Yi Tang

EAAI Journal 2026 Journal Article

A look-ahead dispatch method via evolution strategies embedded with domain knowledge

• Yuchen Dai
• Weiran Jiao
• Yi Tang
• Minghui Yan
• Feng Xue
• Jianfeng Zhao

AAAI Conference 2026 Conference Paper

Learning Underwater Image Enhancement Iteratively Without Reference Images

• Yi Tang
• Hiroshi Kawasaki
• Takafumi Iwaguchi
• Yuhang Zhang
• Hiroshi Masui

Since high-fidelity reference images are difficult to obtain in real underwater scenes, most deep models trained by synthetic paired data cannot match real-world data exactly. In this paper, we propose an unsupervised training framework for underwater image enhancement (UIE) by leveraging an iterative training strategy and quantification of specific neural units. Specifically, to eliminate the heavy color cast and distortion in the underwater images, we decompose the unsupervised image enhancement as two targeted sub-tasks, namely colorization and color compensation. First, a diffusion model is introduced for colorization to correct the green and blue color casts. Then, to intensify the learning ability of balanced color information, we introduce an extra network branch and propose a quantification mechanism for color compensation. The extra branch encodes style information from normal images into the generative model, while the quantification mechanism identifies and adjusts neural units relevant to warm colors, improving the model’s ability to learn balanced color feature representations for robust generation. In the end, through iterative training, color cast and distortion are progressively reduced, leading to a gradual improvement in the quality of the generated images. Experimental results on various widely used underwater datasets demonstrate that our approach achieves excellent performance, even when compared to recent supervised methods.

AAAI Conference 2025 Conference Paper

Mitigating Social Bias in Large Language Models: A Multi-Objective Approach Within a Multi-Agent Framework

• Zhenjie Xu
• Wenqing Chen
• Yi Tang
• Xuanying Li
• Cheng Hu
• Zhixuan Chu
• Kui Ren
• Zibin Zheng

Natural language processing (NLP) has seen remarkable advancements with the development of large language models (LLMs). Despite these advancements, LLMs often produce socially biased outputs. Recent studies have mainly addressed this problem by prompting LLMs to behave ethically, but this approach results in unacceptable performance degradation. In this paper, we propose a multi-objective approach within a multi-agent framework (MOMA) to mitigate social bias in LLMs without significantly compromising their performance. The key idea of MOMA involves deploying multiple agents to perform causal interventions on bias-related contents of the input questions, breaking the shortcut connection between these contents and the corresponding answers. Unlike traditional debiasing techniques leading to performance degradation, MOMA substantially reduces bias while maintaining accuracy in downstream tasks. Our experiments conducted in two datasets and two models demonstrate that MOMA reduces bias scores by up to 87.7%, with only a marginal performance degradation of up to 6.8% in the BBQ dataset. Additionally, it significantly enhances the multi-objective metric icat in the StereoSet dataset by up to 58.1%.

NeurIPS Conference 2025 Conference Paper

Searching Efficient Semantic Segmentation Architectures via Dynamic Path Selection

• Yuxi Liu
• Min Liu
• Shuai Jiang
• Yi Tang
• Yaonan Wang

Existing NAS methods for semantic segmentation typically apply uniform optimization to all candidate networks (paths) within a one-shot supernet. However, the concurrent existence of both promising and suboptimal paths often results in inefficient weight updates and gradient conflicts. This issue is particularly severe in semantic segmentation due to its complex multi-branch architectures and large search space, which further degrade the supernet's ability to accurately evaluate individual paths and identify high-quality candidates. To address this issue, we propose Dynamic Path Selection (DPS), a selective training strategy that leverages multiple performance proxies to guide path optimization. DPS follows a stage-wise paradigm, where each phase emphasizes a different objective: early stages prioritize convergence, the middle stage focuses on expressiveness, and the final stage emphasizes a balanced combination of expressiveness and generalization. At each stage, paths are selected based on these criteria, concentrating optimization efforts on promising paths, thus facilitating targeted and efficient model updates. Additionally, DPS integrates a dynamic stage scheduler and a diversity-driven exploration strategy, which jointly enable adaptive stage transitions and maintain structural diversity among selected paths. Extensive experiments demonstrate that, under the same search space, DPS can discover efficient models with strong generalization and superior performance.

IJCAI Conference 2024 Conference Paper

Unlearning from Weakly Supervised Learning

• Yi Tang
• Yi Gao
• Yong-gang Luo
• Ju-Cheng Yang
• Miao Xu
• Min-Ling Zhang

Machine unlearning provides users with the right to remove their privacy data from a well-trained model. Existing approaches of machine unlearning mainly focus on exploring data removing within supervised learning (SL) tasks. However, weakly supervised learning (WSL) is more applicable to real-world scenarios since collecting WSL data is less laborious than collecting fully supervised data. In this paper, we first propose a machine unlearning approach for WSL by updating the model parameters. Motivated by the uniform distributions of untrained model predictions, we derive a formulated target to force the model's predictions of removed data to be indistinguishable. This encourages the model to forget its ability to recognize features of data slated for unlearning. Moreover, we employ formulated targets to transform the classification unlearning into the convex regression, which can significantly reduce computational cost and avoid extra information storage during the training process. Additionally, we discuss how to design a target to ensure the models' predictions of removed data being indistinguishable in different learning scenarios, e. g. , SL or WSL. As the flexibility in formulating targets, the proposed approach effectively deals with the WSL problem while still excels in SL models. Empirical studies show the superiority of the proposed approach.

AAAI Conference 2021 Conference Paper

Temporal Pyramid Network for Pedestrian Trajectory Prediction with Multi-Supervision

• Rongqin Liang
• Yuanman Li
• Xia Li
• Yi Tang
• Jiantao Zhou
• Wenbin Zou

Predicting human motion behavior in a crowd is important for many applications, ranging from the natural navigation of autonomous vehicles to intelligent security systems of video surveillance. All the previous works model and predict the trajectory with a single resolution, which is relatively ineffective and difficult to simultaneously exploit the long-range information (e. g. , the destination of the trajectory), and the short-range information (e. g. , the walking direction and speed at a certain time) of the motion behavior. In this paper, we propose a temporal pyramid network for pedestrian trajectory prediction through a squeeze modulation and a dilation modulation. Our hierarchical framework builds a feature pyramid with increasingly richer temporal information from top to bottom, which can better capture the motion behavior at various tempos. Furthermore, we propose a coarse-to-fine fusion strategy with multi-supervision. By progressively merging the top coarse features of global context to the bottom fine features of rich local context, our method can fully exploit both the long-range and short-range information of the trajectory. Experimental results on two benchmarks demonstrate the superiority of our method. Our code and models will be available upon acceptance.

AAMAS Conference 2003 Conference Paper

Agent Network Topology and Complexity

• Xiaolong Jin
• Jiming Liu
• Yuanshi Wang
• Yi Tang