Scholar
Jianyuan Guo
Google Scholar ID: UnAbd4gAAAAJ
City University of Hong Kong (CityU)
Citations & Impact
Citations
18,728
H-index
28
i10-index
36
Publications
20
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- [{'Type': 'Paper', 'Title': 'ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning', 'Conference/Journal': 'IJCV 2025'}, {'Type': 'Paper', 'Title': 'Data-efficient Large Vision Models through Sequential Autoregression', 'Conference/Journal': 'ICML 2024'}, {'Type': 'Paper', 'Title': 'GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer', 'Conference/Journal': 'ICML 2024'}, {'Type': 'Paper', 'Title': 'PrimKD: Primary Modality Guided Multimodal Fusion for RGB-D Semantic Segmentation', 'Conference/Journal': 'ACM MM 2024'}, {'Type': 'Paper', 'Title': 'Token Compensator: Altering Inference Cost of Vision Transformer without Re-Tuning', 'Conference/Journal': 'ECCV 2024'}, {'Type': 'Paper', 'Title': 'Revisit the Power of Vanilla Knowledge Distillation from Small Scale to Large Scale', 'Conference/Journal': 'NeurIPS 2023'}, {'Type': 'Paper', 'Title': 'One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation', 'Conference/Journal': 'NeurIPS 2023'}, {'Type': 'Paper', 'Title': 'VanillaNet: the Power of Minimalism in Deep Learning', 'Conference/Journal': 'NeurIPS 2023'}, {'Type': 'Paper', 'Title': 'Hierarchical relational learning for few-shot knowledge graph completion', 'Conference/Journal': 'ICLR 2023'}, {'Type': 'Paper', 'Title': 'Hire-MLP: Vision MLP via Hierarchical Rearrangement', 'Conference/Journal': 'CVPR 2022'}, {'Type': 'Paper', 'Title': 'CMT: Convolutional Neural Networks Meet Vision Transformers', 'Conference/Journal': 'CVPR 2022'}, {'Type': 'Paper', 'Title': 'An Image Patch is a Wave: Quantum Inspired Vision MLP (WaveMLP)', 'Conference/Journal': 'CVPR 2022'}, {'Type': 'Paper', 'Title': 'Brain-inspired Multilayer Perceptron with Spiking Neurons', 'Conference/Journal': 'CVPR 2022'}, {'Type': 'Paper', 'Title': 'Learning efficient vision transformers via fine-grained manifold distillation', 'Conference/Journal': 'NeurIPS 2022'}]
Background
- Research Interests: Machine perception algorithms and their related applications, including efficient neural networks (e.g., CNN and Transformer) in computer vision and natural language processing, self-supervised learning, neural architecture search, multimodal fusion, and LLM for AGI.
Miscellany
- Personal interests and hobbies not mentioned.
Co-authors