Author name cluster

Shaowei Liu

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.

4 papers

1 author row

NeurIPS Conference 2025 Conference Paper

MoBA: Mixture of Block Attention for Long-Context LLMs

Enzhe Lu
Zhejun Jiang
Jingyuan Liu
Yulun Du
Tao Jiang
Chao Hong
Shaowei Liu
Weiran He

Scaling the effective context length is essential for advancing large language models (LLMs) toward artificial general intelligence (AGI). However, the quadratic increase in computational complexity inherent in traditional attention mechanisms presents a prohibitive overhead. Existing approaches either impose strongly biased structures, such as sink or window attention which are task-specific, or radically modify the attention mechanism into linear approximations, whose performance in complex reasoning tasks remains inadequately explored. In this work, we propose a solution that adheres to the ``less structure'' principle, allowing the model to determine where to attend autonomously, rather than introducing predefined biases. We introduce Mixture of Block Attention (MoBA), an innovative approach that applies the principles of Mixture of Experts (MoE) to the attention mechanism. This novel architecture demonstrates superior performance on long-context tasks while offering a key advantage: the ability to seamlessly transition between full and sparse attention, enhancing efficiency without the risk of compromising performance. MoBA has already been deployed to handle actual production workloads with long-context requirements, demonstrating significant advancements in efficient attention computation for LLMs. Our code is available at https: //github. com/MoonshotAI/MoBA.

PDF Details

NeurIPS Conference 2025 Conference Paper

Visual Sync: Multi‑Camera Synchronization via Cross‑View Object Motion

Shaowei Liu
David Yao
Saurabh Gupta
Shenlong Wang

Today, people can easily record memorable moments, ranging from concerts, sports events, lectures, family gatherings, and birthday parties with multiple consumer cameras. However, synchronizing these cross‑camera streams remains challenging. Existing methods assume controlled settings, specific targets, manual correction, or costly hardware. We present VisualSync, an optimization framework based on multi‑view dynamics that aligns unposed, unsynchronized videos at millisecond accuracy. Our key insight is that any moving 3D point, when co‑visible in two cameras, obeys epipolar constraints once properly synchronized. To exploit this, VisualSync leverages off‑the‑shelf 3D reconstruction, feature matching, and dense tracking to extract tracklets, relative poses, and cross‑view correspondences. It then jointly minimizes the epipolar error to estimate each camera’s time offset. Experiments on four diverse, challenging datasets show that VisualSync outperforms baseline methods, achieving an average synchronization error below 130 ms.

PDF Details

EAAI Journal 2023 Journal Article

A dynamic spectrum loss generative adversarial network for intelligent fault diagnosis with imbalanced data

Xin Wang
Hongkai Jiang
Yunpeng Liu
Shaowei Liu
Qiao Yang

Intelligent fault diagnosis with imbalanced data is a problem that often raises concerns. The diagnosis is more effective when the imbalanced dataset is supplemented with data augmentation methods, but there is always a gap between the real data and the generated data, especially in the frequency domain. Therefore, a dynamic spectrum loss generative adversarial network (DSLGAN) is developed for intelligent fault diagnosis. Firstly, a generative information enhancement module is built to simultaneously enhance inefficient information of the generative network from different information sources, thus creating a stable and efficient environment for the generation. Secondly, the spectrum distance is designed to find the difference in spectrum location between the real data and the generated data quantitatively by distance metric, which is used to guide the model training to generate high-quality data with similar features to the real data. Finally, the dynamic spectrum loss is proposed based on the spectrum distance to break through the synthesis of difficult frequencies in the data, by reducing the weight of easily synthesized frequencies in the spectrum while dynamically focusing on the difficult frequency components during training to achieve better generation results. In addition, experiments are conducted using several datasets, and the diagnostic accuracy of DSLGAN is 99. 63% and 99. 65%, reaching a very high level and verifying the effectiveness and superiority of DSLGAN.

Details DOI

NeurIPS Conference 2022 Conference Paper

CASA: Category-agnostic Skeletal Animal Reconstruction

Yuefan Wu
Zeyuan Chen
Shaowei Liu
Zhongzheng Ren
Shenlong Wang

Recovering a skeletal shape from a monocular video is a longstanding challenge. Prevailing nonrigid animal reconstruction methods often adopt a control-point driven animation model and optimize bone transforms individually without considering skeletal topology, yielding unsatisfactory shape and articulation. In contrast, humans can easily infer the articulation structure of an unknown character by associating it with a seen articulated object in their memory. Inspired by this fact, we present CASA, a novel category-agnostic articulated animal reconstruction method. Our method consists of two components, a video-to-shape retrieval process and a neural inverse graphics framework. During inference, CASA first finds a matched articulated shape from a 3D character assets bank so that the input video scores highly with the rendered image, according to a pretrained image-language model. It then integrates the retrieved character into an inverse graphics framework and jointly infers the shape deformation, skeleton structure, and skinning weights through optimization. Experiments validate the efficacy of our method in shape reconstruction and articulation. We further show that we can use the resulting skeletal-animated character for re-animation.

PDF Details