Shaoxuan He

5 papers · 2025–2026 · 4 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 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (10) ⭐ Rising Star (5)

Venues

CVPR (2) AAAI (1) ICCV (1) ICML (1)

Top co-authors

Yefei He (3) Feng Chen (3) Bohan Zhuang (3) Yuanyu He (3) Hong Zhou (2) Kaipeng Zhang (2) Zhou Zhao (2) Ziang Zhang (1) Zhenbang Sun (1) Zhizeng Ye (1)

Research topics

Computer Vision (4) Deep Learning (4) Machine Learning (3) Generation (3) Models (3) Application Areas (2) Artificial Intelligence (1) Analysis (1) Core AI (1) Learning Types (1) Optimization & Theory (1) Techniques (1)

Keywords

parallel decoding (2) video generation (2) 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) speculative decoding (1) contrastive language-image pretraining (1) sampling acceleration (1) rejection sampling (1) spatial perception (1) visual generation (1) feature caching (1) neighboring autoregressive (1) diffusion acceleration (1)

Papers

OmniSparse: Training-Aware Fine-Grained Sparse Attention for Long-Video MLLMs AAAI 2026 TC-Pade: Trajectory-Consistent Pade Approximation for Diffusion Acceleration CVPR 2026 Neighboring Autoregressive Modeling for Efficient Visual Generation ICCV 2025 SpatialCLIP: Learning 3D-aware Image Representations from Spatially Discriminative Language CVPR 2025 ZipAR: Parallel Autoregressive Image Generation through Spatial Locality ICML 2025