arXiv AI
Train Overcomplete, Deploy Compact: Scaling Recovery Capacity for Structured LLM Pruning
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computation and Language
Aug 31
Pruning Laws for Large Language Models
arXiv:2504.04342v2 Announce Type: replace Abstract: Scaling up model parameters and training data consistently improves the performance of large language models (LLMs), but at the cost of rapidly gro...
arXiv AI
Aug 5
On the Limits of Layer Pruning for Generative Reasoning in Large Language Models
arXiv:2602. 01997v3 Announce Type: replace-cross Abstract: Recent work has shown that layer pruning can effectively compress large language models (LLMs) while retaining strong performance on classification benchmarks, often with little or no finetuning.
arXiv AI
Jul 16
ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation
arXiv:2607. 13124v1 Announce Type: cross Abstract: Structured pruning is a hardware-friendly way to compress LLMs, but it is mostly validated on multiple-choice recognition tasks, while the same compressed checkpoints can collapse on the free-form generation that deployment actually requires.
arXiv AI
Aug 25
Revisiting the Effectiveness of LLM Pruning for Test-Time Scaling
The paper revisits the impact of pruning on large language models (LLMs) during test-time scaling (TTS). While prior work found that structured pruning degrades reasoning performance, this study shows that unstructured pruning—removing only specific redundant weights—can actually improve TTS performance on reasoning benchmarks for models s1.1-7B and Qwen3-8B, sometimes surpassing the full-weight models. The authors also examine how different layer-wise sparsity allocation strategies affect these outcomes.
arXiv Machine Learning
Jul 14
Prune, Update and Trim: Robust Structured Pruning for Large Language Models
arXiv:2605. 18331v2 Announce Type: replace Abstract: Large Language Models (LLMs) have experienced significant growth and development in recent years.
arXiv Machine Learning
Jun 9
Beyond FLOPs: Benchmarking Real Inference Acceleration of LLM Pruning under a GEMM-Centric Taxonomy
arXiv:2606. 09080v1 Announce Type: new Abstract: Pruning has emerged as a dominant paradigm for accelerating large language model (LLM) inference, spanning a broad spectrum of methods that remove computation across tokens, layers, heads, dimensions, and attention patterns.