Zhekai Zhang

5 papers · 2020–2026 · 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 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (10) 🐣 Hot Topic Early Bird

Venues

ICLR (3) CVPR (1) ICML (1)

Top co-authors

Song Han (5) Yujun Lin (4) Muyang Li (4) Han Cai (3) Enze Xie (3) Ligeng Zhu (2) Junsong Chen (2) Junyu Chen (2) Jun-Yan Zhu (2) Kelly Peng (1)

Research topics

Deep Learning (5) Computer Vision (3) Generation (3) Models (3) Techniques (3) Artificial Intelligence (2) Machine Learning (2) Application Areas (2) Core AI (2) Architectures (1) Optimization & Theory · Deep Learning (1) Optimization & Theory · Machine Learning (1)

Keywords

diffusion model (2) weight quantization (2) activation quantization (2) neural architecture search (1) efficient inference (1) low-rank decomposition (1) singular value decomposition (1) linear attention (1) video diffusion model (1) diffusion transformer (1) 4-bit quantization (1) network specialization (1) spatiotemporal similarity (1) progressive shrinking (1) low-rank component (1) 8-bit optimizer (1) depth-growth paradigm (1) model depth pruning (1) repeated sampling strategy (1) model compression (1)

Papers

DeltaQuant: 4-bit Video Diffusion Models with Spatiotemporal Delta Smoothing CVPR 2026 SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer ICML 2025 SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion Transformers ICLR 2025 SVDQuant: Absorbing Outliers by Low-Rank Component for 4-Bit Diffusion Models ICLR 2025 Once-for-All: Train One Network and Specialize it for Efficient Deployment ICLR 2020