Tuo An

I am a first-year PhD student at Nanyang Technological University, supervised by Prof. Jianfei Yang. My research is supported by NTU graduate research scholarship. Before that, I received my Bachelor’s degree from the School of Artificial Intelligence, Nanjing University.

My research interests focus on Multimodal Perception and Embodied Intelligence, with an emphasis on developing robust and efficient learning methods for agents operating in the physical world. Specifically, I am interested in the following aspects:

Multimodal Perception: Explore how vision, language, and heterogeneous sensor data (e.g., IoT signals) can be jointly leveraged to enhance an agent’s perception and understanding of real-world environments.

Efficient Learning: Explore how Vision-Language-Action models can adapt to new tasks under limited data through efficient learning.

Generalization and Continual Learning: Explore generalization and continual learning in VLA models, especially in addressing catastrophic forgetting of previously acquired skills and world knowledge inherited from vision–language models.

news

Oct 02, 2025	IoT-LLM is accepted at Patterns, Cell Press, as a Cover Paper.
Aug 11, 2025	I am glad to join the MARS Lab as a PhD student in August 2025. Fighting for the future of AI!
Nov 01, 2024	Awarded National Scholarship (Ranked 3/102)
Aug 07, 2023	Awarded Best Performance Award during the NJU Natural Language Processing(NLP) Summer Camp.

selected publications

Under Review
Optimization-Guided Diffusion for Interactive Scene Generation

Shihao Li, Naisheng Ye, Tianyu Li, and 7 more authors

In arXiv preprint, 2025

Abs Bib

Realistic and diverse multi-agent driving scenes are crucial for evaluating autonomous vehicles. We present OMEGA, an optimization-guided, training-free framework that enforces structural consistency and interaction awareness during diffusion-based sampling from a scene generation model. Experiments on nuPlan and Waymo show that OMEGA improves generation realism, consistency, and controllability.
@inproceedings{li2025optimization, title = {Optimization-Guided Diffusion for Interactive Scene Generation}, author = {Li, Shihao and Ye, Naisheng and Li, Tianyu and Chitta, Kashyap and An, Tuo and Su, Peng and Wang, Boyang and Liu, Haiou and Lv, Chen and Li, Hongyang}, booktitle = {arXiv preprint}, year = {2025}, }
Cell Press
Iot-llm: Enhancing real-world iot task reasoning with large language models

Tuo An, Yunjiao Zhou, Han Zou, and 1 more author

Patterns, Cell Press (Cover Paper), 2025

Abs Bib

This paper presents a novel approach to enhancing real-world IoT task reasoning with large language models. We demonstrate significant improvements in performance across various benchmarks.
@article{an2024iot, title = {Iot-llm: Enhancing real-world iot task reasoning with large language models}, author = {An, Tuo and Zhou, Yunjiao and Zou, Han and Yang, Jianfei}, journal = {Patterns, Cell Press (Cover Paper)}, year = {2025}, }
EMNLP
EFUF: Efficient Fine-grained Unlearning Framework for Mitigating Hallucinations in Multimodal Large Language Models

Shangyu Xing, Fei Zhao, Zhen Wu, and 5 more authors

In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

Abs Bib

Multimodal large language models (MLLMs) have attracted increasing attention in the past few years, but they may still generate descriptions that include objects not present in the corresponding images, a phenomenon known as object hallucination. To eliminate hallucinations, we propose an efficient fine-grained unlearning framework (EFUF), which can eliminate hallucinations without the need for paired data. Extensive experiments show that our method consistently reduces hallucinations while preserving the generation quality with modest computational overhead.
@inproceedings{xing2024efuf, title = {EFUF: Efficient Fine-grained Unlearning Framework for Mitigating Hallucinations in Multimodal Large Language Models}, author = {Xing, Shangyu and Zhao, Fei and Wu, Zhen and An, Tuo and Chen, Weihao and Li, Chunhui and Zhang, Jianbing and Dai, Xinyu}, booktitle = {Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing}, year = {2024}, }

education

Nanyang Technological University (NTU), Singapore

2025 - Present

Ph.D in Mechanical and Aerospace Engineering, Advisor: Prof. Jianfei Yang

Nanjing University (NJU), China

2021 - 2025

B.Eng. in Artificial Intelligence, Overall GPA 91.2/100

selected honors & awards

National Scholarship (the highest honor for Chinese students), 2024
Outstanding Student of Nanjing University, 2023
School of Artificial Intelligence Scholarship, 2022