arXiv:2607. 23634v1 Announce Type: cross Abstract: Attention enables context modeling via query-key scoring with softmax normalization.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2508. 17821v3 Announce Type: replace-cross Abstract: This paper investigates the limitations of the normalization in attention mechanisms.
arXiv:2607. 22781v1 Announce Type: cross Abstract: High task performance does not show whether a model retains prediction-relevant structural information in its internal representation.
arXiv:2512. 11784v2 Announce Type: replace Abstract: Softmax attention is a central component of transformer architectures, yet its nonlinear structure poses significant challenges for theoretical analysis.
arXiv:2602. 03681v2 Announce Type: replace-cross Abstract: The quadratic computational complexity of softmax transformers has become a bottleneck in long-context scenarios.
arXiv:2510. 13554v2 Announce Type: replace-cross Abstract: The reasoning pattern of Large language models (LLMs) remains opaque, and reinforcement learning (RL) typically applies uniform credit across an entire generation, blurring the distinction between pivotal and routine steps.
arXiv:2608. 09558v1 Announce Type: new Abstract: How expressive is prompting a transformer?