Author name cluster

Wei Tao

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.

7 papers

1 author row

JBHI Journal 2026 Journal Article

Decoding Decision-Making and Feedback Interactions: Insights From EEG Activation Network

Xucheng Liu
Lu Shen
Ze Wang
Wei Tao
Shun Liu
Fali Li
Peng Xu
Tzyy-Ping Jung

The interaction of the brain’s decision-making and feedback stages is crucial for guiding human behavior. Previous studies mainly focused on the interaction immediately after the feedback, resulting in a limited understanding of brain communication dynamics during the interaction process. This study examined the communication dynamics of the brain network during decision-feedback interaction under various feedback conditions by employing a newly developed activation network approach to reveal its underlying neural mechanism. Thirty participants completed a decision-feedback task that involved a sequence of cue-induced predictions with highly predictable, somewhat predictable, and unpredictable feedback conditions. We constructed the activation network for all experimental stages using source-level EEG data in the alpha band. Notably, the brain exhibited the highest communication efficiency ( $p < 0. 05$ ) in receiving and integrating feedback with decision-making information during the feedback stage. Furthermore, the network-behavior correlations indicated that the brain tends to evaluate unexpected feedback under highly predictable conditions and expected feedback under unpredictable conditions, suggesting distinct neural strategies of the decision-feedback interaction process. Finally, we decoded the optimization process of decision-feedback interaction across the entire task. Although network correlations between the decision and feedback stages decreased over time (high predictable: $r = -0. 447$, $p = 0. 001$; unpredictable: $r = -0. 305$, $p = 0. 032$ ), classification accuracy significantly improved ( ${r = -0. 448}$, $p = 0. 010$, best accuracy: 86. 667% ) under the highly predictable condition, corresponding with enhanced prediction behavior. These results indicate the optimization process of the cognitive resources allocation that supports more efficient interaction and improved predictive performance. Our findings advance the understanding of the mechanisms of decision-feedback interaction.

Details DOI

EAAI Journal 2026 Journal Article

Intelligent fault detection in seismic data using U-shaped residual network-temporal-spatial attention mechanism with fourier forward-inverse transform constraints

Jing Yang
Renqi Lu
Stefan Buske
Kang Wang
Shuo Zhao
Wei Tao
Minghao Cai
Guanshen Liu

Rapid and intelligent fault identification based on seismic reflection data is profoundly significant for resource exploration and seismic hazard prediction. Although traditional deep learning methods achieved remarkable progress, they still face limitations in global feature modeling and noise resistance capabilities. Meanwhile they neglect the physical properties of seismic reflection data and produce fault identification results lacking physical consistency. This study represents the first application of the U-shaped residual network (URNet)-Temporal-Spatial Attention mechanism (TSA) to intelligent fault identification in seismic reflection data. Through a dual self-attention mechanism operating in both spatial and axial dimensions, we jointly optimized the results in the time and spatial domains. This approach achieves an adaptive correlation of cross-scale features. Additionally, our introduction of multilevel residual connections enhances the feature flow and improves the gradient propagation efficiency. In multiple three-dimensional (3D) seismic reflection data experiments, the proposed method demonstrated significant superiority over approaches including U-Net, URNet, Vision Transformer 3D (ViT-3D), Swin Transformer 3D(Swin3D), U-Net with Transformer Encoder (UNETR) and published fault-identification models (FaultNet and FaultSeg3D). Under noise interference, the Fourier forward-inverse constraints substantially elevate the robustness of the model. Multiple experimental results revealed the enhanced ability of the model to capture both global fault trend orientations and local details with greater precision. We propose a fault identification methodology combining URNet-TSA with Fourier-forward-inverse transform constraints to achieve efficient modeling of seismic reflection data with enhanced physical consistency. Our approach provides novel insights into the integration of deep learning with geophysical domains, with extensive practical application potential.

Details DOI

AAAI Conference 2026 Conference Paper

Vista: Scene-Aware Optimization for Streaming Video Question Answering Under Post-Hoc Queries

Haocheng Lu
Nan Zhang
Wei Tao
Xiaoyang Qu
Guokuan Li
Jiguang Wan
Jianzong Wang

Streaming video question answering (Streaming Video QA) poses distinct challenges for multimodal large language models (MLLMs), as video frames arrive sequentially and user queries can be issued at arbitrary timepoints. Existing solutions relying on fixed-size memory or naive compression often suffer from context loss or memory overflow, limiting their effectiveness in long-form, real-time scenarios.We present Vista, a novel framework for scene-aware streaming video QA that enables efficient and scalable reasoning over continuous video streams. The innovation of Vista can be summarized in three aspects: (1) Scene-aware segmentation. Vista dynamically clusters incoming frames into temporally and visually coherent scene units. (2) Scene-aware compression. Each scene is compressed into a compact token representation and stored in GPU memory for efficient index-based retrieval, while the full-resolution frames are offloaded to CPU memory. (3) Scene-aware recall. Upon receiving a question, relevant scenes are selectively recalled and reintegrated into the model’s input space, enabling both efficiency and completeness. Vista is model-agnostic and integrates seamlessly with a variety of vision-language backbones, enabling long-context reasoning without compromising latency or memory efficiency. Extensive experiments on StreamingBench demonstrate that Vista achieves state-of-the-art performance, establishing a strong baseline for real-world streaming video understanding.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution

Wei Tao
Yucheng Zhou
Yanlin Wang
Wenqiang Zhang
Hongyu Zhang
Yu Cheng

In software development, resolving the emergent issues within GitHub repositories is a complex challenge that involves not only the incorporation of new code but also the maintenance of existing code. Large Language Models (LLMs) have shown promise in code generation but face difficulties in resolving Github issues, particularly at the repository level. To overcome this challenge, we empirically study the reason why LLMs fail to resolve GitHub issues and analyze the major factors. Motivated by the empirical findings, we propose a novel LLM-based M ulti- A gent framework for G itHub I ssue re S olution, MAGIS, consisting of four agents customized for software evolution: Manager, Repository Custodian, Developer, and Quality Assurance Engineer agents. This framework leverages the collaboration of various agents in the planning and coding process to unlock the potential of LLMs to resolve GitHub issues. In experiments, we employ the SWE-bench benchmark to compare MAGIS with popular LLMs, including GPT-3. 5, GPT-4, and Claude-2. MAGIS can resolve 13. 94% GitHub issues, significantly outperforming the baselines. Specifically, MAGIS achieves an eight-fold increase in resolved ratio over the direct application of GPT-4, the advanced LLM.

PDF Details DOI

AAAI Conference 2024 Conference Paper

On the Convergence of an Adaptive Momentum Method for Adversarial Attacks

Sheng Long
Wei Tao
Shuohao LI
Jun Lei
Jun Zhang

Adversarial examples are commonly created by solving a constrained optimization problem, typically using sign-based methods like Fast Gradient Sign Method (FGSM). These attacks can benefit from momentum with a constant parameter, such as Momentum Iterative FGSM (MI-FGSM), to enhance black-box transferability. However, the monotonic time-varying momentum parameter is required to guarantee convergence in theory, creating a theory-practice gap. Additionally, recent work shows that sign-based methods fail to converge to the optimum in several convex settings, exacerbating the issue. To address these concerns, we propose a novel method which incorporates both an innovative adaptive momentum parameter without monotonicity assumptions and an adaptive step-size scheme that replaces the sign operation. Furthermore, we derive a regret upper bound for general convex functions. Experiments on multiple models demonstrate the efficacy of our method in generating adversarial examples with human-imperceptible noise while achieving high attack success rates, indicating its superiority over previous adversarial example generation methods.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Provable Acceleration of Nesterov’s Accelerated Gradient Method over Heavy Ball Method in Training Over-Parameterized Neural Networks

Xin Liu
Wei Tao
Wei Li
Dazhi Zhan
Jun Wang
Zhisong Pan

Due to its simplicity and efficiency, the first-order gradient method has been extensively employed in training neural networks. Although the optimization problem of the neural network is non-convex, recent research has proved that the first-order method is capable of attaining a global minimum during training over-parameterized neural networks, where the number of parameters is significantly larger than that of training instances. Momentum methods, including the heavy ball (HB) method and Nesterov's accelerated gradient (NAG) method, are the workhorse of first-order gradient methods owning to their accelerated convergence. In practice, NAG often exhibits superior performance than HB. However, current theoretical works fail to distinguish their convergence difference in training neural networks. To fill this gap, we consider the training problem of the two-layer ReLU neural network under over-parameterization and random initialization. Leveraging high-resolution dynamical systems and neural tangent kernel (NTK) theory, our result not only establishes tighter upper bounds of the convergence rate for both HB and NAG, but also provides the first theoretical guarantee for the acceleration of NAG over HB in training neural networks. Finally, we validate our theoretical results on three benchmark datasets.

PDF Details DOI

AAAI Conference 2021 Conference Paper

Gradient Descent Averaging and Primal-dual Averaging for Strongly Convex Optimization

Wei Tao
Wei Li
Zhisong Pan
Qing Tao

Averaging scheme has attracted extensive attention in deep learning as well as traditional machine learning. It achieves theoretically optimal convergence and also improves the empirical model performance. However, there is still a lack of sufficient convergence analysis for strongly convex optimization. Typically, the convergence about the last iterate of gradient descent methods, which is referred to as individual convergence, fails to attain its optimality due to the existence of logarithmic factor. In order to remove this factor, we first develop gradient descent averaging (GDA), which is a general projection-based dual averaging algorithm in the strongly convex setting. We further present primal-dual averaging for strongly convex cases (SC-PDA), where primal and dual averaging schemes are simultaneously utilized. We prove that GDA yields the optimal convergence rate in terms of output averaging, while SC-PDA derives the optimal individual convergence. Several experiments on SVMs and deep learning models validate the correctness of theoretical analysis and effectiveness of algorithms.

PDF Details