Position Bias Correction is Insufficient for One-Pass Attention Sorting

arXiv:2603.22300v1 Announce Type: cross Abstract: Scaling Transformers to ultra-long contexts is bottlenecked by the $O(n^2 d)$ cost of self-attention. Existing methods reduce

arXiv:2605.15208v1 Announce Type: cross Abstract: Large Language Models are routinely compressed via post-training quantization to reduce inference costs and memory footprint for

arXiv:2607.20524v1 Announce Type: new Abstract: Mean cross-positional attention degradation is widely reported in transformer interpretability, yet whether it causally limits

arXiv:2604.26233v1 Announce Type: new Abstract: As Large Language Models (LLMs) are proposed as legal decision assistants, and even first-instance decision-makers, across a range

arXiv:2606.19349v1 Announce Type: cross Abstract: While In-Context Learning (ICL) is extensively studied in Autoregressive (AR) LLMs, its mechanism within Diffusion Large Language