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.
arXiv:2607. 03057v1 Announce Type: cross Abstract: The rapid growth in the parameter scale of large language models (LLMs) has created a strong demand for efficient compression techniques.
arXiv:2605. 15491v2 Announce Type: replace-cross Abstract: Layer pruning removes entire Transformer decoder blocks from large language models, but introduces a mismatch between the hidden state received by the next surviving layer and the distribution it was trained to process, leading to significant performance degradation.
arXiv:2606. 03465v1 Announce Type: cross Abstract: Post-training compression is essential for deploying large language models (LLMs) under tight resource constraints.
Post-training compression is essential for deploying large language models (LLMs) under tight resource constraints. Tensor decompositions have emerged as a promising direction, offering compact parameterizations well suited to Transformer weight structures.
arXiv:2411. 09816v5 Announce Type: replace Abstract: Large neural networks achieve state-of-the-art performance on many tasks, yet their sheer size hinders deployment on resource-constrained devices.
arXiv:2601. 22580v2 Announce Type: replace-cross Abstract: The success of Large Language Models (LLMs) hinges on the stable training of deep Transformer architectures.
arXiv:2606. 02559v1 Announce Type: cross Abstract: Post-training compression of Large Language Models (LLMs) removes entire architectural components, either deleting them or replacing them with fitted modules.
arXiv:2604. 21254v3 Announce Type: replace Abstract: LLM architecture research generally aims to maximize model quality subject to fixed compute/latency budgets.
arXiv:2607. 18284v1 Announce Type: cross Abstract: To excel at their domain large language models are comprised of billions of parameters.
arXiv:2606. 07098v1 Announce Type: cross Abstract: We present SigmaScale, a method for learning auxiliary scaling matrices $S$ to aid truncated Singular Value Decomposition (SVD) based Large Language Model (LLM) compression.
arXiv:2509. 25136v3 Announce Type: replace Abstract: Activation-aware low-rank factorization techniques yield strong compression results but are generally confined to linear layers, while existing whitening-based theory typically makes an implicit full-rank assumption on activations.
arXiv:2606. 15157v1 Announce Type: cross Abstract: KV cache compression is essential for reducing the memory cost of long-context large language model inference.