Author name cluster

Chenyu 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.

7 papers

2 author rows

JBHI Journal 2026 Journal Article

A Personalized Point-of-Care Platform for Discovery and Validation of miRNA Targets Using AI and Edge Computing Supporting Personalized Cancer Therapy

Dazhou Li
Chenyu Li
Fa Zhu
Xingchi Chen
Shailendra Mishra
Sidheswar Routray

The paradigm of cancer therapy is rapidly shifting towards personalized precision medicine, yet current diagnostic approaches remain constrained by centralized laboratory infrastructure, creating critical delays between sample collection and therapeutic intervention. To address this limitation, we present GTMIT, a novel point-of-care (POC) platform integrating artificial intelligence (AI) and edge computing for real-time discovery and validation of microRNA (miRNA) targets directly at the patient's bedside. Unlike traditional laboratory-centric models, GTMIT with edge computing operates on local hardware resources (e. g. , portable sequencers and mobile devices), enabling POC decision-making without reliance on the cloud. Our framework combines three key innovations: 1) A Transformer-GNN hybrid architecture with Power Normalization for robust miRNA-mRNA interaction prediction; 2) SNP-adaptive Gapped Pattern Graph Convolutional Networks (GP-GCN) accounting for patient-specific genetic variations; and 3) Edge therapeutic optimization incorporating regional cancer prevalence patterns and resource constraints. We evaluate our proposed platform on several clinical datasets. GTMIT demonstrates excellent performance on a range of metrics, achieving 94% AUC, 87% precision, and 79% recall on benchmark datasets. GTMIT demonstrates excellent performance on a range of metrics, achieving 94% AUC, 87% precision, and 79% recall on benchmark datasets. By bridging molecular diagnostics with immediate intervention at the POC, GTMIT reduces time-to-treatment from days to minutes, particularly benefiting resource-limited settings.

Details DOI

AAAI Conference 2026 Conference Paper

Any-Optical-Model: A Universal Foundation Model for Optical Remote Sensing

Xuyang Li
Chenyu Li
Danfeng Hong

Optical satellites, with their diverse band layouts and ground sampling distances, supply indispensable evidence for tasks ranging from ecosystem surveillance to emergency response. However, significant discrepancies in band composition and spatial resolution across different optical sensors present major challenges for existing Remote Sensing Foundation Models (RSFMs). These models are typically pretrained on fixed band configurations and resolutions, making them vulnerable to real world scenarios involving missing bands, cross sensor fusion, and unseen spatial scales, thereby limiting their generalization and practical deployment. To address these limitations, we propose Any Optical Model (AOM), a universal RSFM explicitly designed to accommodate arbitrary band compositions, sensor types, and resolution scales. To preserve distinctive spectral characteristics even when bands are missing or newly introduced, AOM introduces a spectrum-independent tokenizer that assigns each channel a dedicated band embedding, enabling explicit encoding of spectral identity. To effectively capture texture and contextual patterns from sub-meter to hundred-meter imagery, we design a multi-scale adaptive patch embedding mechanism that dynamically modulates the receptive field. Furthermore, to maintain global semantic consistency across varying resolutions, AOM incorporates a multi-scale semantic alignment mechanism alongside a channel-wise self-supervised masking and reconstruction pretraining strategy that jointly models spectral-spatial relationships. Extensive experiments on over 10 public datasets, including those from Sentinel-2, Landsat, and HLS, demonstrate that AOM consistently achieves state-of-the-art (SOTA) performance under challenging conditions such as band missing, cross sensor, and cross resolution settings. These results highlight AOM as a crucial step toward building truly general-purpose RSFMs.

PDF Details DOI

EAAI Journal 2025 Journal Article

Inspection of cracking in stamping parts surfaces using anomaly detection

Xingjun Dong
Changsheng Zhang
Dawei Wang
Qi Guo
Xinrui Deng
Chenyu Li

Stamping parts are critical components of automobiles, and cracking represents the most serious quality issue in these parts. To effectively address the challenges of delay and low efficiency inherent in manual visual inspections, this article proposes an automated cracking detection framework. Owing to the difficulty in collecting cracking data in actual production, this research proposes a network named local and global self-supervision (LGSS) achieves cracking detection using normal data for model training and is utilized within the designed framework. The proposed LGSS network leverages collected normal samples of stamping parts to self-supervise the pre-trained model for fine-tuning, thereby enabling the model to extract features more effectively. The multivariate Gaussian distribution is employed to calculate the feature distribution of each pixel for anomaly detection (AD), addressing the issue of excessive exposure on stamping part surfaces being misidentified as defects. AD is conducted through both global and local branches, balancing hardware resource utilization while enhancing feature extraction and abnormal score calculation. The LGSS network achieved the score of area under the receiver operating characteristic (AUROC) curve of 100. 0% for detection and 99. 3% for localization in the actual cracking dataset. It can process stamping part images of sizes up to 1792 × 448 within 3 s using limited hardware resources. Experimental results demonstrate that the proposed framework can detect surface cracking on stamping parts both timely and accurately. Furthermore, the versatility of the proposed algorithm for defect detection in other industrial products was evaluated using the MVTec AD and BeanTech AD (BTAD) datasets.

Details DOI

ICML Conference 2025 Conference Paper

PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop

Chenyu Li
Oscar Michel
Xichen Pan
Sainan Liu
Mike Roberts
Saining Xie

Large-scale pre-trained video generation models excel in content creation but are not reliable as physically accurate world simulators out of the box. This work studies the process of post-training these models for accurate world modeling through the lens of the simple, yet fundamental, physics task of modeling object freefall. We show state-of-the-art video generation models struggle with this basic task, despite their visually impressive outputs. To remedy this problem, we find that fine-tuning on a relatively small amount of simulated videos is effective in inducing the dropping behavior in the model, and we can further improve results through a novel reward modeling procedure we introduce. Our study also reveals key limitations of post-training in generalization and distribution modeling. Additionally, we release a benchmark for this task that may serve as a useful diagnostic tool for tracking physical accuracy in large-scale video generative model development. Code is available at this repository: https: //github. com/vision-x-nyu/pisa-experiments.

Details

ICLR Conference 2025 Conference Paper

Unifying Unsupervised Graph-Level Anomaly Detection and Out-of-Distribution Detection: A Benchmark

Yili Wang 0004
Yixin Liu 0001
Xu Shen 0002
Chenyu Li
Rui Miao 0003
Kaize Ding
Ying Wang 0009
Shirui Pan

To build safe and reliable graph machine learning systems, unsupervised graph-level anomaly detection (GLAD) and unsupervised graph-level out-of-distribution (OOD) detection (GLOD) have received significant attention in recent years. Though these two lines of research share the same objective, they have been studied independently in the community due to distinct evaluation setups, creating a gap that hinders the application and evaluation of methods from one to the other. To bridge the gap, in this work, we present a Unified Benchmark for unsupervised Graph-level OOD and anomaly Detection (UB-GOLD), a comprehensive evaluation framework that unifies GLAD and GLOD under the concept of generalized graph-level OOD detection. Our benchmark encompasses 35 datasets spanning four practical anomaly and OOD detection scenarios, facilitating the comparison of 18 representative GLAD/GLOD methods. We conduct multi-dimensional analyses to explore the effectiveness, generalizability, robustness, and efficiency of existing methods, shedding light on their strengths and limitations. Furthermore, we provide an open-source codebase of UB-GOLD to foster reproducible research and outline potential directions for future investigations based on our insights.

Details

NeurIPS Conference 2023 Conference Paper

Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictors

Yong Liu
Chenyu Li
Jianmin Wang
Mingsheng Long

Real-world time series are characterized by intrinsic non-stationarity that poses a principal challenge for deep forecasting models. While previous models suffer from complicated series variations induced by changing temporal distribution, we tackle non-stationary time series with modern Koopman theory that fundamentally considers the underlying time-variant dynamics. Inspired by Koopman theory of portraying complex dynamical systems, we disentangle time-variant and time-invariant components from intricate non-stationary series by Fourier Filter and design Koopman Predictor to advance respective dynamics forward. Technically, we propose Koopa as a novel Koopman forecaster composed of stackable blocks that learn hierarchical dynamics. Koopa seeks measurement functions for Koopman embedding and utilizes Koopman operators as linear portraits of implicit transition. To cope with time-variant dynamics that exhibits strong locality, Koopa calculates context-aware operators in the temporal neighborhood and is able to utilize incoming ground truth to scale up forecast horizon. Besides, by integrating Koopman Predictors into deep residual structure, we ravel out the binding reconstruction loss in previous Koopman forecasters and achieve end-to-end forecasting objective optimization. Compared with the state-of-the-art model, Koopa achieves competitive performance while saving 77. 3% training time and 76. 0% memory.

PDF Details

IJCAI Conference 2021 Conference Paper

Detecting Deepfake Videos with Temporal Dropout 3DCNN

Daichi Zhang
Chenyu Li
Fanzhao Lin
Dan Zeng
Shiming Ge

While the abuse of deepfake technology has brought about a serious impact on human society, the detection of deepfake videos is still very challenging due to their highly photorealistic synthesis on each frame. To address that, this paper aims to leverage the possible inconsistent cues among video frames and proposes a Temporal Dropout 3-Dimensional Convolutional Neural Network (TD-3DCNN) to detect deepfake videos. In the approach, the fixed-length frame volumes sampled from a video are fed into a 3-Dimensional Convolutional Neural Network (3DCNN) to extract features across different scales and identified whether they are real or fake. Especially, a temporal dropout operation is introduced to randomly sample frames in each batch. It serves as a simple yet effective data augmentation and can enhance the representation and generalization ability, avoiding model overfitting and improving detecting accuracy. In this way, the resulting video-level classifier is accurate and effective to identify deepfake videos. Extensive experiments on benchmarks including Celeb-DF(v2) and DFDC clearly demonstrate the effectiveness and generalization capacity of our approach.

PDF Details DOI