Ring Forcing: Towards Precise Long-Term Memory for Autoregressive Video Diffusion

Hugging Face Daily Papers Papers

Summary

Ring Forcing is an autoregressive video diffusion framework that enhances long-term memory for precise minute-long video coherence through ring-structured training, history compression, and sparse rotary embeddings.

Scaling video generation to long durations reveals a critical bottleneck: current models lack robust long-term memory. This deficiency can be studied along two critical aspects: object permanence, the ability to precisely reproduce the appearance of objects upon re-entry; and memory capacity, the ability to process ultra-long context and use information from distant history. Robust long-term memory requires both: object permanence without sufficient context handling limits the temporal scope, while long context length without permanence fails to maintain identity. To address this, we present Ring Forcing, an autoregressive video diffusion framework designed to robustly construct and precisely utilize long-term memory. Our ring-structured training strategy enforces retrieval from distant history, effectively reconciling the trade-off between strict historical adherence and generative diversity. To expand memory capacity, we introduce a compression and timestep composition strategy. Under fixed sequence length constraints, this method extends the effective historical span to minutes-long durations and achieves a comprehensive receptive field over the entire history. Furthermore, we present a sparse RoPE mechanism to enable flexible, scalable memory adaptation while fully exploiting pre-trained priors. Extensive experiments demonstrate that Ring Forcing achieves superior minutes-long coherence and object permanence, significantly outperforming state-of-the-art methods.
Original Article
View Cached Full Text

Cached at: 09/01/26, 12:09 PM

Paper page - Ring Forcing: Towards Precise Long-Term Memory for Autoregressive Video Diffusion

Source: https://huggingface.co/papers/2608.26794

Abstract

Ring Forcing is an autoregressive video diffusion framework that improves long-term memory through ring-structured training, history compression, and sparse rotary embeddings to achieve minute-long coherence.

Scaling video generation to long durations reveals a critical bottleneck: current models lack robust long-term memory. This deficiency can be studied along two critical aspects:object permanence, the ability to precisely reproduce the appearance of objects upon re-entry; andmemory capacity, the ability to process ultra-long context and use information from distant history. Robust long-term memory requires both:object permanencewithout sufficient context handling limits the temporal scope, while long context length without permanence fails to maintain identity. To address this, we presentRing Forcing, anautoregressive video diffusionframework designed to robustly construct and precisely utilize long-term memory. Ourring-structured trainingstrategy enforces retrieval from distant history, effectively reconciling the trade-off between strict historical adherence and generative diversity. To expandmemory capacity, we introduce acompression and timestep compositionstrategy. Under fixed sequence length constraints, this method extends the effective historical span to minutes-long durations and achieves a comprehensive receptive field over the entire history. Furthermore, we present asparse RoPEmechanism to enable flexible, scalable memory adaptation while fully exploiting pre-trained priors. Extensive experiments demonstrate thatRing Forcingachieves superior minutes-long coherence andobject permanence, significantly outperforming state-of-the-art methods.

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2608\.26794

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2608.26794 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.26794 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.26794 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles