Related papers: ReAlign: Text-to-Motion Generation via Step-Aware …

We introduce MotionRL, the first approach to utilize Multi-Reward Reinforcement Learning (RL) for optimizing text-to-motion generation tasks and aligning them with human preferences. Previous works focused on improving numerical performance…

When hearing music, it is natural for people to dance to its rhythm. Automatic dance generation, however, is a challenging task due to the physical constraints of human motion and rhythmic alignment with target music. Conventional…

Text-guided motion synthesis aims to generate 3D human motion that not only precisely reflects the textual description but reveals the motion details as much as possible. Pioneering methods explore the diffusion model for text-to-motion…

Recently, diffusion-based deep generative models (e.g., Stable Diffusion) have shown impressive results in text-to-image synthesis. However, current text-to-image models often require multiple passes of prompt engineering by humans in order…

Flow and diffusion models produce high-quality samples, but adapting them to user preferences or constraints post-training remains costly and brittle, a challenge commonly called reward alignment. We argue that efficient reward alignment…

We explore the methodology and theory of reward-directed generation via conditional diffusion models. Directed generation aims to generate samples with desired properties as measured by a reward function, which has broad applications in…

Video diffusion models lack explicit geometric supervision during training, leading to inconsistency artifacts such as object deformation, spatial drift, and depth violations in generated videos. To address this limitation, we propose a…

Text-to-motion (T2M) generation aims to control the behavior of a target character via textual descriptions. Leveraging text-motion paired datasets, existing T2M models have achieved impressive performance in generating high-quality motions…

Distillation-based acceleration has become foundational for making autoregressive streaming video diffusion models practical, with distribution matching distillation (DMD) as the de facto choice. Existing methods, however, train the student…

Reference-to-video (R2V) generation is a controllable video synthesis paradigm that constrains the generation process using both text prompts and reference images, enabling applications such as personalized advertising and virtual try-on.…

Human motion generation aims to produce plausible human motion sequences according to various conditional inputs, such as text or audio. Despite the feasibility of existing methods in generating motion based on short prompts and simple…

Text-guided molecule generation is a task where molecules are generated to match specific textual descriptions. Recently, most existing SMILES-based molecule generation methods rely on an autoregressive architecture. In this work, we…

Recent advances in generative motion synthesis have enabled the production of realistic human motions from diverse input modalities. However, synthesizing compound actions from texts, which integrate multiple concurrent actions into…

Recent text-to-image (T2I) diffusion models have achieved remarkable advancement, yet faithfully following complex textual descriptions remains challenging due to insufficient interactions between textual and visual features. Prior…

Generating human motion that satisfies customized zero-shot goal functions, enabling applications such as controllable character animation and behavior synthesis for virtual agents, is a critical capability. While current approaches handle…

Video generation has achieved significant advances through rectified flow techniques, but issues like unsmooth motion and misalignment between videos and prompts persist. In this work, we develop a systematic pipeline that harnesses human…

Large-scale generative models have shown impressive image-generation capabilities, propelled by massive data. However, this often inadvertently leads to the generation of harmful or inappropriate content and raises copyright concerns.…

Text-driven human motion generation aims to synthesize realistic motion sequences that follow textual descriptions. Despite recent advances, accurately aligning motion dynamics with textual semantics remains a fundamental challenge. In this…

Reward guidance, also known as posterior sampling, is a popular method for test-time adaptation and post-training in continuous diffusion models. In this paper, we study reward guidance for discrete diffusion language models; now, one…

Recent advances in diffusion models have improved controllable streetscape generation and supported downstream perception and planning tasks. However, challenges remain in accurately modeling driving scenes and generating long videos. To…