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

Portuguese

Os modelos do mundo do vídeo preveem quadros futuros a partir de quadros e ações passados. Eles servem como simuladores em que os agentes treinam, planejam ou são avaliados e que os seres humanos podem controlar interativamente. Eles geram no espaço latente de um codificador de vídeo, cuja compressão define seu custo por quadro e quanto tempo cada ação espera para entrar em vigor. No entanto, os modelos mundiais muitas vezes reutilizam os codificadores de geradores de texto para vídeo, construídos para geração offline sem agentes esperando e, sem seus dados de treinamento e código, não retraçáveis em outra compressão.

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