arXiv:2607. 17568v1 Announce Type: cross Abstract: Structured pruning compresses large language models (LLMs) by removing whole computational units, such as attention heads and feed-forward (FFN) channel groups.
Structured pruning compresses large language models (LLMs) by removing whole computational units, such as attention heads and feed-forward (FFN) channel groups. Most training-free methods, however, rank these units independently, implicitly treating the loss from pruning a set as the sum of its individual losses.
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: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: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: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: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...
COEC (Calibrated Orthogonal-Equivalence Compensation) is a training‑free framework that improves structured pruning of large language models by applying alternating left and right orthogonal rotations to the retained weight matrix. The method optimizes the right rotation on a reduced Stiefel manifold, rescales singular values via generalized cross‑validation, tempers the calibration Gram matrix, and adds an alignment penalty to preserve geometric relations between attention projections. Experiments on Llama‑3, Llama‑3.1, and Qwen2.5 show that COEC consistently improves perplexity and zero‑shot accuracy across multiple sparsity levels, outperforming existing compensation techniques.
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.
MWOP (Modality-aware Width-wise Operation Pruning) is a method that independently prunes visual‑to‑visual, text‑to‑visual, and text‑to‑text attention paths within each layer of multimodal large language models, and separately selects feed‑forward network channels for visual and textual inputs. It uses a first‑order Taylor criterion to guide pruning, re‑evaluates FFN importance after attention pruning, and applies LoRA‑based recovery training. The approach is paired with path‑sparse Triton attention kernels and compact visual‑side FFN execution to achieve practical acceleration, preserving token sequences while reducing computation. "whyItMatters":"MWOP achieves a 1.6× prefill speedup on LLaVA‑OneVision‑7B while retaining 99.7% performance, and further boosts token‑compression methods to 2.9× and 2.7× speedups, demonstrating its effectiveness across architectures."
LILA (Latent-Informed Layer Analysis) introduces a calibration‑free method for structured pruning of large language models by scoring neuron importance using the Kolmogorov–Smirnov distance between singular value distributions of full and neuron‑ablated feed‑forward network weight matrices. The approach requires no training, calibration data, or auxiliary networks, and outperforms existing methods such as PruneNet and SliceGPT on LLaMA‑2‑7B and Phi‑2 at various sparsity levels. After a single epoch of LoRA fine‑tuning, LILA matches heavily calibrated baselines, and a Neural Tangent Kernel analysis provides theoretical support for its spectral importance criterion. Additionally, LILA can dynamically allocate sparsity budgets, achieving state‑of‑the‑art generative preservation and revealing architectural bottlenecks at higher compression.
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.