-purpose VOHs, including activity-based search, conflict-history search, refined weighted degree, pick/dom, and the existing FRBA, which are considered state-of-the-art. Our study demonstrates that right branches matter in failure-based VOHs.

PDF Details DOI

EAAI Journal 2025 Journal Article

Learning color prompt and position constraint for visual tracking

Xuedong He
Huiying Xu
Xinzhong Zhu
Hongbo Li
Xiao Huang
Yunliang Jiang

The flourish of current visual tracking cannot be separated from powerful pre-trained backbone networks. Even the pre-trained networks frozen and used merely as a feature extractor can also obtain substantial tracking performance. However, how to acquire target-aware features suitable for visual tracking has always been a hot research topic to improve tracking robustness. Inspired by prompt learning, we propose the color prompt encoder to guide the acquisition of target-aware capability. Concretely, the color histogram features as a naive feature expression can provide complementary cues, so we employ color histogram features to construct the color target probability as a color prompt. Immediately after, the color prompt constructed is integrated into the unified tracking network to guide the generation of specific target feature maps. Furthermore, Discriminative Correlation Filters (DCF)-based trackers with an online update module can effectively adapt to constantly changing objects, so it is imperative to ensure that credible prediction samples are utilized to refine the tracking model online. Hence, we further devise an uncomplicated position offset constraint method based on target motion inertia to screen more reliable prediction results. Adequate experimental results reveal the validity of the color prompt encoder and position offset constraint in the DCF tracking framework. Our trackers can perform favorably against recent and far more sophisticated trackers on multiple public benchmarks. Concretely, our proposed tracker achieves a 0. 815 robustness and 0. 305 expected average overlap (EAO) on Visual Object Tracking (VOT) 2020 dataset, which is superior to the baseline in robustness (+2. 6 %) and EAO (+0. 8 %).

Details DOI

IROS Conference 2025 Conference Paper

Learning Generalizable 3D Manipulation With 10 Demonstrations

Yu Ren
Yang Cong
Bohao Huang
Jiahao Long
Ronghan Chen
Hongbo Li
Huijie Fan

Learning robust and generalizable manipulation skills from few demonstrations remains a key challenge in robotics, with broad applications in industrial automation and service robotics. Although recent imitation learning methods have achieved impressive results, they often require a large amount of demonstration data and struggle to generalize across different spatial variants. In this work, we propose a framework that learns 3D manipulation policies from only 10 demonstrations while achieving robust generalization to unseen spatial configurations through semantic-guided perception and spatial-equivariant policy learning. Our framework consists of two key modules: a Semantic Guided Perception module that extracts task-aware 3D representations from RGB-D inputs using semantic priors and a Spatial Generalized Decision module implementing a diffusion-based policy that preserves spatial equivariance through denoising. Central to our framework is a spatially equivariant training strategy, which adapts 2D data augmentation principles to 3D manipulation by maintaining gripper-object spatial relationships during trajectory augmentation. We validate our framework through extensive experiments on both simulation benchmarks and real-world robotic systems. Our method demonstrates a significant improvement in success rates over state-of-the-art approaches on a series of challenging tasks, particularly under significant object pose variations. This work shows significant potential to advance efficient and generalizable manipulation skill learning in real-world applications.

Details

AAAI Conference 2025 Conference Paper

Mamba YOLO: A Simple Baseline for Object Detection with State Space Model

Zeyu Wang
Chen Li
Huiying Xu
Xinzhong Zhu
Hongbo Li

Driven by the rapid development of deep learning technology, the YOLO series has set a new benchmark for real-time object detectors. Additionally, transformer-based structures have emerged as the most powerful solution in the field, greatly extending the model's receptive field and achieving significant performance improvements. However, this improvement comes at a cost, as the quadratic complexity of the self-attentive mechanism increases the computational burden of the model. To address this problem, we introduce a simple yet effective baseline approach called Mamba YOLO. Our contributions are as follows: 1) We propose that the ODMamba backbone introduce a State Space Model (SSM) with linear complexity to address the quadratic complexity of self-attention. Unlike the other Transformer-base and SSM-base method, ODMamba is simple to train without pretraining. 2) For real-time requirement, we designed the macro structure of ODMamba, determined the optimal stage ratio and scaling size. 3) We design the RG Block that employs a multi-branch structure to model the channel dimensions, which addresses the possible limitations of SSM in sequence modeling, such as insufficient receptive fields and weak image localization. This design captures localized image dependencies more accurately and significantly. Extensive experiments on the publicly available COCO benchmark dataset show that Mamba YOLO achieves state-of-the-art performance compared to previous methods. Specifically, a tiny version of Mamba YOLO achieves a 7.5% improvement in mAP on a single 4090 GPU with an inference time of 1.5 ms.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

MLEP: Multi-granularity Local Entropy Patterns for Generalized AI-generated Image Detection

Lin Yuan
Xiaowan Li
Yan Zhang
Jiawei Zhang
Hongbo Li
Xinbo Gao

Advances in image generation technologies have raised growing concerns about their potential misuse, particularly in producing misinformation and deepfakes. This creates an urgent demand for effective methods to detect AI-generated images (AIGIs). While progress has been made, achieving reliable performance across diverse generative models and scenarios remains challenging due to the absence of source-invariant features and the limited generalization of existing approaches. In this study, we investigate the potential of using image entropy as a discriminative cue for AIGI detection and propose Multi-granularity Local Entropy Patterns (MLEP), a set of feature maps computed based on Shannon entropy from shuffled small patches at multiple image scales. MLEP effectively captures pixel dependencies across scales and dimensions while disrupting semantic content, thereby reducing potential content bias. Based on MLEP, we can easily build a robust CNN-based classifier capable of detecting AIGIs with enhanced reliability. Extensive experiments in an open-world setting, involving images synthesized by 32 distinct generative models, demonstrate that our approach achieves substantial improvements over state-of-the-art methods in both accuracy and generalization. Our code and models are available at https: //www. github. com/fkeufss/MLEP/.

PDF Details

AAAI Conference 2025 Conference Paper

Prediction-Based Adaptive Variable Ordering Heuristics for Constraint Satisfaction Problems

Jitao Xu
Yaling Wu
Hongbo Li
Minghao Yin

Variable ordering heuristics (VOH) play a central role in solving Constraint Satisfaction Problems (CSP). The performance of different VOHs may vary greatly when solving the same CSP instance, so identifying an efficient candidate VOH for a given CSP has been a key issue in the community. In this study, we propose a prediction-based approach to adaptively select efficient VOHs for different CSPs from a set of candidates. Our work demonstrates that efficient candidate VOHs can be identified by learning from the topology of search trees. Specifically, we propose to represent the topology of a binary search tree by the sequence of the Numbers of Positive Decisions (NPD) made before each failure occurs. Based on the representation, we predict the total failure number of a search tree from its beginning part. When solving a CSP, we run a probing procedure to obtain the NPD sequences generated by candidate VOHs and select an efficient one for the resolution according to the prediction results. Our experiments show that the Long Short Term Memory model and Gradient Boosting Decision Tree models trained with the search trees sampled from easy instances are effective in identifying efficient VOHs for hard instances. The models capture some common structure properties hidden in the search trees of different problems. Our approach outperforms the state-of-the-art adaptive VOHs in terms of the number of solved instances and the PAR2 score of runtime.

PDF Details DOI

IJCAI Conference 2023 Conference Paper

Eliminating the Computation of Strongly Connected Components in Generalized Arc Consistency Algorithm for AllDifferent Constraint

Luhan Zhen
Zhanshan Li
Yanzhi Li
Hongbo Li

AllDifferent constraint is widely used in Constraint Programming to model real world problems. Existing Generalized Arc Consistency (GAC) algorithms map an AllDifferent constraint onto a bipartite graph and utilize the structure of Strongly Connected Components (SCCs) in the graph to filter values. Calculating SCCs is time-consuming in the existing algorithms, so we propose a novel GAC algorithm for AllDifferent constraint in this paper, which eliminates the computation of SCCs. We prove that all redundant edges in the bipartite graph point to some alternating cycles. Our algorithm exploits this property and uses a more efficient method to filter values, which is based on breadth-first search. Experimental results on the XCSP3 benchmark suite show that our algorithm considerably outperforms the state-of-the-art GAC algorithms.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Finding Good Partial Assignments during Restart-Based Branch and Bound Search

Hongbo Li
Jimmy H.M. Lee

Restart-based Branch-and-Bound Search (BBS) is a standard algorithm for solving Constraint Optimization Problems (COPs). In this paper, we propose an approach to find good partial assignments to jumpstart search at each restart for general COPs, which are identified by comparing different best solutions found in different restart runs. We consider information extracted from historical solutions to evaluate the quality of the partial assignments. Thus the good partial assignments are dynamically updated as the current best solution evolves. Our approach makes restart-based BBS explore different promising sub-search-spaces to find high-quality solutions. Experiments on the MiniZinc benchmark suite show how our approach brings significant improvements to a black-box COP solver equipped with the state of the art search techniques. Our method finds better solutions and proves optimality for more instances.

PDF Details DOI

AAAI Conference 2023 Conference Paper

When Congestion Games Meet Mobile Crowdsourcing: Selective Information Disclosure

Hongbo Li
Lingjie Duan

In congestion games, users make myopic routing decisions to jam each other, and the social planner with the full information designs mechanisms on information or payment side to regulate. However, it is difficult to obtain time-varying traffic conditions, and emerging crowdsourcing platforms (e.g., Waze and Google Maps) provide a convenient way for mobile users travelling on the paths to learn and share the traffic conditions over time. When congestion games meet mobile crowdsourcing, it is critical to incentive selfish users to change their myopic routing policy and reach the best exploitation-exploration trade-off. By considering a simple but fundamental parallel routing network with one deterministic path and multiple stochastic paths for atomic users, we prove that the myopic routing policy's price of anarchy (PoA) can be arbitrarily large as the discount factor approaches 1. To remedy such huge efficiency loss, we propose a selective information disclosure (SID) mechanism: we only reveal the latest traffic information to users when they intend to over-explore the stochastic paths, while hiding such information when they want to under-explore. We prove that our mechanism reduces PoA to less than 2. Besides the worst-case performance, we further examine our mechanism's average-case performance by using extensive simulations.

PDF Details DOI

TCS Journal 2022 Journal Article

A novel identity-based multi-signature scheme over NTRU lattices

Xinjian Chen
Qiong Huang
Hongbo Li
Zhijian Liao
Willy Susilo

Multi-signature is an important technology to compress multiple signatures on the common message into a compact one, thereby reducing the consumption of storage space and transmission bandwidth. Such a cryptographic primitive is widely used in financial applications such as blockchain which requires multiple keys to authorize a transaction. With the advent of quantum computers, traditional multi-signature schemes may no longer be secure as their underlying security assumptions (e. g. RSA or discrete logarithm problems) may not hold anymore. In this paper, we propose a novel identity-based multi-signature (IBMS) scheme over NTRU lattices, which is secure against the attacks of quantum computers. To the best of our knowledge, it is the first lattice-based IBMS scheme. We show that our scheme is provably secure in the random oracle model based on the ring version of the short integer solution assumption (Ring-SIS). Compared with the closely related works in the literature, our scheme enables the signer to select its system identity (such as email address, physical IP address, and etc.) as the public key, which effectively alleviates the certificate management problem in the PKI setting, and takes the advantage of discrete Gaussian distribution instead of uniform distribution to generate secret signing keys and multi-signatures. Besides, our scheme does not require all the system users to setup a trusted common string, which further simplifies the deployment of our scheme in practice.

Details DOI

AAAI Conference 2020 Conference Paper

Finding Good Subtrees for Constraint Optimization Problems Using Frequent Pattern Mining

Hongbo Li
Jimmy Lee
He Mi
Minghao Yin

Making good decisions at the top of a search tree is important for ﬁnding good solutions early in constraint optimization. In this paper, we propose a method employing frequent pattern mining (FPM), a classic datamining technique, to ﬁnd good subtrees for solving constraint optimization problems. We demonstrate that applying FPM in a small number of random high-quality feasible solutions enables us to identify subtrees containing optimal solutions in more than 55% of problem instances for four real world benchmark problems. The method works as a plugin that can be combined with any search strategy for branch-and-bound search. Exploring the identiﬁed subtrees ﬁrst, the method brings substantial improvements for four efﬁcient search strategies in both total runtime and runtime of ﬁnding optimal solutions.

PDF Details

AAAI Conference 2016 Conference Paper

Efficient Spatio-Temporal Tactile Object Recognition with Randomized Tiling Convolutional Networks in a Hierarchical Fusion Strategy

Lele Cao
Ramamohanarao Kotagiri
Fuchun Sun
Hongbo Li
Wenbing Huang
Zay Maung Maung Aye

Robotic tactile recognition aims at identifying target objects or environments from tactile sensory readings. The advancement of unsupervised feature learning and biological tactile sensing inspire us proposing the model of 3T-RTCN that performs spatio-temporal feature representation and fusion for tactile recognition. It decomposes tactile data into spatial and temporal threads, and incorporates the strength of randomized tiling convolutional networks. Experimental evaluations show that it outperforms some state-of-the-art methods with a large margin regarding recognition accuracy, robustness, and fault-tolerance; we also achieve an order-of-magnitude speedup over equivalent networks with pretraining and ﬁnetuning. Practical suggestions and hints are summarized in the end for effectively handling the tactile data.

PDF Details

AAAI Conference 2013 Conference Paper

Making Simple Tabular ReductionWorks on Negative Table Constraints

Hongbo Li
Yanchun Liang
Jinsong Guo
Zhanshan Li

Simple Tabular Reduction algorithms (STR) work well to establish Generalized Arc Consistency (GAC) on positive table constraints. However, the existing STR algorithms are useless for negative table constraints. In this work, we propose a novel STR algorithm and its improvement, which work on negative table constraints. Our preliminary experiments are performed on some random instances and a certain benchmark instances. The results show that the new algorithms outperform GAC-valid and the MDD-based GAC algorithm.

PDF Details