Search papers, labs, and topics across Lattice.
Chinese Academy of Sciences, University of Chinese Academy of Sciences
3
0
4
DiT-Pruning achieves unprecedented image quality retention in Diffusion Transformers, maintaining a CLIP score loss of only 0.001 at 50% sparsity.
Suppressing weight outliers via a Hessian-informed additive transformation unlocks >40% perplexity reduction in 2-bit quantized LLMs compared to standard GPTQ.
Achieve superior LLM pruning performance by first nudging models toward sparsity-friendliness *before* applying any weight removal.
