Newest papers

Trajectory Replay: Continuous-Time Mixture Transport for Lifelong Generative Models

Alessandro Palma, Charles Jones, Tristan Cinquin, Fabian J. Theis, Frederik Wenkel · 2026 · arXiv

DOI: 10.48550/arXiv.2610.26749 · open-access PDF

Korean

사전 훈련된 연속 시간 생성 모델을 이전 작업을 잊지 않고 연속적으로 들어오는 데이터에 적응시키는 것은 평생 학습의 핵심 과제입니다. 선도적 인 재생 전략은 역사적인 작업에 대해 훈련 된 생성 모델을 사용하여 자신의 연속 업데이트를 경험의 합성 샘플로 향상시킵니다.그러나 모든 훈련 단계에서 완전한 경로 시뮬레이션을 필요로하며, 이는 판단 오류를 축적하고 재생된 역사적 분포를 악화시킬 수 있습니다.여기에, 우리는 업데이트된 속도 페이를 훈련함으로써 샘플 생성을 우회하는 경로 재생을 제안합니다.

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

Abstract

Adapting pre-trained continuous-time generative models to sequentially incoming data without forgetting earlier tasks is a central challenge in lifelong learning. A leading strategy, generative replay, uses a generative model trained on historical tasks to augment its own continual update with synthetic samples from experience. However, it requires full trajectory simulations at every training step, which accumulate discretization errors and can degrade the replayed historical distribution. Here, we propose trajectory replay, which bypasses sample generation by training an updated velocity fie

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=2610.26749, 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