AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders Paper • 2510.19779 • Published Oct 22 • 60
Efficient Hyperparameter Tuning via Trajectory Invariance Principle Paper • 2509.25049 • Published Sep 29 • 4
SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention Paper • 2509.24006 • Published Sep 28 • 118