Pruning LLMs Like a Physicist: Block Removal as an Ising Optimization Problem
• 25
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Safety for Whom? Boundary-Aware Self-Distillation for Controlled LLM Safety Refusal
Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs
Articles
Article
Pruning LLMs Like a Physicist: Block Removal as an Ising Optimization Problem
MultiverseComputingCAI
• • 25 Article
Safety for Whom? Refusing the Right Subset of a Topic, Not the Whole Topic
MultiverseComputingCAI
• • 31 Article
Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original
MultiverseComputingCAI
• • 69
Article
Making Knowledge Distillation Cheap Enough to Run at Scale
MultiverseComputingCAI
• • 42