Author name cluster

MingMing Yu

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.

3 papers

2 author rows

IROS Conference 2025 Conference Paper

3D-MoRe: Unified Modal-Contextual Reasoning for Embodied Question Answering

Rongtao Xu
Han Gao
Mingming Yu
Dong An 0002
Shunpeng Chen
Changwei Wang 0001
Li Guo 0004
Xiaodan Liang

With the growing need for diverse and scalable data in indoor scene tasks, such as question answering and dense captioning, we propose 3D-MoRe, a novel paradigm designed to generate large-scale 3D-language datasets by lever-aging the strengths of foundational models. The framework integrates key components, including multi-modal embedding, cross-modal interaction, and a language model decoder, to process natural language instructions and 3D scene data. This approach facilitates enhanced reasoning and response generation in complex 3D environments. Using the ScanNet 3D scene dataset, along with text annotations from ScanQA and ScanRefer, 3D-MoRe generates 62, 000 question-answer (QA) pairs and 73, 000 object descriptions across 1, 513 scenes. We also employ various data augmentation techniques and implement semantic filtering to ensure high-quality data. Experiments on ScanQA demonstrate that 3D-MoRe significantly outperforms state-of-the-art baselines, with the CIDEr score improving by 2. 15%. Similarly, on ScanRefer, our approach achieves a notable increase in CIDEr@0. 5 by 1. 84%, highlighting its effectiveness in both tasks. Our code and generated datasets will be publicly released to benefit the community, and both can be accessed on the https://3D-MoRe.github.io.

Details

NeurIPS Conference 2025 Conference Paper

C-NAV: Towards Self-Evolving Continual Object Navigation in Open World

MingMing Yu
Fei Zhu
Wenzhuo Liu
Yirong Yang
Qunbo Wang
Wenjun Wu
Jing Liu

Embodied agents are expected to perform object navigation in dynamic, open-world environments. However, existing approaches typically rely on static trajectories and a fixed set of object categories during training, overlooking the real-world requirement for continual adaptation to evolving scenarios. To facilitate related studies, we introduce the continual object navigation benchmark, which requires agents to acquire navigation skills for new object categories while avoiding catastrophic forgetting of previously learned knowledge. To tackle this challenge, we propose C-Nav, a continual visual navigation framework that integrates two key innovations: (1) A dual-path anti-forgetting mechanism, which comprises feature distillation that aligns multi-modal inputs into a consistent representation space to ensure representation consistency, and feature replay that retains temporal features within the action decoder to ensure policy consistency. (2) An adaptive sampling strategy that selects diverse and informative experiences, thereby reducing redundancy and minimizing memory overhead. Extensive experiments across multiple model architectures demonstrate that C-Nav consistently outperforms existing approaches, achieving superior performance even compared to baselines with full trajectory retention, while significantly lowering memory requirements. The code will be publicly available at \url{https: //bigtree765. github. io/C-Nav-project}.

PDF Details

EAAI Journal 2024 Journal Article

Ultra-low cycle fatigue life prediction of stainless steel based on transfer learning guided artificial neural network

MingMing Yu
Xu Xie

Determining ultra-low cycle fatigue (ULCF) life of stainless steel typically involves laborious and time-consuming tests. While machine learning offers an efficient solution for fatigue life prediction, the inherent demand for sufficient training data remains unaddressed. To solve this challenge, a novel method to predict ULCF life using small datasets was proposed by combining artificial neural network (ANN) and transfer learning (TL). A TL-guided ANN (TLNN) framework was developed, wherein the knowledge gained from a pre-trained ANN model for structural steels was transferred to ULCF life prediction of stainless steel. The TLNN model exhibits enhanced predictive capabilities for stainless steel under small amounts of training datasets, with mean R 2 (coefficient of determination) value of 0. 88 and average MAPE (mean absolute percentage error) value of 25. 52%. In comparison, the directly trained ANN model shows lower performance, possessing that the average R 2 and MAPE are 0. 69 and 47. 58%, respectively. We pioneeringly explored and found that adding synthetic data enhancement had no positive effect on the predictive ability of the TLNN model. Furthermore, the dependence of predictive capacity by the TLNN model on the number of training data availability was studied. The prediction process of the TLNN model was interpreted by SHAP (SHapley Additive exPlanations) method. In general, the developed TLNN model can efficiently predict the ULCF life of stainless steel with high accuracy and reduce the cost of consecutive fatigue property evaluation.

Details DOI