SHIFT-LLM is a training‑free post‑pruning correction framework that inserts a Linear Residual Adapter (LRA) at each depth‑pruned site in large language models. Each LRA preserves the original residual identity while adding a lightweight affine correction calibrated via closed‑form least‑squares regression on a small held‑out set, thereby approximating the hidden state that would have been produced by the removed block. Experiments across multiple model families and benchmarks show that SHIFT‑LLM consistently recovers accuracy lost to depth pruning, achieving gains up to +15.7 points on Llama‑3.1‑8B‑Instruct with only a few hundred calibration samples and no gradient computation.
By Ali Bahri, Hang Li, Hongliang Li, Zhitang Chen
The paper introduces Weight-Redundancy Pruning (WRP), a forward‑free depth‑pruning technique for large language models that estimates inter‑layer redundancy using only checkpoint weights. WRP compares attention outputs and MLP down‑projection weights across layers, combining pairwise similarities with relative projection‑scale information to guide layer grouping and block selection. Experiments show that WRP consistently outperforms existing forward‑free magnitude pruning methods and approaches the performance of activation‑based pruning across various pruning settings, model families, and downstream tasks.
By Vincent-Daniel Yun, Woosang Lim
arXiv:2605. 30836v2 Announce Type: replace Abstract: Recent SVD based compression methods for large language models like SVD LLM and Basis Sharing can be unified under one optimization problem.
By Snigdha Chandan Khilar
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
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.
By Linghao Kong, Inimai Subramanian, Micah Adler, Dan Alistarh, Dan Gutfreund, Nir Shavit
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.
By Minseok Kang, Hyunwoo Kim, Chanyoung Kim, Minwoo Kim, Jaekoo Lee, Dahuin Jung
arXiv:2605. 27786v2 Announce Type: replace-cross Abstract: Large language models are known to contain representational redundancy across network depth, making depth pruning an effective approach for improving inference efficiency.
By Vincent-Daniel Yun, Youngrae Kim, Woosang Lim, YoungJin Heo, Minkyu Kim, Sunwoo Lee
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
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...
By Jaewon Sok, Jewon Yeom, Seonghyeon Park, Jeongjae Park, Taesup Kim
arXiv:2602. 02599v4 Announce Type: replace Abstract: Long-context inference in large language models (LLMs) is bottlenecked by the memory and compute of the key-value (KV) cache.
By Jihao Xin, Tian Lyu, David Keyes, Hatem Ltaief, Marco Canini
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:2608. 16010v1 Announce Type: new Abstract: Model compression is critical for deploying networks on resource-constrained edge devices.
By Zhaocen Liu, Satvik Praveen, Yi Sheng