Author name cluster

Wenjun 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.

4 papers

2 author rows

EAAI Journal 2026 Journal Article

Research on temperature prediction and missing data supplement of concrete box girder of cable-stayed bridges based on data with partial missing

Xuewei Wang
Zhijie Ke
Wenjun Liu
Peiqiang Zhang
Bing Zhu

In recent years, Machine Learning (ML) have emerged as important tools in artificial intelligence, with a wide range of applications such as image recognition, data processing, and engineering applications. This study addresses the issues of insufficient temperature measurement data and partially missing monitoring data in concrete box girders of cable-stayed bridges. By collecting the meteorological data on the bridge site and introducing the ML method, a new idea for the prediction of concrete box girder long-term temperature and the supplement of temperature data missing is proposed. The effects of three different influencing factors and three ML methods on the temperature prediction of concrete box girder are analyzed. Results show that using only time parameters yields poor performance, supplementing with temperature parameters significantly improves the three models, while adding meteorological parameters provides no extra benefit. Among the models, Long Short-Term Memory (LSTM) exhibits superior generalization and accuracy, with a Root Mean Square Error (RMSE) of 1. 3937 and Coefficient of Determination (R2) of 0. 9174, the Mean Absolute Error (MAE) is 1. 0231, the Mean Absolute Percentage error (MAPE) is 0. 0417. When temperature data is extensively missing, traditional imputation methods exhibit insufficient accuracy. Using the R2 values before and after data augmentation as a metric, Linear Interpolation (LI) reduced accuracy by 18. 68%, The Cubic Spline Interpolation (CSI) by 75. 48%, and LSTM by only 0. 57%, highlighting LSTM's notable performance advantage.

Details DOI

ICLR Conference 2025 Conference Paper

Scaling Autonomous Agents via Automatic Reward Modeling And Planning

Zhenfang Chen
Delin Chen
Rui Sun
Wenjun Liu
Chuang Gan 0001

Large language models (LLMs) have demonstrated remarkable capabilities across a range of text-generation tasks. However, LLMs still struggle with problems requiring multi-step decision-making and environmental feedback, such as online shopping, scientific reasoning, and mathematical problem-solving. Unlike pure text data, collecting large-scale decision-making data is challenging. Moreover, many powerful LLMs are only accessible through APIs, which hinders their fine-tuning for agent tasks due to cost and complexity. To address LLM agents' limitations, we propose a framework that can automatically learn a reward model from the environment without human annotations. This model can be used to evaluate the action trajectories of LLM agents and provide heuristics for task planning. Specifically, our approach involves employing one LLM-based agent to navigate an environment randomly, generating diverse action trajectories. Subsequently, a separate LLM is leveraged to assign a task intent and synthesize a negative response alongside the correct response for each trajectory. These triplets (task intent, positive response, and negative response) are then utilized as training data to optimize a reward model capable of scoring action trajectories. This reward model can be integrated with LLM-based agents and various planning algorithms to enhance task-solving performance. The effectiveness and generalizability of our framework are demonstrated through evaluations conducted on different agent benchmarks. In conclusion, our proposed framework represents a significant advancement in enhancing LLM agents' decision-making capabilities. By automating the learning of reward models, we overcome the challenges of data scarcity and API limitations, potentially revolutionizing the application of LLMs in complex and interactive environments. This research paves the way for more sophisticated AI agents capable of tackling a wide range of real-world problems requiring multi-step decision-making.

Details

ICLR Conference 2024 Conference Paper

GENOME: Generative Neuro-Symbolic Visual Reasoning by Growing and Reusing Modules

Zhenfang Chen
Rui Sun
Wenjun Liu
Yining Hong
Chuang Gan 0001

Recent works have shown that Large Language Models (LLMs) could empower traditional neuro-symbolic models via programming capabilities to translate languages into module descriptions, thus achieving strong visual reasoning results while maintaining the model’s transparency and efficiency. However, these models usually exhaustively generate the entire code snippet given each new instance of a task, which is extremely ineffective. On the contrary, human beings gradually acquire knowledge that can be reused and grow into more profound skills for fast generalization to new tasks since we are an infant. Inspired by this, we propose generative neuro-symbolic visual reasoning by growing and reusing modules. Specifically, our model consists of three unique stages, module initialization, module generation, and module execution. First, given a vision-language task, we adopt LLMs to examine whether we could reuse and grow over established modules to handle this new task. If not, we initialize a new module needed by the task and specify the inputs and outputs of this new module. After that, the new module is created by querying LLMs to generate corresponding code snippets that match the requirements. In order to get a better sense of the new module’s ability, we treat few-shot training examples as test cases to see if our new module could pass these cases. If yes, the new module is added to the module library for future reuse. Finally, we evaluate the performance of our model on the testing set by executing the parsed programs with the newly made visual modules to get the results. We find the proposed GENOME model possesses several advantages. First, it performs competitively on standard tasks like visual question answering and referring expression comprehension; Second, the visual modules learned from one task can be seamlessly transferred to new tasks; Last but not least, it is able to adapt to new visual reasoning tasks by observing a few training examples and reusing modules.

Details

NeurIPS Conference 2024 Conference Paper

Interpretable Image Classification with Adaptive Prototype-based Vision Transformers

Chiyu Ma
Jon Donnelly
Wenjun Liu
Soroush Vosoughi
Cynthia Rudin
Chaofan Chen

We present ProtoViT, a method for interpretable image classification combining deep learning and case-based reasoning. This method classifies an image by comparing it to a set of learned prototypes, providing explanations of the form ``this looks like that. '' In our model, a prototype consists of parts, which can deform over irregular geometries to create a better comparison between images. Unlike existing models that rely on Convolutional Neural Network (CNN) backbones and spatially rigid prototypes, our model integrates Vision Transformer (ViT) backbones into prototype based models, while offering spatially deformed prototypes that not only accommodate geometric variations of objects but also provide coherent and clear prototypical feature representations with an adaptive number of prototypical parts. Our experiments show that our model can generally achieve higher performance than the existing prototype based models. Our comprehensive analyses ensure that the prototypes are consistent and the interpretations are faithful.

PDF Details DOI