Zhaoyang Zhang

12

Papers

523

Total Citations

Papers (12)

OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models

AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusion

Image Conductor: Precision Control for Interactive Video Synthesis

DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation

MotionCraft: Crafting Whole-Body Motion with Plug-and-Play Multimodal Controls

NVComposer: Boosting Generative Novel View Synthesis with Multiple Sparse and Unposed Images

Cached Transformers: Improving Transformers with Differentiable Memory Cached

Not All Models Are Equal: Predicting Model Transferability in a Self-Challenging Fisher Space

Differentiable Learning-to-Group Channels via Groupable Convolutional Neural Networks

Real-Time Controllable Denoising for Image and Video

STAR: A Structure-Aware Lightweight Transformer for Real-Time Image Enhancement

Breaking the Communication-Privacy-Accuracy Tradeoff with $f$-Differential Privacy