Newest papers

Rethinking Video Autoencoders for Interactive World Models

Adrien Ramanana Rahary, Yutong Bai, Nicolas Dufour, Patrick Pérez, David Picard · 2026 · arXiv

DOI: 10.48550/arXiv.2610.30129 · open-access PDF

Korean

비디오 세계 모델은 과거 프레임과 행동에서 미래 프레임을 예측합니다. 그들은 에이전트가 훈련, 계획 또는 평가되는 시뮬레이터로 봉사하며 인간이 상호 작용하여 통제 할 수 있습니다. 그들은 비디오 자동 인코더의 숨겨진 공간에서 생성하며, 압축은 프레임당 비용을 설정하고 각 행동이 효과를 기다리는 데 얼마나 오래 걸리는지입니다.그러나 세계 모델은 종종 오프라인 생성을 위해 만들어진 텍스트-to-비디오 생성기의 자동 인코더를 재사용하며, 에이전트가 기다리지 않고 훈련 데이터와 코드가 없으면 다른 압축에서 다시 훈련 할 수 없습니다.

Machine translation (Meta M2M100); the English original follows.

Abstract

Video world models predict future frames from past frames and actions. They serve as simulators in which agents train, plan or are evaluated, and that humans can control interactively. They generate in the latent space of a video autoencoder, whose compression sets their cost per frame and how long each action waits to take effect. Yet world models often reuse the autoencoders of text-to-video generators, built for offline generation with no agent waiting and, without their training data and code, not retrainable at another compression. We therefore ask how, where and how much a world model sh

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.30129, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange