paper-with-me

홈 › Papers

Temporal Anchoring in Deepening Embedding Spaces: Event-Indexed Projections, Drift, Convergence, and an Internal Computational Architecture

2025-08-13 · Faruk Alpay, Bugra Kilictas, Hamdi Alakkad arxiv

We develop an operator-theoretic framework for temporal anchoring in embedding spaces, modeled as drift maps interleaved with event-indexed blocks culminating in affine projections. We provide complete proofs for a variable-block contraction lemma (products of Lipschitz factors), a drift--projection convergence theorem with explicit uniform-gap envelopes, and ontological convergence under nested affine anchors with a robustness variant. We formalize an internal Manuscript Computer (MC) whose computations are defined purely by these operators and prove a rigorous finite-run equivalence theorem (with perturbation bounds). For attention layers, we give a self-contained proof that softmax is $1/2$-Lipschitz in $\ell_2$ and derive sufficient layer-contraction conditions (orthogonal/non-orthogonal heads). All floats are placed exactly where written; the manuscript uses only in-paper pseudocode and appendix figures.

📄 PDF Abstract BibTeX arXiv:2508.09693

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Extracting Event Temporal Relations via Hyperbolic Geometry

2021-09-12 · EMNLP 2021 11 · Xingwei Tan, Gabriele Pergola, Yulan He

Detecting events and their evolution through time is a crucial task in natural language understanding. Recent neural approaches to event temporal relation extraction typically map events to embeddings in the Euclidean sp…

Natural Language UnderstandingRelationRelation ExtractionTemporal Relation Extraction

Temporal Anchoring of Events for the TimeBank Corpus

2016-08-01 · ACL 2016 8 · Nils Reimers, Nazanin Dehghani, Iryna Gurevych

Cross-Document Temporal Relation Extraction with Temporal Anchoring Events

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Automatically extracting a timeline on a certain topic from multiple documents has been a challenge in natural language processing, partly due to the difficulty of collecting large amounts of training data. In this work,…

ArticlesRelationRelation ExtractionRelation Prediction+1

Lookahead Anchoring: Preserving Character Identity in Audio-Driven Human Animation

2025-10-27 · Junyoung Seo, Rodrigo Mira, Alexandros Haliassos, Stella Bounareli 외 arxiv

Audio-driven human animation models often suffer from identity drift during temporal autoregressive generation, where characters gradually lose their identity over time. One solution is to generate keyframes as intermedi…

RCL: Recurrent Continuous Localization for Temporal Action Detection

2022-03-14 · CVPR 2022 1 · Qiang Wang, Yanhao Zhang, Yun Zheng, Pan Pan

Temporal representation is the cornerstone of modern action detection techniques. State-of-the-art methods mostly rely on a dense anchoring scheme, where anchors are sampled uniformly over the temporal domain with a disc…

Action Detection