arXiv:2608. 08652v1 Announce Type: cross Abstract: We present \LegoLM{}, a structured weight-sharing compression framework for large language models grounded in a systematic study of why global weight sharing fails and how to fix it.
arXiv:2607. 27275v1 Announce Type: new Abstract: Post-training quantization to 4-bit weights is widely reported to be nearly lossless.
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:2607. 23711v1 Announce Type: new Abstract: LoRA fine-tuning can create intruder dimensions: new leading singular vectors of the updated weight matrix $W+BA$ that are nearly orthogonal to all pretrained singular vectors and that drive catastrophic forgetting.
arXiv:2607. 16721v1 Announce Type: new Abstract: The strongest open-weight coding models are mixture-of-experts (MoE) networks: most of their size comes from large pools of "expert" subnetworks, of which only a few act on any token.
arXiv:2608. 02940v1 Announce Type: new Abstract: A reproducible compression statistic can still select the wrong candidate.
arXiv:2608. 02829v1 Announce Type: new Abstract: Model families train every size from scratch.
arXiv:2608. 13565v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures scale large language models (LLMs) while preserving computational efficiency through sparse activation.
arXiv:2607. 10137v1 Announce Type: new Abstract: Post-training quantization (PTQ) of large language models degrades sharply below 4-bit precision.
arXiv:2606. 09864v1 Announce Type: cross Abstract: Key-value (KV) cache quantization is widely used to reduce Large Language Model (LLM) inference memory, yet existing evaluations solely focus on measuring perplexity and accuracy without assessing the safety impact.
arXiv:2605. 18838v3 Announce Type: replace-cross Abstract: Scaling laws predict loss from compute but not how capabilities interact.
arXiv:2608. 02703v1 Announce Type: cross Abstract: Weight-only quantization substantially reduces the storage of large language model (LLM) transformer blocks, but practical backends often retain the final language-modeling head (LM-head) in BF16 or FP16.
arXiv:2606. 07559v1 Announce Type: cross Abstract: Fine-tuning a language model on contexts whose correct completion has a near-synonym competitor often fails silently.