Shaoxuan He
4 papers · 2025–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(3)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(15)
Conferences
AAAI (1)
CVPR (1)
ICCV (1)
ICML (1)
Top co-authors
Keywords
image generation
(1)
video generation
(1)
token selection
(1)
3d vision
(1)
autoregressive model
(1)
vision-language model
(1)
multimodal large language model
(1)
memory optimization
(1)
sparse attention
(1)
inference acceleration
(1)
kv cache
(1)
spatial reasoning
(1)
parallel decoding
(1)
spatial perception
(1)
contrastive language-image pre-training
(1)
visual generation
(1)
neighboring autoregressive
(1)
Papers
OmniSparse: Training-Aware Fine-Grained Sparse Attention for Long-Video MLLMs
AAAI 2026
SpatialCLIP: Learning 3D-aware Image Representations from Spatially Discriminative Language
CVPR 2025
Neighboring Autoregressive Modeling for Efficient Visual Generation
ICCV 2025
ZipAR: Parallel Autoregressive Image Generation through Spatial Locality
ICML 2025