paper-with-me

홈 › Papers

Stochastic Parroting in Temporal Attention -- Regulating the Diagonal Sink

2026-02-11 · Victoria Hankemeier, Malte Schilling arxiv

Spatio-temporal models analyze spatial structures and temporal dynamics, which makes them prone to information degeneration among space and time. Prior literature has demonstrated that over-squashing in causal attention or temporal convolutions creates a bias on the first tokens. To analyze whether such a bias is present in temporal attention mechanisms, we derive sensitivity bounds on the expected value of the Jacobian of a temporal attention layer. We theoretically show how off-diagonal attention scores depend on the sequence length, and that temporal attention matrices suffer a diagonal attention sink. We suggest regularization methods, and experimentally demonstrate their effectiveness.

📄 PDF Abstract BibTeX arXiv:2602.10956

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Training Diagonal Linear Networks with Stochastic Sharpness-Aware Minimization

2025-03-14 · Gabriel Clara, Sophie Langer, Johannes Schmidt-Hieber

We analyze the landscape and training dynamics of diagonal linear networks in a linear regression task, with the network parameters being perturbed by small isotropic normal noise. The addition of such noise may be inter…

Neither Stochastic Parroting nor AGI: LLMs Solve Tasks through Context-Directed Extrapolation from Training Data Priors

2025-05-29 · Harish Tayyar Madabushi, Melissa Torgbi, Claire Bonial

In this position paper we raise critical awareness of a realistic view of LLM capabilities that eschews extreme alternative views that LLMs are either "stochastic parrots" or in possession of "emergent" advanced reasonin…

In-Context Learning

Context parroting: A simple but tough-to-beat baseline for foundation models in scientific machine learning

2025-05-16 · Yuanzhao Zhang, William Gilpin

Recently-developed time series foundation models for scientific machine learning exhibit emergent abilities to predict physical systems. These abilities include zero-shot forecasting, in which a model forecasts future st…

In-Context LearningTime SeriesTime Series Forecasting

TeDiO: Temporal Diagonal Optimization for Training-Free Coherent Video Diffusion

2026-05-13 · Nurislam Tursynbek, Zhiqiang Lao, Heather Yu, Gedas Bertasius 외 arxiv

Recent text-to-video diffusion transformers generate visually compelling frames, yet still struggle with temporal coherence, often producing flickering, drifting, or unstable motion. We show that these failures leave a c…

Video Generation

Stochastic diagonal estimation with adaptive parameter selection

2024-10-15 · Zongyuan Han, Wenhao Li, Shengxin Zhu

In this paper, we investigate diagonal estimation for large or implicit matrices, aiming to develop a novel and efficient stochastic algorithm that incorporates adaptive parameter selection. We explore the influence of d…