Bin Cao

AAAI Conference 2026 Conference Paper

HiveMind: Contribution-Guided Online Prompt Optimization of LLM Multi-Agent Systems

• Yihan Xia
• Taotao Wang
• Shengli Zhang
• Zhangyuhua Weng
• Bin Cao
• Soung Chang Liew

Recent advances in LLM-based multi-agent systems have demonstrated remarkable capabilities in complex decision-making scenarios such as financial trading and software engineering. However, evaluating each individual agent’s effectiveness and online optimization of underperforming agents remain open challenges. To address these issues, we present HiveMind, a self-adaptive framework designed to optimize LLM multi-agent collaboration through contribution analysis. At its core, HiveMind introduces Contribution-Guided Online Prompt Optimization (CG-OPO), which autonomously refines agent prompts based on their quantified contributions. We first propose the Shapley value as a grounded metric to quantify each agent's contribution, thereby identifying underperforming agents in a principled manner for automated prompt refinement. To overcome the computational complexity of the classical Shapley value, we present DAG-Shapley, a novel and efficient attribution algorithm for Directed Acyclic Graph (DAG)-structured multi-agent workflows that leverages the inherent DAG structure of the agent workflow to axiomatically prune non-viable coalitions. By hierarchically reusing intermediate outputs of agents in the DAG, our method further reduces redundant computations, and achieving substantial cost savings without compromising the theoretical guarantees of Shapley values. Evaluated in a multi-agent stock-trading scenario, HiveMind achieves superior performance compared to static baselines. Notably, DAG-Shapley reduces LLM calls by over 80 percent while maintaining attribution accuracy comparable to full Shapley values, establishing a new standard for efficient credit assignment and enabling scalable, real-world optimization of multi-agent collaboration.

ICML Conference 2025 Conference Paper

Scaling Large Motion Models with Million-Level Human Motions

• Ye Wang
• Sipeng Zheng
• Bin Cao
• Qianshan Wei
• Weishuai Zeng
• Qin Jin
• Zongqing Lu 0002

Inspired by the recent success of LLMs, the field of human motion understanding has increasingly shifted toward developing large motion models. Despite some progress, current efforts remain far from achieving truly generalist models, primarily due to the lack of massive high-quality data. To address this gap, we present MotionLib, the first million-level dataset for motion generation, which is at least 15$\times$ larger than existing counterparts and enriched with hierarchical text descriptions. Using MotionLib, we train a large motion model named Being-M0, demonstrating robust performance across a wide range of human activities, including unseen ones. Through systematic investigation, for the first time, we highlight the importance of scaling both data and model size for advancing motion generation, along with key insights to achieve this goal. To better integrate the motion modality, we propose Motionbook, an innovative motion encoding approach including (1) a compact yet lossless feature to represent motions; (2) a novel 2D lookup-free motion tokenizer that preserves fine-grained motion details while expanding codebook capacity, significantly enhancing the representational power of motion tokens. We believe this work lays the groundwork for developing more versatile and powerful motion generation models in the future. For further details, visit https: //beingbeyond. github. io/Being-M0/.

ICLR Conference 2025 Conference Paper

SimXRD-4M: Big Simulated X-ray Diffraction Data and Crystal Symmetry Classification Benchmark

• Bin Cao
• Yang Liu 0245
• Zinan Zheng
• Ruifeng Tan
• Jia Li 0009
• Tong-Yi Zhang

Powder X-ray diffraction (XRD) patterns are highly effective for crystal identification and play a pivotal role in materials discovery. While machine learning (ML) has advanced the analysis of powder XRD patterns, progress has been constrained by the limited availability of training data and established benchmarks. To address this, we introduce SimXRD, the largest open-source simulated XRD pattern dataset to date, aimed at accelerating the development of crystallographic informatics. We developed a novel XRD simulation method that incorporates comprehensive physical interactions, resulting in a high-fidelity database. SimXRD comprises 4,065,346 simulated powder XRD patterns, representing 119,569 unique crystal structures under 33 simulated conditions that reflect real-world variations. We benchmark 21 sequence models in both in-library and out-of-library scenarios and analyze the impact of class imbalance in long-tailed crystal label distributions. Remarkably, we find that: (1) current neural networks struggle with classifying low-frequency crystals, particularly in out-of-library situations; (2) models trained on SimXRD can generalize to real experimental data.

TIST Journal 2021 Journal Article

TLDS: A Transfer-Learning-Based Delivery Station Location Selection Pipeline

• Chenyu Hou
• Bin Cao
• Sijie Ruan
• Jing Fan

Delivery stations play important roles in logistics systems. Well-designed delivery station planning can improve delivery efficiency significantly. However, existing delivery station locations are decided by experts, which requires much preliminary research and data collection work. It is not only time consuming but also expensive for logistics companies. Therefore, in this article, we propose a data-driven pipeline that can transfer expert knowledge among cities and automatically allocate delivery stations. Based on existing well-designed station location planning in the source city, we first train a model to learn the expert knowledge about delivery range selection for each station. Then we transfer the learned knowledge to a new city and design three strategies to select delivery stations for the new city. Due to the differences in characteristics among different cities, we adopt a transfer learning method to eliminate the domain difference so that the model can be adapted to a new city well. Finally, we conduct extensive experiments based on real-world datasets and find the proposed method can solve the problem well.

EAAI Journal 2019 Journal Article

Workflow difference detection based on basis paths

• Bin Cao
• Feng Hong
• Jiaxing Wang
• Jing Fan
• Mingqi Lv

Detecting workflow difference is meaningful for many applications, e. g. , in-vehicle system testing. However, current workflow difference detection methods stress on structural differences while ignoring the behavioral aspects of the workflow models. Due to the large number of possible behaviors for a workflow model, it is challenging to detect the behavioral difference. To address this problem, this paper introduces the idea of basis path testing from the software testing field, and presents an efficient method for detecting the workflow difference in terms of their behaviors. First, we compute the cyclomatic complexity according to the number of nodes and arcs in the workflow model. Then, based on the cyclomatic complexity we design an algorithm that can retrieve the basis paths from a tree structure converted from the workflow model. At last, the Kuhn–Munkres (KM) algorithm is used to map the independent paths from two workflow models and generate the optimal mapping that the overall distance is the minimum. The experimental evaluation shows that our proposed method has been proved feasible in terms of both efficiency and effectiveness.

IJCAI Conference 2011 Conference Paper

Distance Metric Learning under Covariate Shift

• Bin Cao
• Xiaochuan Ni
• Jian-Tao Sun
• Gang Wang
• Qiang Yang

Learning distance metrics is a fundamental problem in machine learning. Previous distance-metric learning research assumes that the training and test data are drawn from the same distribution, which may be violated in practical applications. When the distributions differ, a situation referred to as covariate shift, the metric learned from training data may not work well on the test data. In this case the metric is said to be inconsistent. In this paper, we address this problem by proposing a novel metric learning framework known as consistent distance metric learning (CDML), which solves the problem under covariate shift situations. We theoretically analyze the conditions when the metrics learned under covariate shift are consistent. Based on the analysis, a convex optimization problem is proposed to deal with the CDML problem. An importance sampling method is proposed for metric learning and two importance weighting strategies are proposed and compared in this work. Experiments are carried out on synthetic and real world datasets to show the effectiveness of the proposed method.

AAAI Conference 2010 Conference Paper

Adaptive Transfer Learning

• Bin Cao
• Sinno Jialin Pan
• Yu Zhang
• Dit-Yan Yeung
• Qiang Yang

Transfer learning aims at reusing the knowledge in some source tasks to improve the learning of a target task. Many transfer learning methods assume that the source tasks and the target task be related, even though many tasks are not related in reality. However, when two tasks are unrelated, the knowledge extracted from a source task may not help, and even hurt, the performance of a target task. Thus, how to avoid negative transfer and then ensure a “safe transfer” of knowledge is crucial in transfer learning. In this paper, we propose an Adaptive Transfer learning algorithm based on Gaussian Processes (AT-GP), which can be used to adapt the transfer learning schemes by automatically estimating the similarity between a source and a target task. The main contribution of our work is that we propose a new semi-parametric transfer kernel for transfer learning from a Bayesian perspective, and propose to learn the model with respect to the target task, rather than all tasks as in multi-task learning. We can formulate the transfer learning problem as a unified Gaussian Process (GP) model. The adaptive transfer ability of our approach is verified on both synthetic and real-world datasets.

AAAI Conference 2010 Conference Paper

Clickthrough Log Analysis by Collaborative Ranking

• Bin Cao
• Dou Shen
• Kuansan Wang
• Qiang Yang

Analyzing clickthrough log data is important for improving search performance as well as understanding user behaviors. In this paper, we propose a novel collaborative ranking model to tackle two difficulties in analyzing clickthrough log. First, previous studies have shown that users tend to click topranked results even they are less relevant. Therefore, we use pairwise ranking relation to avoid the position bias in clicks. Second, since click data are extremely sparse with respect to each query or user, we construct a collaboration model to eliminate the sparseness problem. We also find that the proposed model and previous popular used click-based models address different aspects of clickthrough log data. We further propose a hybrid model that can achieve significant improvement compared to the baselines on a large-scale real world dataset.

AAAI Conference 2010 Conference Paper

Collaborative Filtering Meets Mobile Recommendation: A User-Centered Approach

• Vincent Zheng
• Bin Cao
• Yu Zheng
• Xing Xie
• Qiang Yang

With the increasing popularity of location tracking services such as GPS, more and more mobile data are being accumulated. Based on such data, a potentially useful service is to make timely and targeted recommendations for users on places where they might be interested to go and activities that they are likely to conduct. For example, a user arriving in Beijing might wonder where to visit and what she can do around the Forbidden City. A key challenge for such recommendation problems is that the data we have on each individual user might be very limited, while to make useful and accurate recommendations, we need extensive annotated location and activity information from user trace data. In this paper, we present a new approach, known as user-centered collaborative location and activity filtering (UCLAF), to pull many users’ data together and apply collaborative filtering to find like-minded users and like-patterned activities at different locations. We model the userlocation-activity relations with a tensor representation, and propose a regularized tensor and matrix decomposition solution which can better address the sparse data problem in mobile information retrieval. We empirically evaluate UCLAF using a real-world GPS dataset collected from 164 users over 2. 5 years, and showed that our system can outperform several state-of-the-art solutions to the problem.

IJCAI Conference 2007 Conference Paper

• Bin Cao
• Dou Shen
• Jian-Tao Sun
• Xuanhui Wang
• Qiang Yang
• Zheng Chen

Detecting and tracking latent factors from temporal data is an important task. Most existing algorithms for latent topic detection such as Nonnegative Matrix Factorization (NMF) have been designed for static data. These algorithms are unable to capture the dynamic nature of temporally changing data streams. In this paper, we put forward an online NMF (ONMF) algorithm to detect latent factors and track their evolution while the data evolve. By leveraging the already detected latent factors and the newly arriving data, the latent factors are automatically and incrementally updated to reflect the change of factors. Furthermore, by imposing orthogonality on the detected latent factors, we can not only guarantee the unique solution of NMF but also alleviate the partial-data problem, which may cause NMF to fail when the data are scarce or the distribution is incomplete. Experiments on both synthesized data and real data validate the efficiency and effectiveness of our ONMF algorithm.