Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
MMLAB CUHK, CPII under InnoHK
4
0
6
A single 24GB GPU can now perform untiled 4K VSR at 2x DiT speed, thanks to hybrid attention that balances local and global interactions.
Token pruning can be done more effectively by directly linking token scores to their utility, achieving high accuracy with significantly reduced computational costs.
Unlock 5x faster autoregressive image generation by using a single entropy signal to simultaneously optimize draft prediction and enable single-step diffusion decoding.
Stop micro-managing your image editing: PhotoAgent autonomously plans and executes multi-step edits based on your aesthetic intent, outperforming instruction-following baselines.