Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Weichen LiuSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works25 from public data
- Bringing AI to edge: From deep learning’s perspective177
This paper surveys the representative and latest deep learning techniques that are useful for edge intelligence systems, including hand-crafted models, model compression, hardware-aware neural architecture search and adaptive deep learning models.
- 31
- 30
- Efficient Deep Learning Infrastructures for Embedded Computing Systems: A Comprehensive Survey and Future Envision25
This survey discusses recent efficient deep learning infrastructures for embedded computing systems from the lens of efficient manual network design for embedded computing systems, efficient automated network design for embedded computing systems, efficient network compression for embedded computing systems, efficient on-device learning for embedded computing systems, and efficient intelligent applications for embedded computing systems.
- 22
- 18
- You only search once14
A lightweight hardware-aware differentiable NAS framework dubbed LightNAS is introduced, striving to find the required architecture that satisfies various performance constraints through a one-time search, to show the superiority of LightNAS over previous state-of-the-art methods.
- 14
- Latency-constrained DNN architecture learning for edge systems using zerorized batch normalization8
This work proposes a latency-oriented neural network learning method to optimize models for high accuracy while fulfilling the latency constraint and introduces a universal hardware-customized latency predictor to optimize this procedure to learn a model that satisfies the latency constraint by only a one-shot training process.
- EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI6
This work introduces dynamic image cropping (DIC), a lightweight foreground predictor to accurately crop the most informative foreground object of input images for inference, which avoids redundant computation on background regions and presents compound shrinking (CS) to collaboratively compress the three dimensions of CNNs according to their contribution to accuracy and model computation.
- CRIMP: C ompact & R eliable DNN Inference on I n- M emory P rocessing via Crossbar-Aligned Compression and Non-ideality Adaptation6
A comprehensive learning framework for co-optimization that can obtain significant improvements over the original model when inferring on the crossbar-based IMP accelerator, with an average reduction of computing power and computing area.
- EvoLP: Self-Evolving Latency Predictor for Model Compression in Real-Time Edge Systems4
Experimental results demonstrate that EvoLP outperforms previous state-of-the-art approaches by being evaluated on three edge devices and four model variants and effectively guides the compression process for higher model accuracy while satisfying strict latency constraints.
- 3
- Collate: Collaborative Neural Network Learning for Latency-Critical Edge Systems3
This work proposes Collate, a novel training framework that collaboratively learns heterogeneous models to meet the latency constraints of multiple edge systems simultaneously, and designs a dynamic zeroizing-recovering method to adjust each local model architecture for high accuracy under its latency constraint.
- Smart Scissor: Coupling Spatial Redundancy Reduction and CNN Compression for Embedded Hardware3
A dynamic image cropping framework to reduce the spatial redundancy by accurately cropping the foreground object from images and a lightweight foreground predictor to efficiently localize and crop the foreground of an image are proposed.
- FedTR: Federated Learning Framework with Transfer Learning for Industrial Visual Inspection2
FedTR is introduced, a novel FL framework incorporating transfer learning designed for Autonomous IVI, focusing on the challenging task of identifying label defects through end-to-end text recognition, and attains performance levels that are on par with those achieved through centralized training.
- 2
- On Hardware-Aware Design and Optimization of Edge Intelligence2
Techniques such as model compression and neural architecture search to enhance system efficiency and effectiveness in hardware-aware design and optimization for edge intelligence are explored.
- Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning2
This paper introduces a two-stage importance evaluation framework, which efficiently and comprehensively evaluates each pruning unit according to both the local importance inside each dimension and the global importance across different dimensions, and presents a heuristic pruning algorithm.
- 2
- 1
- 1
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-11. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it. You will be asked to sign in.