ZipAR: Accelerating Autoregressive Image Generation through Spatial Locality Paper • 2412.04062 • Published 21 days ago • 7 • 2
GATE OpenING: A Comprehensive Benchmark for Judging Open-ended Interleaved Image-Text Generation Paper • 2411.18499 • Published 29 days ago • 18 • 2
ZipVL: Efficient Large Vision-Language Models with Dynamic Token Sparsification and KV Cache Compression Paper • 2410.08584 • Published Oct 11 • 12 • 3
T3M: Text Guided 3D Human Motion Synthesis from Speech Paper • 2408.12885 • Published Aug 23 • 10 • 2