I'm going to join Nanyang Technological University as a Nanyang Assistant Professor in 2026. Currently, I am a Lecturer at ETH Zürich. I work with Prof. Luca Benini and Prof. Luc Van Gool. I also collaborate closely with Dr. Radu Timofte and Dr. Michele Magno.
My research focus on efficient deep learning and artificial intelligence algorithms and systems with applications to vision, language, and biosignals. In particular, I am interested in the following topics:
We have open positions and projects on the topics. Please check the details about the projects in the following section.
This is my old website. The new site is HERE.
We are looking for self-motivated PhD and Master students working on the development, optimization, and deployment of foundation models. In particular, we have the following projects and open positions.
| Sep. 2025 | Three papers on foundation models are accepted to NeurIPS 2025! One paper is on multimodal biosignal foundation model, one is on topology-agnostic EEG foundation model, and another one on segment anything in camouflaged videos with SAM2. Congrats Yanlong, Berkay, and Yuli. |
|---|---|
| Aug. 2025 | One paper is accepted to GLOBECOM 2025! The paper introduces a compute and memory efficient model for 5G receiver on the edge devices. |
| Aug. 2025 | One work WaveFormer is accepted to NER 2025! In this paper, Wavelet transform is introduced to develop a transformer model for gesture recognition with EMG signals. |
| Jun. 2025 | One paper on the acceleration of visual autoregressive models is accepted to ICCV 2025! Check the paper here. |
| Apr. 2025 | Two papers on biosignal foundation models are accepted to EMBC 2025! One paper introduces FEMBA, a state-space model for efficient and scalable EEG analysis. The other paper develops a model for blood pressure estimation with ECG and PPG signals.. |
| Feb. 2025 | Three papers are accepted to CVPR 2025! One paper is on state space models, one is on foundation models for Markush structures, and another one on semantic and sequential alignment for vision-language models. |
| Jan. 2025 | We are organizing the 10th NTIRE workshop and challenge on efficient image super-resolution and image denoising. |
| Sep. 2024 | One paper on Graph Attention in Transformers is accepted to NeurIPS 2024! Check the paper here. |
| Sep. 2024 | One paper on masked autoencoder for point clouds is accepted to ACCV 2024! Check the paper here. |
| Jul. 2024 | One paper on Open-Vocabulary Video Segmentation is accepted to ECCV 2024! Check the paper here. |
| Apr. 2024 | Report for the 9th NTIRE Challenge on Efficient SR is online now. |
| Mar. 2024 | We open PhD positions on Secure Machine Learning on RISC-V Servers and Accelerators. at ETH Zürich |
| Feb. 2024 | One paper is accepted to CVPR 2024! Check the paper here. |
| Feb. 2024 | VRT is accepted to IEEE TIP! Check the paper here. |
| Feb. 2024 | KGT paper is online. Check the paper here. |
| Jan. 2024 | We are organizing the 9th NTIRE Challenge on Efficient Super-Resolution. |
| Dec. 2023 | I start as a Lecturer at ETH Zürich! |
| Nov. 2023 | Our work on smart glasses is online. Check the paper here. |
| Sep. 2023 | One paper is accepted to Machine Intelligence Research. Check the paper here. |
| Aug. 2023 | TinyTracker is accepted to IEEE Sensors. Check the paper here. |
| Apr. 2023 | LSDIR dataset is accepted as a workshop paper at CVPR 2023. Check the paper here. |
| Mar. 2023 | One paper is accepted to ICME. Check the paper here. |
| Feb. 2023 | Two papers are accepted to CVPR2023. GRL sets the new state-of-the-art for 7 image restoration tasks. |
| Jan. 2023 | We are organizing the NTIRE 2023 Challenge on Efficient Super-Resolution, Image Denosing, and Image Super-Resolution (x4). |
| Jul. 2022 | One paper is accepted to ECCV 2022. |
| Apr. 2022 | I start as a Postdoc researcher at the Computer Vision Lab of ETH Zürich! |
| Feb. 2022 | I defended my thesis! |
| Feb. 2022 | Random pruning paper is accepted to CVPR 2022. | Jan. 2022 | We are organizing the NTIRE 2022 Challenge on Efficient Super-Resolution. |
| Jul. 2021 | Efficient GCN paper is accepted to ICCV 2021! |
| Apr. 2021 | Our work on efficient graph convolutional networks is available on arXiv! Check the paper here. |
| Mar. 2021 | Three papers are accepted to CVPR 2021! Check the papers here. The Heterogeneity Hypothesis. DASR. MOCDA. |
| Dec. 2020 | I'm going to serve as as a Senior PC member for IJCAI 2021. |
| Sep. 2020 | DPIR paper is online. Check the paper here. |
| Aug. 2020 | Code of DHP is available. Check it here. |
| Jul. 2020 | DHP paper is accepted to ECCV2020! |
| Jul. 2020 | The Heterogeneity Hypothesis paper is online now. Check it on Arxiv. |
| Apr. 2020 | DASR paper is online (Arxiv). |
| Mar. 2020 | DHP paper is online (Arxiv) |
| Feb. 2020 | One paper accepted to CVPR2020. |
| Jul. 2019 | One paper accepted to ICCV2019. |
| Jul. 2019 | I won the best poster presentation at ICVSS. |
| Feb. 2019 | One paper accepted to CVPR2019. |
|
CEReBrO: Compact Encoder for Representations of EEG Using Efficient Alternating Attention |
|
FEMBA: Efficient and Scalable EEG Analysis with a Bidirectional Mamba Foundation Model |
|
IntLoRA: Integral Low-rank Adaptation of Quantized Diffusion Models |
|
SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models |
|
MarkushGrapher: Joint Visual and Textual Recognition of Markush Structures |
|
MambaIRv2: Attentive State Space Restoration |
|
Sharing Key Semantics in Transformer Makes Efficient Image Restoration |
|
Unified Embedding Alignment for Open-Vocabulary Video Instance Segmentation |
|
Ultra-Efficient On-Device Object Detection on AI-Integrated Smart Glasses with TinyissimoYOLO |
|
Retina : Low-Power Eye Tracking with Event Camera and Spiking Hardware |
|
Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary |
|
Efficient and explicit modelling of image hierarchies for image restoration |
|
LocalViT: Analyzing Locality in Vision Transformers |
|
TinyTracker: Ultra-Fast and Ultra-Low-Power Edge Vision In-Sensor for Gaze Estimation |
|
Revisiting Random Channel Pruning for Neural Network Compression |
|
Towards Efficient Graph Convolutional Networks for Point Cloud Handling |
|
Plug-and-Play Image Restoration with Deep Denoiser Prior |
|
The Heterogeneity Hypothesis: Finding Layer-Wise Dissimilated Network Architecture |
|
Unsupervised Real-world Image Super Resolution via Domain-distance Aware Training |
|
Cluster, Split, Fuse, and Update: Meta-Learning for Open Compound Domain Adaptive Semantic Segmentation |
|
DHP: Differentiable Meta Pruning via HyperNetworks |
|
AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results |
|
Group sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compression |
|
Learning filter basis for convolutional neural network compression |
|
Self-guided network for fast image denoising |
|
3D appearance super-resolution with deep learning |
|
CARN: Convolutional anchored regression network for fast and accurate single image super-resolution |
|
Multiview Video Super-Resolution via Information Extraction and Merging |
Yawei Li © 2024. All rights reserved. Powered by Bootstrap.
