Yawei Li

Democratizing AI for pervasive applications.

prof_pic.jpg

Gloriastrasse 35, 8092 Zürich

Switzerland

I am a Lecturer at ETH Zürich. I work with Prof. Luca Benini. I also collaborate with Prof. Radu Timofte, Dr. Michele Magno, and Prof. Ming-Hsuan Yang. I got my PhD degree from the Computer Vision Lab supervised by Prof. Luc Van Gool. During my PhD, I was mentored by Babak Ehteshami Bejnordi, Tijmen Blankevoort, and Amir Habibian at Qualcomm and Rakesh Ranjan at Meta. After my graduation, I worked as a Postdoc at CVL, and part-time at Meta.


My research focuses on AI efficiency, aiming to accelerate computation, reduce memory footprint, and mitigate power consumption in AI systems. This is a fascinating area that drives AI applications across both cloud and edge environments. Addressing this challenge requires delving into the system stack to understand its fundamental units, from input modalities, models, computation mechanisms, mappings to hardware specifications. Through joint optimization across techniques and layers, it becomes possible to achieve extreme computational efficiency.

My research covers the topics on the following levels of AI system stack:

  • Computational-efficient model design: My work investigate efficient computational mechnism for CNNs, graph neural networks, vision Transformers (LocalViT, GRL, SemanIR, VRT), and state-space models (MambaIR, FEMBA).
  • Model compression and deployment: My work covers multiple model compression methods including model pruning (group sparsity, random pruning, DHP) token pruning (FastVAR), quantization (SliM-LLM, OBR), tensor decomposition(learning filter basis), and low-rank adaptation (IntLoRA) methods to compress LLMs and diffusion models.
  • Software-hardware co-design: I investigate how to co-design software and hardware to serve modern deep models efficiently on both large clusters (FlatAttention) and edge devices (smart glasses, Retina, TinyTracker).
  • Foundation model for biosignals: Biosignals capture physiological activities of human beings and find wide applications in healthcare, disease monitoring and detection, BCI, HCI, AR/VR, etc. These applications usually involves efficient on-device computation and accurate modelling capacity. This is an area that I’m interested in recently (PhysioWave, LUNA, WaveFormer, FEMBA, CEReBrO).

News

Sep 18, 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.
Sep 14, 2025 One work on joint quantization and sparsification is released on arxiv. In this work, we propose an error compensation method to reconcile the conflicting requirements of quantization and pruning. The proposed method delivers up to 4.72x speedup and 6.4x memory reduction compared to the FP16-dense baseline.
Aug 05, 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.
Aug 02, 2025 One paper on AI/ML acceleration on edge device is accepted to CASES in conjunction with ESWEEK!
Aug 01, 2025 One paper is accepted to GLOBECOM 2025! The paper introduces a compute and memory efficient model for 5G receiver on the edge devices.
Jun 25, 2025 One paper on the acceleration of visual autoregressive models is accepted to ICCV 2025! Check the paper here.
May 11, 2025 One paper on dataflow and accelerator co-design is accepted to ISVLSI 2025! Check the paper here.
May 01, 2025 Two papers on model quantization are accepted to ICML 2025! IntLoRA proposes an integral low-rank adaption method for quantized diffusion models. After low-rank adaptation, all the weights are converted to integers. SliM-LLM proposes a mixed precision quantization method for LLMs.
Apr 29, 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 26, 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 18, 2025 We are organizing the 10th NTIRE workshop and challenge on efficient image super-resolution and image denoising.
Sep 26, 2024 One paper on Graph Attention in Transformers is accepted to NeurIPS 2024! Check the paper here.
Sep 25, 2024 One paper on masked autoencoder for point clouds is accepted to ACCV 2024! Check the paper here.
Aug 30, 2024 TinyTracker is accepted to IEEE Sensors. Check the paper here.
Jul 01, 2024 One paper on Open-Vocabulary Video Segmentation is accepted to ECCV 2024! Check the paper here.
Apr 30, 2024 LSDIR dataset is accepted as a workshop paper at CVPR 2023. Check the paper here.
Mar 12, 2024 One paper is accepted to ICME. Check the paper here.
Mar 01, 2024 We open PhD positions on Secure Machine Learning on RISC-V Servers and Accelerators at ETH Zürich. More info here.
Feb 27, 2024 VRT is accepted to IEEE TIP! Check the paper here.
Feb 27, 2024 One paper is accepted to CVPR 2024! Check the paper here.
Jan 11, 2024 We are organizing the 9th NTIRE Challenge on Efficient Super-Resolution. Check it here and here.
Dec 01, 2023 I start as a Lecturer at ETH Zürich!
Nov 04, 2023 Our work on smart glasses is online. Check the paper here.
Sep 30, 2023 One paper is accepted to Machine Intelligence Research. Check the paper here.
Jul 03, 2023 One paper on reference-based SR is accepted to ECCV 2022.
Apr 01, 2023 I start as a Postdoc researcher at the Computer Vision Lab of ETH Zürich!
Feb 27, 2023 Two papers are accepted to CVPR 2023! Check the papers here and here. GRL sets the new state-of-the-art for 7 image restoration tasks. Check GRL here.
Jan 01, 2023 We are organizing the NTIRE 2023 Challenge on Efficient Super-Resolution, Image Denoising, and Image Super-Resolution (x4). More info here.
Mar 02, 2022 Random pruning paper is accepted to CVPR 2022! Check the paper here.
Feb 16, 2022 I defended my thesis! Check it here.
Jan 01, 2022 We are organizing the NTIRE 2022 Challenge on Efficient Super-Resolution. More info here.
Jul 22, 2021 Efficient GCN paper is accepted to ICCV 2021! Check the paper here.
Feb 28, 2021 Three papers are accepted to CVPR 2021! Check the papers: The Heterogeneity Hypothesis, DASR, MOCDA.
Jul 03, 2020 DHP paper is accepted to ECCV 2020! Check the paper here.
Feb 23, 2020 One paper is accepted to CVPR 2020. Check it here

Selected Publications

  1. Arxiv
    2025_arxiv_obr.png
    Optimal Brain Restoration for Joint Quantization and Sparsification of LLMs
    Hang Guo, Yawei Li, and Luca Benini
    arXiv preprint arXiv:2509.11177, 2025
  2. Arxiv
    2025_arxiv_msp.png
    Towards Extreme Pruning of LLMs with Plug-and-Play Mixed Sparsity
    Chi Xu, Gefei Zhang, Yantong Zhu, Luca Benini, Guosheng Hu, Yawei Li, and Zhihong Zhang
    arXiv preprint arXiv:2503.11164, 2025
  3. Arxiv
    2025_arxiv_cerebro.png
    CEReBrO: Compact Encoder for Representations of Brain Oscillations Using Efficient Alternating Attention
    Alexandru Dimofte, Glenn Anta Bucagu, Thorir Mar Ingolfsson, Xiaying Wang, Andrea Cossettini, Luca Benini, and Yawei Li
    arXiv preprint arXiv:2501.10885, 2025
  4. NeurIPS
    2025_neurips_physiowave.png
    PhysioWave: A Multi-Scale Wavelet-Transformer for Physiological Signal Representation
    Yanlong Chen, Mattia Orlandi, Pierangelo Maria Rapa, Simone Benatti, Luca Benini, and Yawei Li
    In Advances in Neural Information Processing Systems (NeurIPS), 2025
  5. NeurIPS
    2025_neurips_luna.png
    LUNA: Efficient and Topology-Agnostic Foundation Model for EEG Signal Analysis
    Berkay Döner, Thorir Mar Ingolfsson, Luca Benini, and Yawei Li
    In Advances in Neural Information Processing Systems (NeurIPS), 2025
  6. NeurIPS
    2025_neurips_camsam2.png
    CamSAM2: Segment Anything Accurately in Camouflaged Videos
    Yuli Zhou, Guolei Sun, Yawei Li, Yuqian Fu, Luca Benini, and Ender Konukoglu
    In Advances in Neural Information Processing Systems (NeurIPS), 2025
  7. ICCV
    2025_iccv_fastvar.png
    FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning
    Hang Guo, Yawei Li, Taolin Zhang, Jiangshan Wang, Tao Dai, Shu-Tao Xia, and Luca Benini
    In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025
  8. NER
    2025_ner_waveformer.png
    WaveFormer: A Lightweight Transformer Model for Real-time sEMG-based Gesture Recognition
    Yanlong Chen, Mattia Orlandi Orlandi, Pierangelo Maria Rapa, Simone Benatti, Luca Benini, and Yawei Li
    In The International IEEE/EMBS Conference on Neural Engineering (NER), 2025
  9. ISVLSI
    2025_isvlsi_flatattention.png
    FlatAttention: Dataflow and Fabric Collectives Co-Optimization for Efficient Multi-Head Attention on Tile-Based Many-PE Accelerators
    Chi Zhang, Luca Colagrande, Renzo Andri, Thomas Benz, Gamze Islamoglu, Alessandro Nadalini, Francesco Conti, Yawei Li, and Luca Benini
    In IEEE Computer Society Annual Symposium on VLSI, 2025
  10. GLOBECOM
    2025_globecom_mdx.png
    A Compute&Memory Efficient Model-Driven Neural 5G Receiver for Edge AI-assisted RAN
    Mahdi Abdollahpour, Marco Bertuletti, Yichao Zhang, Yawei Li, Luca Benini, and Alessandro Vanelli-Coralli
    In IEEE Conference on Global Communications (GLOBECOM), 2025
  11. ICML
    2025_icml_intlora.png
    IntLoRA: Integral Low-rank Adaptation of Quantized Diffusion Models
    Hang Guo, Yawei Li, Tao Dai, Shu-Tao Xia, and Luca Benini
    In Proceedings of International Conference on Machine Learning, 2025
  12. ICML
    2025_icml_slim-llm.png
    SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models
    Wei Huang, Haotong Qin, Yangdong Liu, Yawei Li, Qinshuo Liu, Xianglong Liu, Luca Benini, Michele Magno, Shiming Zhang, and Xiaojuan Qi
    In Proceedings of International Conference on Machine Learning, 2025
  13. EMBC
    2025_embc_femba.png
    FEMBA: Efficient and Scalable EEG Analysis with a Bidirectional Mamba Foundation Model
    Anna Teagon, Thorir Mar Ingolfsson, Xiaying Wang, Luca Benini, and Yawei Li
    In Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2025
  14. EMBC
    2025_embc_finetuning.png
    Finetuning and Quantization of EEG-Based Foundational BioSignal Models on ECG and PPG Data for Blood Pressure Estimation
    Bálint Tóth, Dominik Senti, Thorir Mar Ingolfsson, Jeffrey Zweidler, Alexandre Elsig, Luca Benini, and Yawei Li
    In Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2025
  15. CVPR
    2025_cvpr_mambairv2.png
    MambaIRv2: Attentive State Space Restoration
    Hang Guo, Yong Guo, Yaohua Zha, Yulun Zhang, Wenbo Li, Tao Dai, Shu-Tao Xia, and Yawei Li
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025
  16. CVPR
    2025_cvpr_ssa.png
    Semantic and Sequential Alignment for Referring Video Object Segmentation
    Feiyu Pan, Hao Fang, Fangkai Li, Yanyu Xu, Yawei Li, Luca Benini, and Xiankai Lu
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025
  17. NeurIPS
    2024_neurips_semanir.png
    Sharing Key Semantics in Transformer Makes Efficient Image Restoration
    Bin Ren, Yawei Li, Jingyun Liang, Rakesh Ranjan, Mengyuan Liu, Rita Cucchiara, Luc Van Gool, Ming-Hsuan Yang, and Nicu Sebe
    In Advances in Neural Information Processing Systems, 2024
  18. ECCV
    2024_eccv_ovformer.png
    Unified Embedding Alignment for Open-Vocabulary Video Instance Segmentation
    Hao Fang, Peng Wu, Yawei Li, Xinxin Zhang, and Xiankai Lu
    In Proceedings of the European Conference on Computer Vision, 2024
  19. ECCV
    2024_eccv_smart_glasses.png
    Ultra-Efficient On-Device Object Detection on AI-Integrated Smart Glasses with TinyissimoYOLO
    Julian Moosmann, Pietro Bonazzi, Yawei Li, Sizhen Bian, Philipp Mayer, Luca Benini, and Michele Magno
    In Proceedings of the European conference on computer vision Workshops, 2024
  20. CVPR
    2024_cvpr_retina.png
    Retina: Low-Power Eye Tracking with Event Camera and Spiking Hardware
    Pietro Bonazzi, Sizhen Bian, Giovanni Lippolis, Yawei Li, Sadique Sheik, and Michele Magno
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2024
  21. CVPR
    2024_cvpr_atd-sr.png
    Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary
    Leheng Zhang, Yawei Li, Xingyu Zhou, Xiaorui Zhao, and Shuhang Gu
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
  22. AICAS
    2024_aicas_q_segment.png
    Q-Segment: Segmenting Images In-Sensor for Vessel-Based Medical Diagnosis
    Pietro Bonazzi, Yawei Li, Sizhen Bian, and Michele Magno
    In Proceedings of the IEEE 6th International Conference on AI Circuits and Systems (AICAS), 2024
  23. MIR
    2023_mir_scunet.png
    Practical Blind Denoising via Swin-Conv-UNet and Data Synthesis
    Kai Zhang, Yawei Li, Jingyun Liang, Jiezhang Cao, Yulun Zhang, Hao Tang, Radu Timofte, and Luc Van Gool
    Machine Intelligence Research, 2023
  24. IROS
    2023_iros_localvit.png
    LocalViT: Analyzing Locality in Vision Transformers
    Yawei Li, Kai Zhang, Jiezhang Cao, Radu Timofte, Michele Magno, Luca Benini, and Luc Van Gool
    In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2023
  25. IEEE Sensors
    2023_sensors_tinytracker.png
    TinyTracker: Ultra-Fast and Ultra-Low-Power Edge Vision for In-Sensor Gaze Estimation
    Pietro Bonazzi, Thomas Ruegg, Sizhen Bian, Yawei Li, and Michele Magno
    In Proceedings of IEEE Sensors, 2023
  26. CVPR
    2023_cvpr_grl.png
    Efficient and Explicit Modelling of Image Hierarchies for Image Restoration
    Yawei Li, Yuchen Fan, Xiaoyu Xiang, Denis Demandolx, Rakesh Ranjan, Radu Timofte, and Luc Van Gool
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023
  27. CVPR
    2023_cvpr_lsdir.png
    LSDIR: A large Scale Dataset for Image Restoration
    Yawei Li, Kai Zhang, Jingyun Liang, Jiezhang Cao, Ce Liu, Rui Gong, Yulun Zhang, Hao Tang, Yun Liu, Denis Demandolx, Rakesh Ranjan, Radu Timofte, and Luc Van Gool
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023
  28. TPAMI
    2022_tpami_DPIR.png
    Plug-and-Play Image Restoration with Deep Denoiser Prior
    Kai Zhang, Yawei Li, Wangmeng Zuo, Lei Zhang, Luc Van Gool, and Radu Timofte
    IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
  29. CVPR
    2022_cvpr_random_pruning.png
    Revisiting Random Channel Pruning for Neural Network Compression
    Yawei Li, Kamil Adamczewski, Wen Li, Shuhang Gu, Radu Timofte, and Luc Van Gool
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
  30. ICCV
    2021_iccv_efficient_gcn.png
    Towards Efficient Graph Convolutional Networks for Point Cloud Handling
    Yawei Li, He Chen, Zhaopeng Cui, Radu Timofte, Marc Pollefeys, Gregory Chirikjian, and Luc Van Gool
    In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021
  31. CVPR
    2021_cvpr_heterogeneity.png
    The Heterogeneity Hypothesis: Finding Layer-Wise Differentiated Network Architectures
    Yawei Li, Wen Li, Martin Danelljan, Zhang Kai, Shuhang Gu, Luc Van Gool, and Radu Timofte
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021
  32. CVPR
    2021_cvpr_dasr.png
    Unsupervised Real-world Image Super Resolution via Domain-distance Aware Training
    Yunxuan Wei, Shuhang Gu, Yawei Li, Radu Timofte, Longcun Jin, and Hengjie Song
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021
  33. ECCV
    2020_eccv_dhp.png
    DHP: Differentiable Meta Pruning via HyperNetworks
    Yawei Li, Shuhang Gu, Kai Zhang, Luc Van Gool, and Radu Timofte
    In Proceedings of the European Conference on Computer Vision, 2020
  34. CVPR
    2020_cvpr_group_sparsity.png
    Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compression
    Yawei Li, Shuhang Gu, Christoph Mayer, Luc Van Gool, and Radu Timofte
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020
  35. ICCV
    2019_iccv_filter_basis.png
    Learning Filter Basis for Convolutional Neural Network Compression
    Yawei Li, Shuhang Gu, Luc Van Gool, and Radu Timofte
    In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019
  36. CVPR
    2019_cvpr_3d_appearance.png
    3D Appearance Super-Resolution with Deep Learning
    Yawei Li, Vagia Tsiminaki, Radu Timofte, Marc Pollefeys, and Luc Van Gool
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019
  37. ICCV
    2019_iccv_sgn.png
    Self-Guided Network for Fast Image Denoising
    Shuhang Gu, Yawei Li, Luc Van Gool, and Radu Timofte
    In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019
  38. CVIU
    Modified Non-Local Means for Super-Resolution of Hybrid Videos
    Yawei Li, Xiaofeng Li, and Zhizhong Fu
    Computer Vision and Image Understanding, 2018
  39. ECCV
    2018_eccvw_carn.png
    CARN: Convolutional Anchored Regression Network for Fast and Accurate Single Image Super-Resolution
    Yawei Li, Eirikur Agustsson, Shuhang Gu, Radu Timofte, and Luc Van Gool
    In Proceedings of the European Conference on Computer Vision Workshops, 2018
  40. Electronics Letters
    Envelope and Phase Statistics of Cauchy Quadratures
    Yawei Li, Xiaofeng Li, Norman C Beaulieu, and Zhizhong Fu
    Electronics Letters, 2016