Han Cai

han-cai's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 7 papers about 1 month ago

SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer

Paper • 2501.18427 • Published Jan 30 • 21

Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity

Paper • 2502.01776 • Published Feb 3 • 3

Accelerate High-Quality Diffusion Models with Inner Loop Feedback

Paper • 2501.13107 • Published Jan 22 • 2

SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation

Paper • 2503.09641 • Published Mar 12 • 40

Scaling Vision Pre-Training to 4K Resolution

Paper • 2503.19903 • Published Mar 25 • 42

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer

Paper • 2507.04947 • Published Jul 7

DC-AE 1.5: Accelerating Diffusion Model Convergence with Structured Latent Space

Paper • 2508.00413 • Published Aug 1 • 3

authored a paper 3 months ago

Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation

Paper • 2505.18875 • Published May 24 • 42

authored 12 papers 10 months ago

COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training

Paper • 2410.19313 • Published Oct 25, 2024 • 19

Long Text Generation via Adversarial Training with Leaked Information

Paper • 1709.08624 • Published Sep 24, 2017

TinyTL: Reduce Activations, Not Trainable Parameters for Efficient On-Device Learning

Paper • 2007.11622 • Published Jul 22, 2020

Real-Time Bidding by Reinforcement Learning in Display Advertising

Paper • 1701.02490 • Published Jan 10, 2017

Path-Level Network Transformation for Efficient Architecture Search

Paper • 1806.02639 • Published Jun 7, 2018

APQ: Joint Search for Network Architecture, Pruning and Quantization Policy

Paper • 2006.08509 • Published Jun 15, 2020

MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning

Paper • 2110.15352 • Published Oct 28, 2021

Large-scale Interactive Recommendation with Tree-structured Policy Gradient

Paper • 1811.05869 • Published Nov 14, 2018

Activation Maximization Generative Adversarial Nets

Paper • 1703.02000 • Published Mar 6, 2017

Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation

Paper • 2205.01271 • Published May 3, 2022

Network Augmentation for Tiny Deep Learning

Paper • 2110.08890 • Published Oct 17, 2021

Efficient Architecture Search by Network Transformation

Paper • 1707.04873 • Published Jul 16, 2017 • 2