arXiv:2604. 08591v2 Announce Type: replace-cross Abstract: Hallucinations in large ASR models present a critical safety risk.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
The paper investigates how nonlinearity in attention mechanisms affects scaling laws in large language models. It finds that nonlinear attention leads to an inverse-depth decay of loss across various data spectra, enabling models to learn both strong and weak spectral directions simultaneously. This behavior contrasts with linear-attention models, which rely on a power-law data spectrum and learn directions sequentially.
arXiv:2606. 07473v1 Announce Type: cross Abstract: Whisper, a widely adopted ASR model, is known to suffer from hallucinations - coherent transcriptions generated for non-speech audio entirely disconnected from the input.
arXiv:2607. 09753v1 Announce Type: cross Abstract: Diffusion models have achieved remarkable success across diverse domains, with performance closely related to the denoising backbones that parameterize the score function.
arXiv:2610.16745v1 Announce Type: cross Abstract: Attention sinks are usually studied after they have formed. We ask whether a measurable hidden-state change appears beforehand and whether changing t...
arXiv:2608. 09417v2 Announce Type: replace Abstract: Deep decoder-only Transformers often replace the original Post-Norm architecture with Pre-Norm variants because Post-Norm training is highly sensitive to warmup and learning rate under conventional initialization schemes.
arXiv:2510. 05554v2 Announce Type: replace Abstract: As large language models scale to longer contexts, attention layers suffer from a fundamental pathology: attention scores collapse toward uniformity as context length $n$ increases, causing tokens to cluster excessively, a phenomenon known as rank-collapse.