Search papers, labs, and topics across Lattice.
Westlake University
5
0
6
BAG achieves superior performance by dynamically balancing computational efficiency and budget constraints, outperforming traditional caching methods in diverse scenarios.
BudCache redefines caching for diffusion models by prioritizing output quality over traditional heuristic approaches, achieving superior results within fixed compute budgets.
Instance-specific timestep schedules can significantly boost diffusion model performance, challenging the reliance on global discretization strategies.
Ditch the handcrafted coefficients: DyWeight learns how to dynamically weight gradients in diffusion model sampling, slashing compute while boosting image quality.
Content leakage in text-to-image style transfer can be dramatically reduced by simply suppressing the tail components of the style embedding using SVD and a time-aware schedule, without any retraining.
