← Authors

Yingyan Lin

24 papers · 2018–2025 · 7 conferences · across top CS/AI conferences

Achievements

πŸ—ΊοΈ Taxonomy Completionist (35) 🌍 Conference Polyglot (7) πŸƒ Academic Marathon (7) 🌈 Renaissance Researcher (5) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (10) 🀝 Dynamic Duo (15) πŸ‘‘ Triple Crown πŸ† Grand Slam πŸ”¬ Deep Specialist (15) πŸ’Ž Century Club (24) ⚑ Prolific Year (6) πŸ—ƒοΈ Keyword Collector (85) πŸ“ˆ Trend Setter ❓ The Questioner πŸ”₯ Unstoppable (6)

Conferences

ICML (6) NIPS (6) ICLR (5) AAAI (3) ECCV (2) CVPR (1) ICCV (1)

Top co-authors

Yonggan Fu (15) Haoran You (10) Chaojian Li (8) Zhangyang Wang (8) Yue Wang (7) Qixuan Yu (3) Cheng Wan (3) Yang Zhang (3) Xiaohan Chen (3) Yongan Zhang (3)

Research topics

Computer Vision (1) Education (1)

Keywords

model compression (11) neural architecture search (4) convolutional neural network (4) efficient computing (4) adversarial robustness (3) efficient training (2) vision transformer (2) lottery ticket hypothesis (2) energy efficiency (2) knowledge distillation (2) computational efficiency (2) weight sharing (2) model training (2) adversarial training (2) image translation (1) network pruning (1) active learning (1) attention mechanism (1) neural network optimization (1) efficient inference (1)

Papers

Early-Bird Diffusion: Investigating and Leveraging Timestep-Aware Early-Bird Tickets in Diffusion Models for Efficient Training CVPR 2025
ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer NIPS 2023
SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning ECCV 2022
ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networks ICML 2022
DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks ICML 2022
PipeGCN: Efficient Full-Graph Training of Graph Convolutional Networks with Pipelined Feature Communication ICLR 2022
Early-Bird GCNs: Graph-Network Co-optimization towards More Efficient GCN Training and Inference via Drawing Early-Bird Lottery Tickets AAAI 2022
MIA-Former: Efficient and Robust Vision Transformers via Multi-Grained Input-Adaptation AAAI 2022
Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations? ICLR 2022
SACoD: Sensor Algorithm Co-Design Towards Efficient CNN-Powered Intelligent PhlatCam ICCV 2021
Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks NIPS 2021
Locality Sensitive Teaching NIPS 2021
CPT: Efficient Deep Neural Network Training via Cyclic Precision ICLR 2021
HW-NAS-Bench: Hardware-Aware Neural Architecture Search Benchmark ICLR 2021
Double-Win Quant: Aggressively Winning Robustness of Quantized Deep Neural Networks via Random Precision Training and Inference ICML 2021
Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators ICML 2021
HALO: Hardware-Aware Learning to Optimize ECCV 2020
Fractional Skipping: Towards Finer-Grained Dynamic CNN Inference AAAI 2020
FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training NIPS 2020
ShiftAddNet: A Hardware-Inspired Deep Network NIPS 2020
AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks ICML 2020
Drawing Early-Bird Tickets: Toward More Efficient Training of Deep Networks ICLR 2020
E2-Train: Training State-of-the-art CNNs with Over 80% Energy Savings NIPS 2019
Deep k-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions ICML 2018