Chang Zou

10 papers · 2023–2026 · 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 (13) 💎 Century Club · Bronze ⚡ Prolific Year · Productive

Venues

CVPR (4) ICCV (3) AAAI (2) ICLR (1)

Top co-authors

Linfeng Zhang (9) Jiacheng Liu (6) Shikang Zheng (3) Peiliang Cai (3) Junjie Chen (2) Liang Feng (2) Yue Ma (2) Yuqi Lin (2) Xinyu Wang (2) Yuan Ge (1)

Research topics

Deep Learning (9) Models (9) Computer Vision (8) Generation (6) Machine Learning (4) Optimization & Theory · Deep Learning (4) Artificial Intelligence (2) Application Areas (2) Core AI (2) Analysis (1) Architectures (1) Learning Types (1) Optimization & Theory · Machine Learning (1) Processing (1)

Keywords

diffusion transformer (7) feature caching (6) diffusion model (5) image generation (4) inference acceleration (4) video generation (3) model acceleration (2) person re-identification (1) flow matching (1) generative model (1) latent representation (1) ordinary differential equation (1) ode solver (1) linear predictor (1) feature prediction (1) kolmogorov-arnold network (1) speech generation (1) intra-class compactness (1) taylor series expansion (1) text-to-video synthesis (1)

Papers

Beyond Fixed Formulas: Data-Driven Linear Predictor for Efficient Diffusion Models CVPR 2026 DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching CVPR 2026 Forecast Then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers AAAI 2026 From Sketch to Fresco: Efficient Diffusion Transformer with Progressive Resolution CVPR 2026 LESA: Learnable Stage-Aware Predictors for Diffusion Model Acceleration CVPR 2026 WaveEx: Accelerating Flow Matching-based Speech Generation via Wavelet-guided Extrapolation AAAI 2026 Accelerating Diffusion Transformers with Token-wise Feature Caching ICLR 2025 EEdit : Rethinking the Spatial and Temporal Redundancy for Efficient Image Editing ICCV 2025 From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers ICCV 2025 Discrepant and Multi-Instance Proxies for Unsupervised Person Re-Identification ICCV 2023