Related papers: MaskControl: Spatio-Temporal Control for Masked Mo…
We present Meissonic, which elevates non-autoregressive masked image modeling (MIM) text-to-image to a level comparable with state-of-the-art diffusion models like SDXL. By incorporating a comprehensive suite of architectural innovations,…
Despite the success in large-scale text-to-image generation and text-conditioned image editing, existing methods still struggle to produce consistent generation and editing results. For example, generation approaches usually fail to…
Generating human motion guided by conditions such as textual descriptions is challenging due to the need for datasets with pairs of high-quality motion and their corresponding conditions. The difficulty increases when aiming for finer…
Masked diffusion language models (MDLMs) generate text via iterative masked-token denoising, enabling mask-parallel decoding and distinct controllability and efficiency tradeoffs from autoregressive LLMs. Yet, efficient representation-level…
We present SceneNAT, a single-stage masked non-autoregressive Transformer that synthesizes complete 3D indoor scenes from natural language instructions through only a few parallel decoding passes, offering improved performance and…
Autoregressive language models dominate modern text generation, yet their sequential nature introduces fundamental limitations: decoding is slow, and maintaining global coherence remains challenging. Diffusion models offer a promising…
The conditional text-to-image diffusion models have garnered significant attention in recent years. However, the precision of these models is often compromised mainly for two reasons, ambiguous condition input and inadequate condition…
Video representation learning has seen tremendous progress in recent years. This has been driven by many factors, including the scale of training and the success of visual models trained contrastively with language. While these factors have…
In this work, we introduce an unconditional video generative model, InMoDeGAN, targeted to (a) generate high quality videos, as well as to (b) allow for interpretation of the latent space. For the latter, we place emphasis on interpreting…
Text-conditioned diffusion models have emerged as powerful tools for high-quality video generation. However, enabling Interactive Video Generation (IVG), where users control motion elements such as object trajectory, remains challenging.…
Query-based Vision Transformer segmentation models typically reconstruct dense spatial feature maps to predict masks, inheriting design patterns from convolutional architectures. We show that this explicit image-space reconstruction is not…
We introduce MarDini, a new family of video diffusion models that integrate the advantages of masked auto-regression (MAR) into a unified diffusion model (DM) framework. Here, MAR handles temporal planning, while DM focuses on spatial…
Generating videos of complex human motions such as flips, cartwheels, and martial arts remains challenging for current video diffusion models. Text-only conditioning is temporally ambiguous for fine-grained motion control, while explicit…
Motion controllability is crucial in video synthesis. However, most previous methods are limited to single control types, and combining them often results in logical conflicts. In this paper, we propose a disentangled and unified framework,…
We have recently seen tremendous progress in realistic text-to-motion generation. Yet, the existing methods often fail or produce implausible motions with unseen text inputs, which limits the applications. In this paper, we present OMG, a…
The DEtection TRansformer (DETR) is a powerful end-to-end object detector, yet its one-to-one matching strategy suffers from slow convergence and low recall. A common approach to address this issue is to use one-to-many label assignment to…
Emerging video diffusion models achieve high visual fidelity but fundamentally couple scene dynamics with camera motion, limiting their ability to provide precise spatial and temporal control. We introduce a 4D-controllable video diffusion…
The increasing prevalence of Large Language Models (LMs) in critical applications highlights the need for controlled language generation strategies that are not only computationally efficient but that also enjoy performance guarantees. To…
In the realm of motion generation, the creation of long-duration, high-quality motion sequences remains a significant challenge. This paper presents our groundbreaking work on "Infinite Motion", a novel approach that leverages long text to…
There is an increasing demand for controller design techniques capable of addressing the complex requirements of todays embedded applications. This demand has sparked the interest in symbolic control where lower complexity models of control…