Author name cluster

Wentao 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.

4 papers

2 author rows

AAAI Conference 2026 Conference Paper

CycleChemist: A Dual-Pronged Machine Learning Framework for Organic Photovoltaic Discovery

Hou Hei Lam
Jiangjie Qiu
Xiuyuan Hu
Wentao Li
Fankun Zeng
Siwei Fu
Hao Zhang
Xiaonan Wang

Organic photovoltaic (OPV) materials offer a promising pathway for sustainable energy generation. However, their development is hindered by the challenge of identifying high-performance donor-acceptor pairs with optimal power conversion efficiencies (PCEs). Most existing design strategies focus exclusively on either the donor or the acceptor, rather than employing a unified model capable of designing both components. In this work, we introduce a dual-pronged machine learning framework for OPV discovery, integrating predictive modeling and generative molecular design. In this study, we propose the newly curated Organic Photovoltaic Donor-Acceptor Dataset (OPV²D), the largest of its kind, comprising 2,000 experimentally characterized donor-acceptor pairs. This dataset serves as a comprehensive foundation for model training and evaluation. To enable accurate property prediction in organic photovoltaic (OPV) materials, we first introduce the Organic Photovoltaic Classifier (OPVC) to predict the likelihood that a given material exhibits OPV behavior. Complementing this, we develop a hierarchical graph neural network framework that integrates multi-task learning and cross-modal donor–acceptor interaction modeling. This framework includes the Molecular Orbital Energy Estimator (MOE²) for predicting the highest occupied molecular orbital–lowest unoccupied molecular orbital (HOMO–LUMO) energy levels, and the Photovoltaic Performance Predictor (P³) for estimating power conversion efficiency (PCE). In addition, we introduce the Material Generative Pretrained Transformer (MatGPT) to generate synthetically accessible organic semiconductors. Building on this, we propose a reinforcement learning strategy with three-objective policy optimization that guides molecular generation while preserving chemical validity. By bridging molecular representation learning with device performance prediction, our framework advances computational OPV material discovery.

PDF Details DOI

ICRA Conference 2025 Conference Paper

Human-Like Walking Motion Generation for Self-Balancing Lower Limb Rehabilitation Exoskeletons

Ming Yang
Ziqiang Chen
Wentao Li
Feng Li 0059
Weiwei Shang 0001
Dingkui Tian
Xinyu Wu 0001

Self-balancing lower limb rehabilitation exoskeletons (SLLREs) allow individuals with lower limb dysfunction to walk without the use of crutches. Stable and human-like walking motions are crucial for SLLREs because achieving a close imitation of healthy human walking is a key goal in rehabilitation therapy. Existing SLLREs can realize stable walking but lack human-like features such as knee-stretched, heel-strike and toe-off. This paper designs a walking motion generator based on hierarchical optimization to generate a human-like walking motion with variable hip height, heelstrike, toe-off, and knee-stretched features. This generator consists of a knee-stretched optimizer and a stabilizing filter. Specifically, the knee-stretched optimizer realizes the stretched knee feature by optimizing the hip trajectory with varying heights. And the stabilizing filter realizes stable walking by optimizing the hip trajectory in the sagittal plane direction. To validate the effectiveness of the proposed human-like walking motion generator, walking experiments were conducted on SLLRE AutoLEE-G3 both in a simulation environment and the real world. The experimental results show that the humanlike walking motions look more natural and reduce the required torque for the knee joint compared with knee-bent walking.

Details

EAAI Journal 2025 Journal Article

Multimodal prompt state space models for unified adverse weather removal

Pengyue Li
Wentao Li
Jiandong Tian
Yandong Tang

Image restoration under adverse weather conditions can improve the robustness of outdoor machine vision systems. Most existing methods are designed to deal with just one type of adverse weather degradation using uni-modal image information. Moreover, popular restoration backbones such as convolutional neural networks and transformer structures have inherent limitations. In this paper, we propose a multimodal locally enhanced state space model for unified adverse weather removal. It leverages multimodal information to provide comprehensive prompts, enabling the model to achieve unified adverse weather removal from diverse degradation types and levels effectively. The locally enhanced state space model simultaneously achieves local feature representation and long-range dependency modeling with linear complexity, which promotes the performance and efficiency of the restoration network. Moreover, we introduce a novel multiscale gated feed-forward network to realize the effective propagation of multiscale features. Specifically, our method first uses parallel multimodal encoders to represent text and image features adequately. Then, it utilizes multiple degradation semantic adaptors to conduct adaptive learning from the encoded features to generate descriptions of weather-specific knowledge. Finally, the multimodal semantic information is fed into the decoder of the restoration network to guide adverse weather removal. Experiments show that our method achieves state-of-the-art results across four tasks and 33 benchmarks. Our method improves the average peak signal-to-noise ratio (PSNR) by 2. 45 decibel (dB) and 2. 09 decibel (dB), and structural similarity index measure (SSIM) by 3% and 1. 6% over the sub-optimal all-in-one and one-by-one methods on four tasks, respectively. The running time is only 0. 38 s.

Details DOI

JBHI Journal 2024 Journal Article

Survival Analysis for Multimode Ablation Using Self-Adapted Deep Learning Network Based on Multisource Features

Ziqi Zhao
Wentao Li
Ping Liu
Aili Zhang
Jianqi Sun
Lisa X. Xu

Novel multimode thermal therapy by freezing before radio-frequency heating has achieved a desirable therapeutic effect in liver cancer. Compared with surgical resection, ablation treatment has a relatively high risk of tumor recurrence. To monitor tumor progression after ablation, we developed a novel survival analysis framework for survival prediction and efficacy assessment. We extracted preoperative and postoperative MRI radiomics features and vision transformer-based deep learning features. We also combined the immune features extracted from peripheral blood immune responses using flow cytometry and routine blood tests before and after treatment. We selected features using random survival forest and improved the deep Cox mixture (DCM) for survival analysis. To properly accommodate multitype input features, we proposed a self-adapted fully connected layer for locally and globally representing features. We evaluated the method using our clinical dataset. Of note, the immune features rank the highest feature importance and contribute significantly to the prediction accuracy. The results showed a promising C $^{\mathit{td}}$ -index of 0. 885 $\pm$ 0. 040 and an integrated Brier score of 0. 041 $\pm$ 0. 014, which outperformed state-of-the-art method combinations of survival prediction. For each patient, individual survival probability was accurately predicted over time, which provided clinicians with trustable prognosis suggestions.

Details DOI