arXiv Machine Learning
Jul 31
WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning
arXiv:2607. 28418v1 Announce Type: cross Abstract: Pruning is a promising approach for improving the efficiency of LLMs.
LEAP: Learnable End-to-End Adaptive Pruning of Large Language Models
arXiv:2605. 17289v2 Announce Type: replace-cross Abstract: Unstructured sparsity is now natively accelerated by recent GPU kernels and dataflow hardware, shifting the bottleneck from inference execution to the pruning algorithm.
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 Machine Learning
Aug 10
The Sparsity Whisperer
arXiv:2608. 06630v1 Announce Type: new Abstract: Pruning reduces the inference cost of large language models, but existing criteria primarily preserve large activations or reconstruct layer outputs.
arXiv Machine Learning
Aug 10
Prune Once: Retraining-Free Task-Agnostic Pruning for Vision-Language Models
arXiv:2608. 06901v1 Announce Type: cross Abstract: Vision-language models (VLMs) have achieved remarkable generalization across diverse multimodal tasks through large-scale pre-training, yet their rapidly increasing computational and memory requirements pose significant challenges for deployment in constrained environments.
arXiv Machine Learning
Jul 21
NIRVANA: Structured Pruning Reimagined for Large Language Model Compression
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 Machine Learning
Jul 22
SHUFFLESPARSE: Learned Shuffles for Structured Sparse Networks
arXiv:2510. 14812v2 Announce Type: replace Abstract: Structured weight sparsity accelerates training and inference on modern GPUs, but it trails unstructured dynamic sparse training (DST) in accuracy especially at extreme sparsity.
arXiv Machine Learning
Sep 10
Hidden in Plain Sight: The Overlooked Significance of Canonical Elements for Extreme LLM Sparsity
arXiv:2609.06557v1 Announce Type: new Abstract: Large language models (LLMs) are often considered fragile under aggressive sparsification, and maintaining reliable performance typically requires stic...
arXiv Machine Learning
Aug 4
GPrune-LLM: Generalization-Aware Structured Pruning for Large Language Models
arXiv:2603. 13418v2 Announce Type: replace Abstract: Structured pruning is widely applied to compress large language models (LLMs), but its performance depends heavily on how neuron importance is estimated.
arXiv Machine Learning
Sep 1
MOONSHOT : A Framework for Multi-Objective Pruning of Vision and Large Language Models
arXiv:2604.13287v2 Announce Type: replace Abstract: Weight pruning is a common technique for compressing large neural networks. We focus on the challenging post-training one-shot setting, where a pre...
arXiv AI
4d ago
Data-Free Pruning of Self-Attention Layers in LLMs
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 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 AI
Sep 7
Don't Drop Dropout: Optimizing Layer Sparsity for Efficient LLM Training and Inference
The paper demonstrates that layer dropout, also known as stochastic depth, can be effectively used in state‑of‑the‑art large language model (LLM) training. By optimizing the layer distribution, schedule, and optimizer settings, the authors show that layer dropout can reduce training loss while saving up to 25 % of training FLOPs. Additionally, layer dropout enables post‑training optimizations such as early exit and self‑speculative decoding, achieving up to 1.5× inference speedup with negligible accuracy loss across models ranging from 271 M to 8.2 B parameters and datasets up to 160 B tokens.