Zhengyang Zhuge
3 papers · 2024–2026 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
Top co-authors
Research topics
Keywords
model compression
(1)
vision transformer
(1)
attention mechanism
(1)
efficient computing
(1)
sample selection
(1)
low-bit quantization
(1)
spiking transformer
(1)
masked image modeling
(1)
token sparsification
(1)
dual alignment
(1)
inter alignment
(1)
intra alignment
(1)
timestep-wise anchor token
(1)
Papers
A Universal Self-Attention Enhancement for Bridging Low-bit Quantization and Vision Transformers
WACV 2026
Patch-Aware Sample Selection for Efficient Masked Image Modeling
AAAI 2024
Towards Efficient Spiking Transformer: a Token Sparsification Framework for Training and Inference Acceleration
ICML 2024