model compression posts and papers

Pruning LLMs Like a Physicist: Block Removal as an Ising Optimization Problem huggingface.co

The authors cast transformer block removal as a constrained binary optimization problem equivalent to an Ising glass, using a Hessian‑derived energy as a proxy for downstream quality. Solving the resulting QUBO with classical or quantum‑inspired solvers yields up to 23 MMLU points improvement over prior block‑removal baselines at 50 % depth compression.

Hugging Facehuggingface.coAntonio Tiene, Ali Hashemi, David Jansen, Roman Rausch16h8 min

model compression

Retention-Constrained Post-Training Quantization of Cellpose-SAM for Stem Cell Microscopyarxiv.org

Pruning LLMs Like a Physicist: Block Removal as an Ising Optimization Problemhuggingface.co

Retention-Constrained Post-Training Quantization of Cellpose-SAM for Stem Cell Microscopy arxiv.org

Pruning LLMs Like a Physicist: Block Removal as an Ising Optimization Problem huggingface.co