LADDER2 min read
Building a Nested LADDER for LLM Unstructured Post-Training Pruning
Non-uniform allocation can improve post-training pruning of large language models, yet quality can still degrade sharply at high sparsity. To control degradation as sparsity increases, we introduce LADDER (Layer-Wise Allocation via Damage-Driven Evaluation and Refinement), which allocates sparsity…
By Nicol\'as Mauricio Cuadrado \'Avila, Ivo Gollini Navarrete, Martin Tak\'a\v{c}, Samuel Horv\'atharXiv cs.LG
Read the full story
Originally published by arXiv cs.LG on Oct 22, 2026.
Comments
Sign in to join the discussion.