Author name cluster

Boyuan 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.

5 papers

2 author rows

AAAI Conference 2026 Conference Paper

A Unified Shape-Aware Foundation Model for Time Series Classification

Zhen Liu
Yucheng Wang
Boyuan Li
Junhao Zheng
Emadeldeen Eldele
Min Wu
Qianli Ma

Foundation models pre-trained on large-scale source datasets are reshaping the traditional training paradigm for time series classification. However, existing time series foundation models primarily focus on forecasting tasks and often overlook classification-specific challenges, such as modeling interpretable shapelets that capture class-discriminative temporal features. To bridge this gap, we propose UniShape, a unified shape-aware foundation model designed for time series classification. UniShape incorporates a shape-aware adapter that adaptively aggregates multiscale discriminative subsequences (shapes) into class tokens, effectively selecting the most relevant subsequence scales to enhance model interpretability. Meanwhile, a prototype-based pretraining module is introduced to jointly learn instance- and shape-level representations, enabling the capture of transferable shape patterns. Pre-trained on a large-scale multi-domain time series dataset comprising 1.89 million samples, UniShape exhibits superior generalization across diverse target domains. Experiments on 128 UCR datasets and 30 additional time series datasets demonstrate that UniShape achieves state-of-the-art classification performance, with interpretability and ablation analyses further validating its effectiveness.

PDF Details DOI

EAAI Journal 2026 Journal Article

Cross-Granularity Fusion Vision Mamba UNet for medical image segmentation

Tuersunjiang Baidi
Zitong Ren
Kurban Ubul
Alimjan Aysa
Boyuan Li
Shihao Wang

Recently, state space models (SSMs), represented by Mamba, have shown significant potential in medical image segmentation. However, the inherent axial sequential scanning mechanism limits the modeling of complex spatial relationships, and single-scale processing hinders effective cross-granularity feature interaction. Therefore, this paper proposes a novel hybrid network, named the Cross-Granularity Fusion Vision Mamba UNet (CGFM-UNet), whose core is the Cross-Granularity Fusion Vision State Space (CGF-VSS) block. Specifically, within CGF-VSS, the Multi-Scale Focal Enhancement (MFE) module decomposes the input features into a fine-grained structure-aware branch and a coarse-grained semantics-aware branch. Subsequently, the novel Chess-trajectory Stepwise Selective Scan (CTSt-SS) block leverages this dual-stream information to guide Mamba along spatially interleaved paths, enabling the deep modeling of structured long-range dependencies. Finally, the Dynamic Gating Fusion (DGF) module adaptively aggregates the enhanced features to form a discriminative unified cross-granularity representation. Extensive experiments on three datasets from different imaging modalities demonstrate that CGFM-UNet achieves highly competitive performance, providing an effective solution for complex medical image segmentation and advancing medical artificial intelligence.

Details DOI

ICML Conference 2025 Conference Paper

HyperIMTS: Hypergraph Neural Network for Irregular Multivariate Time Series Forecasting

Boyuan Li
Yicheng Luo
Zhen Liu 0023
Junhao Zheng
Jianming Lv
Qianli Ma 0001

Irregular multivariate time series (IMTS) are characterized by irregular time intervals within variables and unaligned observations across variables, posing challenges in learning temporal and variable dependencies. Many existing IMTS models either require padded samples to learn separately from temporal and variable dimensions, or represent original samples via bipartite graphs or sets. However, the former approaches often need to handle extra padding values affecting efficiency and disrupting original sampling patterns, while the latter ones have limitations in capturing dependencies among unaligned observations. To represent and learn both dependencies from original observations in a unified form, we propose HyperIMTS, a Hyper graph neural network for I rregular M ultivariate T ime S eries forecasting. Observed values are converted as nodes in the hypergraph, interconnected by temporal and variable hyperedges to enable message passing among all observations. Through irregularity-aware message passing, HyperIMTS captures variable dependencies in a time-adaptive way to achieve accurate forecasting. Experiments demonstrate HyperIMTS’s competitive performance among state-of-the-art models in IMTS forecasting with low computational cost. Our code is available at https: //github. com/qianlima-lab/PyOmniTS.

Details

ICML Conference 2025 Conference Paper

Learning Soft Sparse Shapes for Efficient Time-Series Classification

Zhen Liu 0023
Yicheng Luo
Boyuan Li
Emadeldeen Eldele
Min Wu 0008
Qianli Ma 0001

Shapelets are discriminative subsequences (or shapes) with high interpretability in time series classification. Due to the time-intensive nature of shapelet discovery, existing shapelet-based methods mainly focus on selecting discriminative shapes while discarding others to achieve candidate subsequence sparsification. However, this approach may exclude beneficial shapes and overlook the varying contributions of shapelets to classification performance. To this end, we propose a Soft sparse Shapes (SoftShape) model for efficient time series classification. Our approach mainly introduces soft shape sparsification and soft shape learning blocks. The former transforms shapes into soft representations based on classification contribution scores, merging lower-scored ones into a single shape to retain and differentiate all subsequence information. The latter facilitates intra- and inter-shape temporal pattern learning, improving model efficiency by using sparsified soft shapes as inputs. Specifically, we employ a learnable router to activate a subset of class-specific expert networks for intra-shape pattern learning. Meanwhile, a shared expert network learns inter-shape patterns by converting sparsified shapes into sequences. Extensive experiments show that SoftShape outperforms state-of-the-art methods and produces interpretable results.

Details

ICLR Conference 2025 Conference Paper

Think Then React: Towards Unconstrained Action-to-Reaction Motion Generation

Wenhui Tan
Boyuan Li
Chuhao Jin
Wenbing Huang 0001
Xiting Wang
Ruihua Song

Modeling human-like action-to-reaction generation has significant real-world applications, like human-robot interaction and games. Despite recent advancements in single-person motion generation, it is still challenging to well handle action-to-reaction generation, due to the difficulty of directly predicting reaction from action sequence without prompts, and the absence of a unified representation that effectively encodes multi-person motion. To address these challenges, we introduce Think-Then-React (TTR), a large language-model-based framework designed to generate human-like reactions. First, with our fine-grained multimodal training strategy, TTR is capable to unify two processes during inference: a thinking process that explicitly infers action intentions and reasons corresponding reaction description, which serve as semantic prompts, and a reacting process that predicts reactions based on input action and the inferred semantic prompts. Second, to effectively represent multi-person motion in language models, we propose a unified motion tokenizer by decoupling egocentric pose and absolute space features, which effectively represents action and reaction motion with same encoding. Extensive experiments demonstrate that TTR outperforms existing baselines, achieving significant improvements in evaluation metrics, such as reducing FID from 3.988 to 1.942.

Details