Author name cluster

Mingyang Wang

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.

5 papers

2 author rows

ICLR Conference 2025 Conference Paper

Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Transformers

Shaobo Wang 0001
Hongxuan Tang
Mingyang Wang
Hongrui Zhang
Xuyang Liu
Weiya Li
Xuming Hu
Linfeng Zhang 0001

The debate between self-interpretable models and post-hoc explanations for black-box models is central to Explainable AI (XAI). Self-interpretable models, such as concept-based networks, offer insights by connecting decisions to human-understandable concepts but often struggle with performance and scalability. Conversely, post-hoc methods like Shapley values, while theoretically robust, are computationally expensive and resource-intensive. To bridge the gap between these two lines of research, we propose a novel method that combines their strengths, providing theoretically guaranteed self-interpretability for black-box models without compromising prediction accuracy. Specifically, we introduce a parameter-efficient pipeline, AutoGnothi, which integrates a small side network into the black-box model, allowing it to generate Shapley value explanations without changing the original network parameters. This side-tuning approach significantly reduces memory, training, and inference costs, outperforming traditional parameter-efficient methods, where full fine-tuning serves as the optimal baseline. AutoGnothi enables the black-box model to predict and explain its predictions with minimal overhead. Extensive experiments show that AutoGnothi offers accurate explanations for both vision and language tasks, delivering superior computational efficiency with comparable interpretability.

Details

NeurIPS Conference 2025 Conference Paper

Refusal Direction is Universal Across Safety-Aligned Languages

Xinpeng Wang
Mingyang Wang
Yihong Liu
Hinrich Schuetze
Barbara Plank

Refusal mechanisms in large language models (LLMs) are essential for ensuring safety. Recent research has revealed that refusal behavior can be mediated by a single direction in activation space, enabling targeted interventions to bypass refusals. While this is primarily demonstrated in an English-centric context, appropriate refusal behavior is important for any language, but poorly understood. In this paper, we investigate the refusal behavior in LLMs across 14 languages using \textit{PolyRefuse}, a multilingual safety dataset created by translating malicious and benign English prompts into these languages. We uncover the surprising cross-lingual universality of the refusal direction: a vector extracted from English can bypass refusals in other languages with near-perfect effectiveness, without any additional fine-tuning. Even more remarkably, refusal directions derived from any safety-aligned language transfer seamlessly to others. We attribute this transferability to the parallelism of refusal vectors across languages in the embedding space and identify the underlying mechanism behind cross-lingual jailbreaks. These findings provide actionable insights for building more robust multilingual safety defenses and pave the way for a deeper mechanistic understanding of cross-lingual vulnerabilities in LLMs.

PDF Details

EAAI Journal 2023 Journal Article

Information complementary attention-based multidimension feature learning for person re-identification

Mingyang Wang
Hui Ma
Yiwei Huang

With the need for criminal investigation technology and the development of deep learning, the task of person re-identification has gradually become a research hotspot. Recently, various neural network-based person re-identification technologies designed by researchers have shown excellent results. However, most of the frameworks focus on complex structural design or redundant networks to guide model construction, which hugely increases the cost of train and application cost. In addition, the correlation between the channel information and spatial information on the pedestrian feature map is also relatively lacking. Therefore, we design a lightweight attention module to address the lack of correlation question response. The proposed module sequentially extracts person images’ channel and spatial features and effectively associates the two kinds of information through sequential connections. The proposed attention module has a simple structure, and the parameter increase in the backbone network is tiny. We place the fuse module in each feature extraction layer to focus on the pedestrian information extracted by each layer. To solve the problem of complex model structure, we choose the residual network as the backbone network and the attention mechanism to extract person features without using pose point estimation or additional network assistance to reduce model complexity. We adjust the drop rate of the person classification layer to improve the model’s generalization ability. We estimate the performance of our method on three public datasets: Market-1501, DukeMTMC-reID, and CUHK03 (both detected and labeled) demonstrate the proposed method’s effectiveness and obtain highly competitive performance on the three datasets.

Details DOI

AAAI Conference 2023 Conference Paper

Meta-Reinforcement Learning Based on Self-Supervised Task Representation Learning

Mingyang Wang
Zhenshan Bing
Xiangtong Yao
Shuai Wang
Huang Kai
Hang Su
Chenguang Yang
Alois Knoll

Meta-reinforcement learning enables artificial agents to learn from related training tasks and adapt to new tasks efficiently with minimal interaction data. However, most existing research is still limited to narrow task distributions that are parametric and stationary, and does not consider out-of-distribution tasks during the evaluation, thus, restricting its application. In this paper, we propose MoSS, a context-based Meta-reinforcement learning algorithm based on Self-Supervised task representation learning to address this challenge. We extend meta-RL to broad non-parametric task distributions which have never been explored before, and also achieve state-of-the-art results in non-stationary and out-of-distribution tasks. Specifically, MoSS consists of a task inference module and a policy module. We utilize the Gaussian mixture model for task representation to imitate the parametric and non-parametric task variations. Additionally, our online adaptation strategy enables the agent to react at the first sight of a task change, thus being applicable in non-stationary tasks. MoSS also exhibits strong generalization robustness in out-of-distributions tasks which benefits from the reliable and robust task representation. The policy is built on top of an off-policy RL algorithm and the entire network is trained completely off-policy to ensure high sample efficiency. On MuJoCo and Meta-World benchmarks, MoSS outperforms prior works in terms of asymptotic performance, sample efficiency (3-50x faster), adaptation efficiency, and generalization robustness on broad and diverse task distributions.

PDF Details DOI

IROS Conference 2022 Conference Paper

Meeting-Merging-Mission: A Multi-robot Coordinate Framework for Large-Scale Communication-Limited Exploration

Yuman Gao
Yingjian Wang 0001
Xingguang Zhong
Tiankai Yang 0002
Mingyang Wang
Zhixiong Xu
Yongchao Wang
Yi Lin 0010

This letter presents a complete framework Meeting-Merging-Mission for multi-robot exploration under communication restriction. Considering communication is limited in both bandwidth and range in the real world, we propose a lightweight environment presentation method and an efficient cooperative exploration strategy. For lower bandwidth, each robot uses specific polytopes to maintain free space and to generate Super Frontier Information (SFI), which serves as the source for exploration decision-making. To reduce repeated exploration, we develop a mission-based protocol that drives robots to share collected information in stable rendezvous. We also design a complete path planning scheme for both centralized and decentralized cases. To validate that our framework is practical and generic, we present an extensive benchmark and deploy our system into multi-UGV and multi-UAV platforms.

Details