相关论文: Dance Like a Chicken: Low-Rank Stylization for Hum…

In this paper, we introduce DirectorLLM, a novel video generation model that employs a large language model (LLM) to orchestrate human poses within videos. As foundational text-to-video models rapidly evolve, the demand for high-quality…

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…

We introduce MoRAG, a novel multi-part fusion based retrieval-augmented generation strategy for text-based human motion generation. The method enhances motion diffusion models by leveraging additional knowledge obtained through an improved…

Low-rank adaptation is a popular parameter-efficient fine-tuning method for large language models. In this paper, we analyze the impact of low-rank updating, as implemented in LoRA. Our findings suggest that the low-rank updating mechanism…

Public large-scale text-to-image diffusion models, such as Stable Diffusion, have gained significant attention from the community. These models can be easily customized for new concepts using low-rank adaptations (LoRAs). However, the…

Fine-tuning large language models (LLMs) aims to adapt pre-trained models to specific tasks using relatively small and domain-specific datasets. Among Parameter-Efficient Fine-Tuning (PEFT) methods, Low-Rank Adaptation (LoRA) stands out by…

Stylized motion breathes life into characters. However, the fixed skeleton structure and style representation hinder existing data-driven motion synthesis methods from generating stylized motion for various characters. In this work, we…

Dancing with music is always an essential human art form to express emotion. Due to the high temporal-spacial complexity, long-term 3D realist dance generation synchronized with music is challenging. Existing methods suffer from the…

Personalized text-to-image generation aims to synthesize novel images of a specific subject or style using only a few reference images. Recent methods based on Low-Rank Adaptation (LoRA) enable efficient single-concept customization by…

3D human motion generation has seen substantial advancement in recent years. While state-of-the-art approaches have improved performance significantly, they still struggle with complex and detailed motions unseen in training data, largely…

We propose a simple and novel method for generating 3D human motion from complex natural language sentences, which describe different velocity, direction and composition of all kinds of actions. Different from existing methods that use…

Diffusion models have recently shown the ability to generate high-quality images. However, controlling its generation process still poses challenges. The image style transfer task is one of those challenges that transfers the visual…

Text-to-motion generation has gained increasing attention, but most existing methods are limited to generating short-term motions that correspond to a single sentence describing a single action. However, when a text stream describes a…

Efficient fine-tuning plays a fundamental role in modern large models, with low-rank adaptation emerging as a particularly promising approach. However, the existing variants of LoRA are hampered by limited expressiveness, a tendency to…

Recent progress in large models has led to significant advances in unified multimodal generation and understanding. However, the development of models that unify motion-language generation and understanding remains largely underexplored.…

Large pretrained diffusion models can provide strong priors beneficial for many graphics applications. However, generative applications such as neural rendering and inverse methods such as SVBRDF estimation and intrinsic image decomposition…

In this paper, we present a predictor-corrector strategy for constructing rank-adaptive dynamical low-rank approximations (DLRAs) of matrix-valued ODE systems. The strategy is a compromise between (i) low-rank step-truncation approaches…

We propose DemoDiffusion, a simple method for enabling robots to perform manipulation tasks by imitating a single human demonstration, without requiring task-specific training or paired human-robot data. Our approach is based on two…

Large pre-trained models, such as large language models (LLMs), present significant resource challenges for fine-tuning due to their extensive parameter sizes, especially for applications in mobile systems. To address this, Low-Rank…

We propose LoRA-MCL, a training scheme that extends next-token prediction in language models with a method designed to decode diverse, plausible sentence continuations at inference time. Traditional language modeling is an intrinsically…