Author name cluster

Zeyu Lu

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

YNICL Journal 2025 Journal Article

Mechanisms underlying the spontaneous reorganization of depression network after stroke

Yirong Fang
Xian Chao
Zeyu Lu
Hongmei Huang
Ran Shi
Dawei Yin
Hao Chen
Yanan Lu

Exploring the causal relationship between focal brain lesions and post-stroke depression (PSD) can provide therapeutic insights. However, a gap exists between causal and therapeutic information. Exploring post-stroke brain repair processes post-stroke could bridge this gap. We defined a depression network using the normative connectome and investigated the predictive capacity of lesion-induced network damage on depressive symptoms in discovery cohort of 96 patients, at baseline and six months post-stroke. Stepwise functional connectivity (SFC) was used to examine topological changes in the depression network over time to identify patterns of network reorganization. The predictive value of reorganization information was evaluated for follow-up symptoms in discovery and validation cohort 1 (22 worsening PSD patients) as well as for treatment responsiveness in validation cohort 2 (23 antidepressant-treated patients). We evaluated the consistency of significant reorganization areas with neuromodulation targets. Spatial correlations of network reorganization patterns with gene expression and neurotransmitter maps were analyzed. The predictive power of network damage for symptoms diminished at follow-up compared to baseline (Δadjusted R2 = -0. 070, p < 0. 001). Reorganization information effectively predicted symptoms at follow-up in the discovery cohort (adjust R2 = 0. 217, 95 %CI: 0. 010 to 0. 431), as well as symptom exacerbation (r = 0. 421, p = 0. 033) and treatment responsiveness (r = 0. 587, p = 0. 012) in the validation cohorts. Regions undergoing significant reorganization overlapped with neuromodulatory targets known to be effective in treating depression. The reorganization of the depression network was associated with immune-inflammatory responses gene expressions and gamma-aminobutyric acid. Our findings may yield important insights into the repair mechanisms of PSD and provide a critical context for developing post-stroke treatment strategies.

Details DOI

ICML Conference 2024 Conference Paper

FiT: Flexible Vision Transformer for Diffusion Model

Zeyu Lu
Zidong Wang 0004
Di Huang
Chengyue Wu
Xihui Liu
Wanli Ouyang
Lei Bai 0001

In the context of this reality, existing diffusion models, such as Diffusion Transformers, often face challenges when processing image resolutions outside of their trained domain. To overcome this limitation, we present the Flexible Vision Transformer (FiT), a transformer architecture specifically designed for generating images with unrestricted resolutions and aspect ratios. Unlike traditional methods that perceive images as static-resolution grids, FiT conceptualizes images as sequences of dynamically-sized tokens. This perspective enables a flexible training strategy that effortlessly adapts to diverse aspect ratios during both training and inference phases, thus promoting resolution generalization and eliminating biases induced by image cropping. Enhanced by a meticulously adjusted network structure and the integration of training-free extrapolation techniques, FiT exhibits remarkable flexibility in resolution extrapolation generation. Comprehensive experiments demonstrate the exceptional performance of FiT across a broad range of resolutions. Repository available at https: //github. com/whlzy/FiT.

Details

NeurIPS Conference 2023 Conference Paper

Seeing is not always believing: Benchmarking Human and Model Perception of AI-Generated Images

Zeyu Lu
Di Huang
Lei Bai
Jingjing Qu
Chengyue Wu
Xihui Liu
Wanli Ouyang

Photos serve as a way for humans to record what they experience in their daily lives, and they are often regarded as trustworthy sources of information. However, there is a growing concern that the advancement of artificial intelligence (AI) technology may produce fake photos, which can create confusion and diminish trust in photographs. This study aims to comprehensively evaluate agents for distinguishing state-of-the-art AI-generated visual content. Our study benchmarks both human capability and cutting-edge fake image detection AI algorithms, using a newly collected large-scale fake image dataset Fake2M. In our human perception evaluation, titled HPBench, we discovered that humans struggle significantly to distinguish real photos from AI-generated ones, with a misclassification rate of 38. 7\%. Along with this, we conduct the model capability of AI-Generated images detection evaluation MPBench and the top-performing model from MPBench achieves a 13\% failure rate under the same setting used in the human evaluation. We hope that our study can raise awareness of the potential risks of AI-generated images and facilitate further research to prevent the spread of false information. More information can refer to https: //github. com/Inf-imagine/Sentry.

PDF Details

ICML Conference 2023 Conference Paper

π-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation

Chengyue Wu
Teng Wang 0007
Yixiao Ge
Zeyu Lu
Ruisong Zhou
Ying Shan
Ping Luo 0002

Foundation models have achieved great advances in multi-task learning with a unified interface of unimodal and multimodal tasks. However, the potential of such multi-task learners has not been exploited during transfer learning. In this work, we present a universal parameter-efficient transfer learning method, termed Predict-Interpolate Tuning ($\pi$-Tuning), for vision, language, and vision-language tasks. It aggregates the parameters of lightweight task-specific experts learned from similar tasks to aid the target downstream task. The task similarities are predicted in a unified modality-independent space, yielding a scalable graph to demonstrate task relationships. $\pi$-Tuning has several appealing benefits. First, it flexibly explores both intra- and inter-modal transferability between similar tasks to improve the accuracy and robustness of transfer learning, especially in data-scarce scenarios. Second, it offers a systematical solution for transfer learning with multi-task prediction-and-then-interpolation, compatible with diverse types of parameter-efficient experts, such as prompt and adapter. Third, an extensive study of task-level mutual benefits on 14 unimodal and 6 multimodal datasets shows that $\pi$-Tuning surpasses fine-tuning and other parameter-efficient transfer learning methods both in full-shot and low-shot regimes. The task graph also enables an in-depth interpretable analysis of task transferability across modalities. The code will be available at https: //github. com/TencentARC/pi-Tuning.

Details

IROS Conference 2020 Conference Paper

A Deep Learning Based End-to-End Locomotion Mode Detection Method for Lower Limb Wearable Robot Control

Zeyu Lu
Ashwin Narayan
Haoyong Yu

To function effectively in real-world environments, powered wearable robots such as exoskeletons and robotic prostheses must recognize the user's motion intent by detecting the user's locomotion modes such as walking, stair ascent and descent or ramp ascent and descent. Traditionally, intent detection is achieved using rule based methods such as state machines or fuzzy logic using data from wearable sensors. Due to the difficulty of manual rule design, these methods are limited to detect certain simple locomotion modes. Machine learning (ML) based methods can perform classification on a large number of classes without manual rule design and recent research has explored several ML methods for locomotion mode classification. However, current ML based methods for locomotion mode detection use classical methods that require use of feature engineering to achieve acceptable accuracies. Additionally, current ML strategies only classify when certain motion events are detected. This strategy, while computationally efficient could result in misclassifications affecting large sections of motion recognition. To overcome these limitations, this paper proposes an end-to-end deep learning based method for locomotion mode detection that eliminates the need for feature engineering and classifies at a fixed sample rate. This paper introduces a new metric called confidence index and proposes a strategy for tuning confidence index thresholds to achieve a stable intent recognition and overall accuracy of greater than 95% on a publicly available benchmark dataset.

Details