Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Paper • 2505.19602 • Published May 26 • 13
VeriThinker: Learning to Verify Makes Reasoning Model Efficient Paper • 2505.17941 • Published May 23 • 25
Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient Paper • 2411.17787 • Published Nov 26, 2024 • 12
AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising Paper • 2406.06911 • Published Jun 11, 2024 • 12