相关论文: MotionMERGE: A Multi-granular Framework for Human …

Generative modeling of human motion has broad applications in computer animation, virtual reality, and robotics. Conventional approaches develop separate models for different motion synthesis tasks, and typically use a model of a small size…

With the rapid progress of large language models (LLMs), multimodal frameworks that unify understanding and generation have become promising, yet they face increasing complexity as the number of modalities and tasks grows. We observe that…

Text-guided motion editing enables high-level semantic control and iterative modifications beyond traditional keyframe animation. Existing methods rely on limited pre-collected training triplets, which severely hinders their versatility in…

Fine-grained image-text alignment is a pivotal challenge in multimodal learning, underpinning key applications such as visual question answering, image captioning, and vision-language navigation. Unlike global alignment, fine-grained…

Recent advancements in personalized Text-to-Video (T2V) generation have made significant strides in synthesizing character-specific content. However, these methods face a critical limitation: the inability to perform fine-grained control…

Recent advances in video generation have shown promise for generating future scenarios, critical for planning and control in autonomous driving and embodied intelligence. However, real-world applications demand more than visually plausible…

Stylized motion generation is actively studied in computer graphics, especially benefiting from the rapid advances in diffusion models. The goal of this task is to produce a novel motion respecting both the motion content and the desired…

Human motion understanding and generation are crucial for vision and robotics but remain limited in reasoning capability and test-time planning. We propose MoRL, a unified multimodal motion model trained with supervised fine-tuning and…

Motion understanding is fundamental to physical reasoning, enabling models to infer dynamics and predict future states. However, state-of-the-art models still struggle on recent motion benchmarks, primarily due to the scarcity of…

This research delves into the problem of interactive editing of human motion generation. Previous motion diffusion models lack explicit modeling of the word-level text-motion correspondence and good explainability, hence restricting their…

Text-driven motion generation has achieved substantial progress with the emergence of diffusion models. However, existing methods still struggle to generate complex motion sequences that correspond to fine-grained descriptions, depicting…

Generating lifelike human motions from descriptive texts has experienced remarkable research focus in the recent years, propelled by the emerging requirements of digital humans.Despite impressive advances, existing approaches are often…

Human motion generation has been widely studied due to its crucial role in areas such as digital humans and humanoid robot control. However, many current motion generation approaches disregard physics constraints, frequently resulting in…

Motion generation, the task of synthesizing realistic motion sequences from various conditioning inputs, has become a central problem in computer vision, computer graphics, and robotics, with applications ranging from animation and virtual…

Discrete motion tokenization has recently enabled Large Language Models (LLMs) to serve as versatile backbones for motion understanding and motion-language reasoning. However, existing pipelines typically decouple motion quantization from…

Despite continuous advancements in deep learning for understanding human motion, existing models often struggle to accurately identify action timing and specific body parts, typically supporting only single-round interaction. Such…

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…

Fine-grained video action recognition can be conceptualized as a video-text matching problem. Previous approaches often rely on global video semantics to consolidate video embeddings, which can lead to misalignment in video-text pairs due…

Model merging constructs versatile models by integrating task-specific models without requiring labeled data or expensive joint retraining. Although recent methods improve adaptability to heterogeneous tasks by generating customized merged…

Text-to-motion generation has advanced with diffusion- and flow-based generative models, yet supervised pretraining remains insufficient to align models with high-level objectives such as semantic consistency, realism, and human preference.…