arXiv:2507. 01900v3 Announce Type: replace-cross Abstract: Pruning is a highly effective approach for compressing large language models (LLMs), significantly reducing inference latency.
arXiv:2601.06787v2 Announce Type: replace Abstract: Large Language Models (LLMs) are known to contain significant redundancy, yet a systematic explanation for why certain components, particularly in...
arXiv:2504. 21174v2 Announce Type: replace Abstract: Deep learning drives a new wave in computing systems and triggers the automation of increasingly complex problems.
arXiv:2605. 18331v2 Announce Type: replace Abstract: Large Language Models (LLMs) have experienced significant growth and development in recent years.
arXiv:2509. 14230v2 Announce Type: replace Abstract: While structured pruning presents a highly effective pathway for accelerating Large Language Model (LLM) inference, existing methods frequently suffer from significant performance degradation and demand computationally retraining to recover capabilities.
arXiv:2512.20636v2 Announce Type: replace-cross Abstract: Many self-attention sublayers in large language models (LLMs) can be removed with little to no loss. We attribute this to the Attention Suppr...
arXiv:2606. 19150v1 Announce Type: new Abstract: The remarkable success of Transformer-based models in natural language processing stems from architectural scaling, which leads to a large number of parameters and hinders deployment in resource-constrained environments.
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...
The paper shows that only a small subset of attention heads in vision-language models is responsible for selecting critical visual tokens. By pruning tokens based on similarity before LLM reasoning and then applying head‑aware pruning during reasoning, the proposed ProViP framework achieves high task performance with significant speedups. Experiments on LLaVA‑1.5‑7B demonstrate 95.9% performance retention and a 1.62× inference speedup at an 88.9% pruning ratio.
arXiv:2606. 24970v1 Announce Type: new Abstract: Pruning Large Language Models (LLMs) reduces memory and inference costs by removing parts of the network, producing smaller models that retain most of their accuracy.
arXiv:2607. 22587v1 Announce Type: new Abstract: Large language models (LLMs) achieve strong performance across diverse tasks but their deployment is constrained by the memory and compute cost of their parameters.
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.
The paper introduces STD, a hierarchical token pruning framework for Large Vision‑Language Models that aligns pruning strategies with the functional roles of different network stages. By using high‑frequency spectral analysis in shallow layers, Gaussian‑smoothed attention in intermediate layers, and a stability‑adaptive trigger in deep layers, STD preserves essential visual information while aggressively reducing token counts. Experiments demonstrate that STD outperforms existing pruning methods, achieving up to 94.4% token reduction and a 3.9× speed‑up on LLaVA‑NeXT‑7B.