Author name cluster

Yuqi Li

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.

9 papers

2 author rows

AAAI Conference 2026 Conference Paper

A Pseudo-Label Optimization Method Based on Polar Coordinate Modeling and Prior Constraints

Yudi Wang
Hailan Shen
Yixiao Fu
Yuqi Li
Zeshi Lu
Zailiang Chen

Magnetic Resonance Imaging (MRI) and its automatic segmentation are pivotal in assisting physicians with clinical diagnosis. In recent years, with the scarcity of labeled data, significant advancements have been made in semi-supervised segmentation. However, the prediction of many current methods is affected by the presence of false positive regions, which limits their reliability in clinical applications. To tackle this issue, we propose a pseudo-label optimization method based on polar coordinate modeling and prior constraints (PMPC), which refines false positive regions in pseudo-labels by leveraging prior knowledge within the polar coordinate system. Firstly, to improve the efficiency and rationality during polar coordinate modeling, the Adaptive Pole Selection (APS) algorithm is presented to ensure that the pole is located within the foreground region. Secondly, to mitigate false positive regions in pseudo-labels that violate medical anatomical priors, we propose the Prior Knowledge Constraint in Polar Coordinate System (KCP) module to reassign pixel categories in these regions. Finally, the Shape-aware Weighting (SaW) strategy is presented to evaluate the quality of the optimized pseudo-labels based on their shape and then determine their weight in guiding network parameter updates. Experiments on three MRI datasets demonstrate that the proposed method can be effectively integrated with existing pelvic MRI segmentation approaches, significantly reducing false positive rates and further improving segmentation quality.

PDF Details DOI

EAAI Journal 2026 Journal Article

From theory to industry: A survey of deep learning-enabled bearing fault diagnosis in complex environments

Zhiqiang Bao
Changfu Liu
Hui Yang
Jiayao Zhang
Yuqi Li

Bearing fault diagnosis, critical for industrial equipment intelligent maintenance, enhances complex-condition equipment reliability, driving advances in intelligent detection. This paper systematically reviews deep learning-based research and applications via a "data-model-application-challenges-prospects" framework. Contributions in Artificial Intelligence (AI) include constructing digital twin-enhanced small-sample learning frameworks, developing physically constrained interpretable models, and exploring edge-cloud collaborative diagnostic architectures—advancing AI for fault diagnosis. Applications in engineering focus on industrial closed-loop logic (not algorithm stacking), offering paradigms/pathways for complex-scenario intelligent diagnosis to enable industrial-scale generalization and boost equipment safety.

Details DOI

AAAI Conference 2026 Conference Paper

SepPrune: Structured Pruning for Efficient Deep Speech Separation

Yuqi Li
Kai Li
Xin Yin
Zhifei Yang
Zeyu Dong
Zhengtao Yao
Haoyan Xu
Yingli Tian

Although deep learning has substantially advanced speech separation in recent years, most existing studies continue to prioritize separation quality while overlooking computational efficiency, an essential factor for low-latency speech processing in real-time applications. In this paper, we propose SepPrune, the first structured pruning framework specifically designed to compress deep speech separation models and reduce their computational cost. SepPrune begins by analyzing the computational structure of a given model to identify layers with the highest computational burden. It then introduces a differentiable masking strategy to enable gradient-driven channel selection. Based on the learned masks, SepPrune prunes redundant channels and fine-tunes the remaining parameters to recover performance. Extensive experiments demonstrate that this learnable pruning paradigm yields substantial advantages for channel pruning in speech separation models, outperforming existing methods. Notably, a model pruned with SepPrune can recover 85% of the performance of a pre-trained model (trained over hundreds of epochs) with only one epoch of fine-tuning, and achieves convergence 36x faster than training from scratch.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

$\text{S}^2$Q-VDiT: Accurate Quantized Video Diffusion Transformer with Salient Data and Sparse Token Distillation

Weilun Feng
Haotong Qin
Chuanguang Yang
Xiangqi Li
Han Yang
Yuqi Li
Zhulin An
Libo Huang

Diffusion transformers have emerged as the mainstream paradigm for video generation models. However, the use of up to billions of parameters incurs significant computational costs. Quantization offers a promising solution by reducing memory usage and accelerating inference. Nonetheless, we observe that the joint modeling of spatial and temporal information in video diffusion models (V-DMs) leads to extremely long token sequences, which introduces high calibration variance and learning challenges. To address these issues, we propose **$S^2$Q-VDiT**, a post-training quantization framework for V-DMs that leverages **S**alient data and **S**parse token distillation. During the calibration phase, we identify that quantization performance is highly sensitive to the choice of calibration data. To mitigate this, we introduce *Hessian-aware Salient Data Selection*, which constructs high-quality calibration datasets by considering both diffusion and quantization characteristics unique to V-DMs. To tackle the learning challenges, we further analyze the sparse attention patterns inherent in V-DMs. Based on this observation, we propose *Attention-guided Sparse Token Distillation*, which exploits token-wise attention distributions to emphasize tokens that are more influential to the model's output. Under W4A6 quantization, $S^2$Q-VDiT achieves lossless performance while delivering $3. 9\times$ model compression and $1. 3\times$ inference acceleration. Code will be available at https: //github. com/wlfeng0509/s2q-vdit.

PDF Details

ECAI Conference 2025 Conference Paper

FDS-Net: A Frequency-Decomposed Synergistic Network for Multivariate Time Series Prediction

Zhijiang Wang
Yuqi Li
Jinzhe Liang
Keyan Jin

Time series prediction is widely used in traffic planning, weather forecasting, and energy management. However, real-world time series often exhibit complex dynamic characteristics, such as multi-scale patterns and dynamic dependencies, making predictions challenging. Existing methods can model these patterns but struggle with component interactions and timestamp utilization. To address these issues, we propose FDS-Net (Frequency-Decomposed Synergistic Network), which enhances interactions and timestamp utilization through three core modules: Frequency-Decomposed and Reconstructed Block, which decomposes time series into components for explicit modeling and facilitates interactions through signal reconstruction; Multi-Scale Temporal Semantic Extraction Block, which uses multi-scale convolutions to extract diverse temporal features; and Temporal Feature Interaction Block which integrates timestamp features with reconstructed signals and uses attention mechanisms to capture dynamic dependencies. Additionally, we introduce an adaptive dynamic weighted loss function to optimize training. Experimental results show FDS-Net’s superior performance in long-term and short-term forecasting, providing new insights for time series prediction.

Details

AAAI Conference 2025 Conference Paper

Few-Shot Domain Adaptation for Learned Image Compression

Tianyu Zhang
Haotian Zhang
Yuqi Li
Li Li
Dong Liu

Learned image compression (LIC) has achieved state-of-the-art rate-distortion performance, deemed promising for next-generation image compression techniques. However, pre-trained LIC models usually suffer from significant performance degradation when applied to out-of-training-domain images, implying their poor generalization capabilities. To tackle this problem, we propose a few-shot domain adaptation method for LIC by integrating plug-and-play adapters into pre-trained models. Drawing inspiration from the analogy between latent channels and frequency components, we examine domain gaps in LIC and observe that out-of-training-domain images disrupt pre-trained channel-wise decomposition. Consequently, we introduce a method for channel-wise re-allocation using convolution-based adapters and low-rank adapters, which are lightweight and compatible to mainstream LIC schemes. Extensive experiments across multiple domains and multiple representative LIC schemes demonstrate that our method significantly enhances pre-trained models, achieving comparable performance to H.266/VVC intra coding with merely 25 target-domain samples. Additionally, our method matches the performance of full-model finetune while transmitting fewer than 2% of the parameters.

PDF Details DOI

ICLR Conference 2024 Conference Paper

BatteryML: An Open-source Platform for Machine Learning on Battery Degradation

Han Zhang
Xiaofan Gui
Shun Zheng 0001
Ziheng Lu
Yuqi Li
Jiang Bian 0002

Battery degradation remains a pivotal concern in the energy storage domain, with machine learning emerging as a potent tool to drive forward insights and solutions. However, this intersection of electrochemical science and machine learning poses complex challenges. Machine learning experts often grapple with the intricacies of battery science, while battery researchers face hurdles in adapting intricate models tailored to specific datasets. Beyond this, a cohesive standard for battery degradation modeling, inclusive of data formats and evaluative benchmarks, is conspicuously absent. Recognizing these impediments, we present BatteryML—a one-step, all-encompass, and open-source platform designed to unify data preprocessing, feature extraction, and the implementation of both traditional and state-of-the-art models. This streamlined approach promises to enhance the practicality and efficiency of research applications. BatteryML seeks to fill this void, fostering an environment where experts from diverse specializations can collaboratively contribute, thus elevating the collective understanding and advancement of battery research.

Details

EAAI Journal 2024 Journal Article

SoftmaxU: Open softmax to be aware of unknowns

Xulun Ye
Jieyu Zhao
Jiangbo Qian
Yuqi Li

Softmax, as one of the most fundamental classification methods, has been widely exploited in the modern machine learning society. However, the conventional softmax model is trained to predict the labels in the known environment. The real world contains many unknowns (unknown classes and unknown class number). To handle this problem, first, we propose a general open softmax model (SoftmaxU). Then, to validate our proposed general open softmax framework, a deep neural network-based SoftmaxU model (DSoftmaxU) is implemented, in which Bayesian low-rank and deep non-linear subspace network is proposed to generate the unknown class number and detect the novel classes. In addition, the corresponding posterior probability inference and model optimization algorithm is derived. Finally, we demonstrate the proposed open softmax model on both the synthetic and real datasets to validate our theoretic analysis, where our model achieves an average performance improvement of 2% along with unknown class number detection against the conventional open-set, novelty detection methods. Our source code will be available on the website for the further study (https: //github. com/yexlwh/SoftmaxU).

Details DOI

AAAI Conference 2019 Conference Paper

Temporal Bilinear Networks for Video Action Recognition

Yanghao Li
Sijie Song
Yuqi Li
Jiaying Liu

Temporal modeling in videos is a fundamental yet challenging problem in computer vision. In this paper, we propose a novel Temporal Bilinear (TB) model to capture the temporal pairwise feature interactions between adjacent frames. Compared with some existing temporal methods which are limited in linear transformations, our TB model considers explicit quadratic bilinear transformations in the temporal domain for motion evolution and sequential relation modeling. We further leverage the factorized bilinear model in linear complexity and a bottleneck network design to build our TB blocks, which also constrains the parameters and computation cost. We consider two schemes in terms of the incorporation of TB blocks and the original 2D spatial convolutions, namely wide and deep Temporal Bilinear Networks (TBN). Finally, we perform experiments on several widely adopted datasets including Kinetics, UCF101 and HMDB51. The effectiveness of our TBNs is validated by comprehensive ablation analyses and comparisons with various state-of-the-art methods.

PDF Details