arXiv preprint finds that minimizing reconstruction loss in weight-only PTQ does not guarantee better model performance and can hurt results when input activation distributions…
arXiv preprint from October 2026 introduces Sera, a framework that extracts degradation semantics from battery time series using rule-based knowledge and LLM interpretation…
arXiv preprint from 2026-10-08 introduces LS-LoRA, which applies LoRA adapters only to Transformer layers with low input-output cosine similarity. This forward-only proxy…
New preprint introduces MAP4CS, a multi-dimensional pruning method that selects high-quality subsets for code retriever fine-tuning in RAG systems. Experiments show comparable…
The October 8 2026 arXiv preprint presents ResOT, a training-free inference-time approach using localized distribution alignment via Gaussian optimal transport to repair…
Ai2 presented hybrid transformer-recurrent models at COLM 2026 that match OLMo 3 7B MMLU accuracy with 49% fewer tokens while releasing training infrastructure and advancing…
arXiv preprint dated October 8 2026 introduces ARGUS, an evidence-constrained agentic system that separates deterministic biological computation from LLM reasoning to improve…
An arXiv preprint introduces ZIP-SR and ZE-EDEN, two approaches to 4-bit optimizer-state quantization for AdamW that reduce validation-loss gap to 32-bit baselines by up to 70%…
A new arXiv preprint dated 2026-10-07 introduces Step-Aligned Privileged Distillation, an off-policy self-distillation technique that converts fixed demonstrations into…
arXiv preprint introduces DisParQ, a self-supervised method that derives spatially grounded discrete concepts and quantized attributes from a frozen DINOv2 backbone. Evaluated…
arXiv preprint identifies LayerNorm scales and GELU approximations as main quantization error sources in transformers. TR-PTQ uses shared Taylor Region primitives for fully…
arXiv preprint dated October 7 2026 presents UniSkill a method that uses contrastive action feedback from existing trajectories to evaluate skill proposals without additional…