Han Cai

14

Papers

40

Total Citations

Papers (14)

Condition-Aware Neural Network for Controlled Image Generation

Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search

NeurIPS 2025arXiv

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs

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

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

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

EfficientViT: Lightweight Multi-Scale Attention for High-Resolution Dense Prediction

Scaling Vision Pre-Training to 4K Resolution

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

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

DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models

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

Memory-efficient Patch-based Inference for Tiny Deep Learning

Path-Level Network Transformation for Efficient Architecture Search