Author name cluster

Yiming Zhao

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.

11 papers

2 author rows

AAAI Conference 2026 Conference Paper

CoS: Towards Optimal Event Scheduling via Chain-of-Scheduling

Yiming Zhao
Jiwei Tang
Shimin Di
Libin Zheng
Jianxing Yu
Jian Yin

Recommending event schedules is a key issue in Event-based Social Networks (EBSNs) in order to maintain user activity. An effective recommendation is required to maximize the user's preference, subjecting to both time and geographical constraints. Existing methods face an inherent trade-off among efficiency, effectiveness, and generalization, due to the NP-hard nature of the problem. This paper proposes the Chain-of-Scheduling (CoS) framework, which activates the event scheduling capability of Large Language Models (LLMs) through a guided, efficient scheduling process. CoS enhances LLM by formulating the schedule task into three atomic stages, i.e., exploration, verification and integration. Then we enable the LLMs to generate CoS autonomously via Knowledge Distillation (KD). Experimental results show that CoS achieves near-theoretical optimal effectiveness with high efficiency on three real-world datasets in a interpretable manner. Moreover, it demonstrates strong zero-shot learning ability on out-of-domain data.

PDF Details DOI

ECAI Conference 2025 Conference Paper

ADAPT: Auction-Based Dynamic Prioritization for Multi-Agent Coordination

Zaipeng Xie
Chentai Qiao
Nuo Yang
Yiming Zhao

Effective coordination in multi-agent systems remains challenging in dynamic and partially observable environments, where agents must reason over evolving interdependencies and limited communication bandwidth. We propose ADAPT, a unified framework for multi-agent coordination that integrates message compression, dependency estimation, and a novel auction-based dynamic prioritization mechanism. In ADAPT, agents exchange compact messages and compute dependency scores to determine how much their behavior depends on others. A distributed auction protocol then assigns priority positions, guiding autoregressive decision-making in a manner aligned with inter-agent influence. This enables flexible, influence-aware coordination without centralized control or extensive communication rounds. Experiments on SMACv2 and GRF show that ADAPT achieves higher win rates, faster convergence, and lower communication cost compared to state-of-the-art baselines. Further analyses confirm its scalability to large teams, compatibility with value decomposition, and runtime efficiency. These results show that ADAPT enables scalable, efficient, and modular multi-agent coordination.

Details

IROS Conference 2025 Conference Paper

CLEA: Closed-Loop Embodied Agent for Enhancing Task Execution in Dynamic Environments

Mingcong Lei
Ge Wang
Yiming Zhao
Zhixin Mai
Qing Zhao
Yao Guo 0002
Zhen Li 0026
Shuguang Cui

Large Language Models (LLMs) exhibit remarkable capabilities in the hierarchical decomposition of complex tasks through semantic reasoning. However, their application in embodied systems faces challenges in ensuring reliable execution of subtask sequences and achieving one-shot success in long-term task completion. To address these limitations in dynamic environments, we propose Closed-Loop Embodied Agent (CLEA)—a novel architecture incorporating four specialized open-source LLMs with functional decoupling for closed-loop task management. The framework features two core innovations: (1) Interactive task planner that dynamically generates executable subtasks based on the environmental memory, and (2) Multimodal execution critic employing an evaluation framework to conduct a probabilistic assessment of action feasibility, triggering hierarchical re-planning mechanisms when environmental perturbations exceed preset thresholds. To validate CLEA’s effectiveness, we conduct experiments in a real environment with manipulable objects, using two heterogeneous robots for object search, manipulation, and search-manipulation integration tasks. Across 12 task trials, CLEA outperforms the baseline model, achieving a 67. 3% improvement in success rate and a 52. 8% increase in task completion rate. These results demonstrate that CLEA significantly enhances the robustness of task planning and execution in dynamic environments. Our code is available at https://sp4595.github.io/CLEA/.

Details

IJCAI Conference 2025 Conference Paper

Dual Encoder Contrastive Learning with Augmented Views for Graph Anomaly Detection

Nannan Wu
Hongdou Dong
Wenjun Wang
Yiming Zhao

Graph anomaly detection (GAD), which aims to identify patterns that deviate significantly from normal nodes in attributed networks, is widely used in financial fraud, cybersecurity, and bioinformatics. The paradigms of jointly optimizing contrastive learning and reconstruction learning have shown significant potential in this field. However, when using GNNs as an encoder, it still faces the problem of over-smoothing, and it is difficult to effectively capture the fine-grain topology information of the graph. In this paper, we introduce an innovative approach: Dual Encoder Contrastive Learning with Augmented Views for Graph Anomaly Detection, named DECLARE. Specifically, the dual encoder integrates the strengths of GNNs and Graph Transformers to learn graph representation from multiple perspectives comprehensively. Although contrastive learning enhances the model's ability to learn discriminative features, it cannot directly identify anomalous patterns. To address this, the reconstruction module independently reconstructs graph structures and attributes, helping the model focus on learning the normal patterns of both structure and attributes. Through extensive experimental analysis, we demonstrate the superiority of DECLARE over the state-of-the-art baselines on six benchmark datasets.

PDF Details DOI

ICML Conference 2025 Conference Paper

GPEN: Global Position Encoding Network for Enhanced Subgraph Representation Learning

Nannan Wu
Yuming Huang
Yiming Zhao
Jie Chen
Wenjun Wang 0002

Subgraph representation learning has attracted growing interest due to its wide applications in various domains. However, existing methods primarily focus on local neighborhood structures while overlooking the significant impact of global structural information, in particular the influence of multi-hop neighbors beyond immediate neighborhoods. This presents two key challenges: how to effectively capture the structural relationships between distant nodes, and how to prevent excessive aggregation of global structural information from weakening the discriminative ability of subgraph representations. To address these challenges, we propose GPEN (Global Position Encoding Network). GPEN leverages a hierarchical tree structure to encode each node’s global position based on its path distance to the root node, enabling a systematic way to capture relationships between distant nodes. Furthermore, we introduce a boundary-aware convolution module that selectively integrates global structural information while maintaining the unique structural patterns of each subgraph. Extensive experiments on eight public datasets identify that GPEN significantly outperforms state-of-the-art methods in subgraph representation learning.

Details

NeurIPS Conference 2025 Conference Paper

SEEA-R1: Tree-Structured Reinforcement Fine-Tuning for Self-Evolving Embodied Agents

Wanxin Tian
Shijie Zhang
Kevin Zhang
Xiaowei Chi
Chun-Kai Fan
Junyu Lu
Yulin Luo
Qiang Zhou

Self-evolution, the ability of agents to autonomously improve their reasoning and behavior, is essential for the embodied domain with long-horizon, real-world tasks. Despite current advancements in reinforcement fine-tuning (RFT) showing strong performance in enhancing reasoning in LLMs, its potential to enable self-evolving embodied intelligence with multi-modal interactions remains largely unexplored. Specifically, reinforcement fine-tuning faces two fundamental obstacles in embodied settings: (i) the lack of accessible intermediate rewards in multi-step reasoning tasks limits effective learning signals, and (ii) reliance on hand-crafted reward functions restricts generalization to novel tasks and environments. To address these challenges, we present Self-Evolving Embodied Agents-R1, SEEA-R1, the first RFT framework designed for enabling the self-evolving capabilities of embodied agents. Specifically, to convert sparse delayed rewards into denser intermediate signals that improve multi-step reasoning, we propose Tree-based group relative policy optimization ( Tree-GRPO ) integrates Monte Carlo Tree Search into GRPO. To generalize reward estimation across tasks and scenes, supporting autonomous adaptation and reward-driven self-evolution, we further introduce Multi-modal Generative Reward Model ( MGRM ). To holistically evaluate the effectiveness of SEEA-R1, we evaluate on the ALFWorld benchmark, surpassing state-of-the-art methods with scores of 85. 07\% (textual) and 46. 27\% (multi-modal), outperforming prior models including GPT-4o. SEEA-R1 also achieves scores of 80. 3\% (textual) and 44. 03\% (multi-modal) without ground truth reward, surpassing all open-source baselines and highlighting its scalability as a self-evolving embodied agent. Additional experiments and qualitative analysis further support the potential of SEEA-R1 for future research in scalable embodied intelligence. Project page is at https: //seea-r1. github. io/.

PDF Details

IJCAI Conference 2025 Conference Paper

State Feedback Enhanced Graph Differential Equations for Multivariate Time Series Forecasting

Jiaxu Cui
Qipeng Wang
Yiming Zhao
Bingyi Sun
Pengfei Wang
Bo Yang

Multivariate time series forecasting holds significant theoretical and practical importance in various fields, including web analytics and transportation. Recently, graph neural networks and graph differential equations have shown exceptional capabilities in modeling spatio-temporal features. However, existing methods often suffer from over-smoothing, hindering real-world problem-solving. In this work, we analyze the graph propagation process as a dynamical system and propose a novel feedback mechanism to enhance representation power, adaptively adjusting the representations to align with desired performance outcomes, thereby fundamentally mitigating the issue of over-smoothing. Moreover, we introduce an effective multivariate time series forecasting model called SF-GDE, based on the proposed graph propagation with the feedback mechanism. Intensive experiments are conducted on three real-world datasets from diverse fields. Results show that SF-GDE outperforms the state of the arts, and the feedback mechanism can serve as a universal booster to improve performance for graph propagation models.

PDF Details DOI

ICRA Conference 2022 Conference Paper

A Divide-and-Merge Point Cloud Clustering Algorithm for LiDAR Panoptic Segmentation

Yiming Zhao
Xiao Zhang
Xinming Huang 0001

Clustering objects from the LiDAR point cloud is an important research problem with many applications such as autonomous driving. To meet the real-time requirement, existing research proposed to apply the connected-component-labeling (CCL) technique on LiDAR spherical range image with a heuristic condition to check if two neighbor points are connected. However, LiDAR range image is different from a binary image which has a deterministic condition to tell if two pixels belong to the same component. The heuristic condition used on the LiDAR range image only works empirically, which suggests the LiDAR clustering algorithm should be robust to potential failures of the empirical heuristic condition. To overcome this challenge, this paper proposes a divide-and-merge LiDAR clustering algorithm. This algorithm firstly conducts clustering in each evenly divided local region, then merges the local clustered small components by voting on edge point pairs. Assuming there are $N$ LiDAR points of objects in total with $m$ divided local regions, the time complexity of the proposed algorithm is $O(N)+O(m^{2})$. A smaller $m$ means the voting will involve more neighbor points, but the time complexity will become larger. So the $m$ controls the trade-off between the time complexity and the clustering accuracy. A proper $m$ helps the proposed algorithm work in real-time as well as maintain good performance. We evaluate the divide-and-merge clustering algorithm on the SemanticKITTI panoptic segmentation benchmark by cascading it with a state-of-the-art semantic segmentation model. The final performance evaluated through the leaderboard achieves the best among all published methods. The proposed algorithm is implemented with C++ and wrapped as a python function. It can be easily used with the modern deep learning framework in python. We released the code under the following link 1 1 https://github.com/placeforyiming/Divide-and-Merge-LiDAR-Panoptic-Cluster.

Details

MFCS Conference 2022 Conference Paper

Computing the Minimum Bottleneck Moving Spanning Tree

Haitao Wang 0001
Yiming Zhao

Given a set P of n points that are moving in the plane, we consider the problem of computing a spanning tree for these moving points that does not change its combinatorial structure during the point movement. The objective is to minimize the bottleneck weight of the spanning tree (i. e. , the largest Euclidean length of all edges) during the whole movement. The problem was solved in O(n²) time previously [Akitaya, Biniaz, Bose, De Carufel, Maheshwari, Silveira, and Smid, WADS 2021]. In this paper, we present a new algorithm of O(n^{4/3} log³ n) time.

Details

TCS Journal 2021 Journal Article

Algorithms for diameters of unicycle graphs and diameter-optimally augmenting trees

Haitao Wang
Yiming Zhao

We consider the problem of computing the diameter of a unicycle graph (i. e. , a graph with a unique cycle). We present an O ( n ) time algorithm for the problem, where n is the number of vertices of the graph. This improves the previous best O ( n log ⁡ n ) time solution [Oh and Ahn, ISAAC 2016]. Using this algorithm as a subroutine, we solve the problem of adding a shortcut to a tree so that the diameter of the new graph (which is a unicycle graph) is minimized; our algorithm takes O ( n 2 log ⁡ n ) time and O ( n ) space. The previous best algorithms solve the problem in O ( n 2 log 3 ⁡ n ) time and O ( n ) space [Oh and Ahn, ISAAC 2016], or in O ( n 2 ) time and O ( n 2 ) space [Bilò, ISAAC 2018].

Details DOI

IROS Conference 2021 Conference Paper

FIDNet: LiDAR Point Cloud Semantic Segmentation with Fully Interpolation Decoding

Yiming Zhao
Lin Bai 0002
Xinming Huang 0001

Projecting the point cloud on the 2D spherical range image transforms the LiDAR semantic segmentation to a 2D segmentation task on the range image. However, the LiDAR range image is still naturally different from the regular 2D RGB image; for example, each position on the range image encodes the unique geometry information. In this paper, we propose a new projection-based LiDAR semantic segmentation pipeline that consists of a novel network structure and an efficient post-processing step. In our network structure, we design a FID (fully interpolation decoding) module that directly upsamples the multi-resolution feature maps using bilinear interpolation. Inspired by the 3D distance interpolation used in PointNet++, we argue this FID module is a 2D version distance interpolation on (θ, ϕ) space. As a parameter-free decoding module, the FID largely reduces the model complexity by maintaining good performance. Besides the network structure, we empirically find that our model predictions have clear boundaries between different semantic classes. This makes us rethink whether the widely used K-nearest-neighbor post-processing is still necessary for our pipeline. Then, we realize the many-to-one mapping causes the blurring effect that some points are mapped into the same pixel and share the same label. Therefore, we propose to process those occluded points by assigning the nearest predicted label to them. This NLA (nearest label assignment) post-processing step shows a better performance than KNN with faster inference speed in the ablation study. On SemanticKITTI dataset, our pipeline achieves the best performance among all projection-based methods with 64×2048 resolution and all point-wise solutions. With a ResNet-34 as the backbone, both the training and testing of our model can be finished on a single RTX 2080 Ti with 11G memory. The code is released here. 1

Details