Related papers: Macro-from-Micro Planning for High-Quality and Par…

While large-scale video diffusion models have demonstrated impressive capabilities in generating high-resolution and semantically rich content, a significant gap remains between their pretraining performance and real-world deployment…

We present TempoMaster, a novel framework that formulates long video generation as next-frame-rate prediction. Specifically, we first generate a low-frame-rate clip that serves as a coarse blueprint of the entire video sequence, and then…

Recent advances in large language models (LLMs) have enabled breakthroughs in many multimodal generation tasks, but a significant performance gap still exists in text-to-motion generation, where LLM-based methods lag far behind non-LLM…

A diffusion probabilistic model (DPM), which constructs a forward diffusion process by gradually adding noise to data points and learns the reverse denoising process to generate new samples, has been shown to handle complex data…

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…

Recently, interactive digital human video generation has attracted widespread attention and achieved remarkable progress. However, building such a practical system that can interact with diverse input signals in real time remains…

Diffusion language models have recently emerged as a competitive alternative to autoregressive language models. Beyond next-token generation, they are more efficient and flexible by enabling parallel and any-order token generation. However,…

Autoregressive models for text sometimes generate repetitive and low-quality output because errors accumulate during the steps of generation. This issue is often attributed to exposure bias - the difference between how a model is trained,…

As text generation has become a core capability of modern Large Language Models (LLMs), it underpins a wide range of downstream applications. However, most existing LLMs rely on autoregressive (AR) generation, producing one token at a time…

Visual generation is dominated by three paradigms: AutoRegressive (AR), diffusion, and Visual AutoRegressive (VAR) models. Unlike AR and diffusion, VARs operate on heterogeneous input structures across their generation steps, which creates…

This paper considers an efficient video modeling process called Video Latent Flow Matching (VLFM). Unlike prior works, which randomly sampled latent patches for video generation, our method relies on current strong pre-trained image…

While recent machine learning research has revealed connections between deep generative models such as VAEs and rate-distortion losses used in learned compression, most of this work has focused on images. In a similar spirit, we view…

We present Flowception, a novel non-autoregressive and variable-length video generation framework. Flowception learns a probability path that interleaves discrete frame insertions with continuous frame denoising. Compared to autoregressive…

Video generation has witnessed great success recently, but their application in generating long videos still remains challenging due to the difficulty in maintaining the temporal consistency of generated videos and the high memory cost…

Ultra long video understanding remains an open challenge, as existing vision language models (VLMs) falter on such content due to limited context length and inefficient long term memory retention. To address this, recent works have…

Foundational world models must be both interactive and preserve spatiotemporal coherence for effective future planning with action choices. However, present models for long video generation have limited inherent world modeling capabilities…

Motion generation is essential for animating virtual characters and embodied agents. While recent text-driven methods have made significant strides, they often struggle with achieving precise alignment between linguistic descriptions and…

Despite recent progress of pre-trained language models on generating fluent text, existing methods still suffer from incoherence problems in long-form text generation tasks that require proper content control and planning to form a coherent…

We tackle the long video generation problem, i.e.~generating videos beyond the output length of video generation models. Due to the computation resource constraints, video generation models can only generate video clips that are relatively…

Diffusion models have revolutionized image and video generation, achieving unprecedented visual quality. However, their reliance on transformer architectures incurs prohibitively high computational costs, particularly when extending…