conftrace_

block skipping

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

shared projection (1) rank maximization (1) dynamic patch sampling (1) memory-efficient fine-tuning (1) cross-attention masking (1) low-rank compression (1) large language model (1) diffusion transformer (1) text-to-image generation (1)

Papers

Memory-Efficient Fine-Tuning Diffusion Transformers via Dynamic Patch Sampling and Block Skipping CVPR 2026 SkipCat: Rank-Maximized Low-Rank Compression of Large Language Models via Shared Projection and Block Skipping AAAI 2026