相关论文: LUMA: Low-Dimension Unified Motion Alignment with …

The goal of this paper is to optimize the training process of diffusion-based text-to-speech models. While recent studies have achieved remarkable advancements, their training demands substantial time and computational costs, largely due to…

Diffusion models have demonstrated remarkable performance in the domain of text-to-image generation. However, most widely used models still employ CLIP as their text encoder, which constrains their ability to comprehend dense prompts,…

Our goal is to generate realistic human motion from natural language. Modern methods often face a trade-off between model expressiveness and text-to-motion alignment. Some align text and motion latent spaces but sacrifice expressiveness;…

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…

Video Diffusion Models (VDMs) have demonstrated remarkable capabilities in synthesizing realistic videos by learning from large-scale data. Although vanilla Low-Rank Adaptation (LoRA) can learn specific spatial or temporal movement to…

We introduce MoLingo, a text-to-motion (T2M) model that generates realistic, lifelike human motion by denoising in a continuous latent space. Recent works perform latent space diffusion, either on the whole latent at once or…

Text-to-motion generation holds significant potential for cross-linguistic applications, yet it is hindered by the lack of bilingual datasets and the poor cross-lingual semantic understanding of existing language models. To address these…

Large language models have achieved remarkable success under the autoregressive paradigm, yet high-quality text generation need not be tied to a fixed left-to-right order. Existing alternatives still struggle to jointly achieve generation…

Diffusion Language Models (DLMs) promise parallel generation and bidirectional context, yet they underperform autoregressive (AR) models in both likelihood modeling and generated text quality. We identify that this performance gap arises…

In this paper, we introduce LGTM, a novel Local-to-Global pipeline for Text-to-Motion generation. LGTM utilizes a diffusion-based architecture and aims to address the challenge of accurately translating textual descriptions into…

The remarkable success of diffusion models in text-to-image generation has sparked growing interest in expanding their capabilities to a variety of multi-modal tasks, including image understanding, manipulation, and perception. These tasks…

Recent DiT-based text-to-image models increasingly adopt LLMs as text encoders, yet text conditioning remains largely static and often utilizes only a single LLM layer, despite pronounced semantic hierarchy across LLM layers and…

We present LLaDA2.0-Uni, a unified discrete diffusion large language model (dLLM) that supports multimodal understanding and generation within a natively integrated framework. Its architecture combines a fully semantic discrete tokenizer, a…

Generating realistic human motion sequences from text descriptions is a challenging task that requires capturing the rich expressiveness of both natural language and human motion.Recent advances in diffusion models have enabled significant…

Recent advancements in text-to-image diffusion models have yielded impressive results in generating realistic and diverse images. However, these models still struggle with complex prompts, such as those that involve numeracy and spatial…

While diffusion Multimodal Large Language Models (dMLLMs) have recently achieved remarkable strides in multimodal generation, the development of interpretability mechanisms has lagged behind their architectural evolution. Unlike traditional…

Unified multimodal models (UMMs) achieve strong performance in both understanding and generation by learning a shared latent space, yet they often exhibit functional inconsistency between these two capabilities. We observe that this issue…

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.…

In this paper, we propose a unified framework that leverages a single pretrained LLM for Motion-related Multimodal Generation, referred to as MoMug. MoMug integrates diffusion-based continuous motion generation with the model's inherent…

Autoregressive (AR) large audio language models (LALMs) such as Qwen-2.5-Omni have achieved strong performance on audio understanding and interaction, but scaling them remains costly in data and computation, and strictly sequential decoding…