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.
By Yaniv Livertovsky, Shahar Somin, Gonen Singer
arXiv:2507. 01900v3 Announce Type: replace-cross Abstract: Pruning is a highly effective approach for compressing large language models (LLMs), significantly reducing inference latency.
By Songtao Liu, Peng Liu
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...
By Dhananjay Saikumar, Blesson Varghese
Sparse autoencoders (SAEs) are commonly used to interpret large language models, but their reliability after pruning is unclear. This study shows that pruning’s effect on an SAE is governed by perturbation energy, a covariance-weighted norm, and that magnitude pruning distorts the representation space by ignoring activation geometry. Activation-aware pruning methods such as Wanda and SparseGPT better preserve SAE behavior, and the authors find that middle layers are especially vulnerable, leading them to propose a layer‑wise sparsity allocation that reduces perplexity for a given sparsity level.
By Suchit Gupte, Xueru Zhang, Mohammad Mahdi Khalili
The paper investigates how quantization and pruning—common compression techniques—affect language models of different sizes. By isolating a small set of attention heads responsible for in-context retrieval, the authors decompose the loss from ablating these heads into components that are compensated by the rest of the network and components that directly impact the output. Their findings show that while smaller models largely recover from such damage, larger models retain most of the loss because their compensatory mechanisms are less effective, indicating that compression can be far more detrimental as models scale.
By Gautam Gupta, Dikshant Kukreja, Unique Kumar, Avni Mittal, Deepanshu Dabas, Kshitij Sah, Erik Cambria, Rajiv Ratn Shah, Zhengkui Wang, Avinash Anand
arXiv:2606. 27449v1 Announce Type: new Abstract: Multi-head attention conventionally partitions the hidden dimension equally across all heads at every layer, enforcing an identical representational subspace dimension (dh = dmodel/h) throughout the models depth.
By Shubham Aggarwal
arXiv:2605. 18331v2 Announce Type: replace Abstract: Large Language Models (LLMs) have experienced significant growth and development in recent years.
By Diego Coello de Portugal Mecke, Tom Hanika, Lars Schmidth-Thieme
The paper investigates how quantization and pruning affect language models of different sizes. It shows that compression damages specific components—particularly attention heads used for in‑context retrieval—more severely in larger models, and that the network’s ability to compensate for this damage diminishes as model size grows. Consequently, compression techniques that appear benign on small models can become costly on larger ones.
arXiv:2607. 23054v1 Announce Type: cross Abstract: Multi-head Latent Attention (MLA), introduced in DeepSeek-V2, compresses key-value pairs through a shared low-rank bottleneck (cKV), achieving 81% KV-cache reduction during inference.
By Dhruvil S, Fenil Sojitra, Ravirajsinh Chauhan
arXiv:2505. 15548v2 Announce Type: replace Abstract: Autoregressive transformer language models frequently exhibit training instability when trained on long sequences, particularly under low-precision arithmetic.
By Suvadeep Hajra
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.
By Manel Kara laoua, Soumia Bouyahiaoui, Aicha Boutorh
The paper introduces FTC, a sequential functional structured Tucker compression method for large language model attentions. FTC adapts its approximation to the current compressed model, jointly exploits the Q/K/V head structure, and treats the output projection separately to handle representation shifts. It achieves the lowest WikiText‑2 perplexity across seven decoder‑only LLMs (6B–32B) at all tested keep ratios, with significant gains under aggressive compression and benefits that transfer to downstream tasks.
By Jiangfeng Chen, Xinyu Wang, Tianshuo Yan, Hanwei Wu, Xiao-Wen Chang, Yang Zhang, Lei Ding