Related papers: Pack and Force Your Memory: Long-form and Consiste…
Understanding and predicting motion is a fundamental component of visual intelligence. Although modern video models exhibit strong comprehension of scene dynamics, exploring multiple possible futures through full video synthesis remains…
Autoregressive video diffusion models support real-time synthesis but suffer from error accumulation and context loss over long horizons. We discover that attention heads in AR video diffusion transformers serve functionally distinct roles…
Video generation is a rapidly advancing research area, garnering significant attention due to its broad range of applications. One critical aspect of this field is the generation of long-duration videos, which presents unique challenges and…
Recent advances in autoregressive video diffusion have enabled real-time frame streaming, yet existing solutions still suffer from temporal repetition, drift, and motion deceleration. We find that naively applying StreamingLLM-style…
The autoregressive video diffusion model has recently gained considerable research interest due to its causal modeling and iterative denoising. In this work, we identify that the multi-head self-attention in these models under-utilizes…
Despite recent advances in diffusion transformers (DiTs) for text-to-video generation, scaling to long-duration content remains challenging due to the quadratic complexity of self-attention. While prior efforts -- such as sparse attention…
Spatially consistent long-horizon video generation aims to maintain temporal and spatial consistency along predefined camera trajectories. Existing methods mostly entangle memory modeling with video generation, leading to inconsistent…
Autoregressive video diffusion models enable open-ended generation through local attention and KV caching. However, existing training-free long-video optimization methods mainly focus on stable extension under a single prompt, making them…
Generating long and consistent videos has emerged as a significant yet challenging problem. While most existing diffusion-based video generation models, derived from image generation models, demonstrate promising performance in generating…
We address the problem of generating long-horizon videos for robotic manipulation tasks. Text-to-video diffusion models have made significant progress in photorealism, language understanding, and motion generation but struggle with…
Producing long, coherent video sequences with stable 3D structure remains a major challenge, particularly in streaming scenarios. Motivated by this, we introduce Endless World, a real-time framework for infinite, 3D-consistent video…
Autoregressive video diffusion models hold promise for world simulation but are vulnerable to exposure bias arising from the train-test mismatch. While recent works address this via post-training, they typically rely on a bidirectional…
Creating a vivid video from the event or scenario in our imagination is a truly fascinating experience. Recent advancements in text-to-video synthesis have unveiled the potential to achieve this with prompts only. While text is convenient…
Autoregressive (AR) diffusion enables streaming, interactive long-video generation by producing frames causally, yet maintaining coherence over minute-scale horizons remains challenging due to accumulated errors, motion drift, and content…
Long video generation is fundamentally a long context memory problem: models must retain and retrieve salient events across a long range without collapsing or drifting. However, scaling diffusion transformers to generate long-context videos…
Interactive real-time autoregressive video generation is essential for applications such as content creation and world modeling, where visual content must adapt to dynamically evolving event conditions. A fundamental challenge lies in…
With recent advancements in video backbone architectures, combined with the remarkable achievements of large language models (LLMs), the analysis of long-form videos spanning tens of minutes has become both feasible and increasingly…
Instructional video generation is an emerging task that aims to synthesize coherent demonstrations of procedural activities from textual descriptions. Such capability has broad implications for content creation, education, and human-AI…
Memory-based video object segmentation methods model multiple objects over long temporal-spatial spans by establishing memory bank, which achieve the remarkable performance. However, they struggle to overcome the false matching and are…
This paper presents WorldPlay, a streaming video diffusion model that enables real-time, interactive world modeling with long-term geometric consistency, resolving the trade-off between speed and memory that limits current methods.…