Related papers: T2M-GPT: Generating Human Motion from Textual Desc…

Enabling humanoid robots to synthesize complex, physically coherent motions from natural language commands is a cornerstone of autonomous robotics and human-robot interaction. While diffusion models have shown promise in this text-to-motion…

Text-driven human motion generation based on diffusion strategies establishes a reliable foundation for multimodal applications in human-computer interactions. However, existing advances face significant efficiency challenges due to the…

This study explores the potential of open-source video conditional generation models as encoders for downstream tasks, focusing on instance segmentation using the BAIR Robot Pushing Dataset. The researchers propose using video prediction…

Deep latent variable models (LVM) such as variational auto-encoder (VAE) have recently played an important role in text generation. One key factor is the exploitation of smooth latent structures to guide the generation. However, the…

Recent progress in stochastic motion prediction, i.e., predicting multiple possible future human motions given a single past pose sequence, has led to producing truly diverse future motions and even providing control over the motion of some…

This work proposes a model for continual learning on tasks involving temporal sequences, specifically, human motions. It improves on a recently proposed brain-inspired replay model (BI-R) by building a biologically-inspired conditional…

Modern machine learning systems achieve great success when trained on large datasets. However, these datasets usually contain sensitive information (e.g. medical records, face images), leading to serious privacy concerns. Differentially…

Although autoregressive models have achieved promising results on image generation, their unidirectional generation process prevents the resultant images from fully reflecting global contexts. To address the issue, we propose an effective…

Conditional Generative Models are now acknowledged an essential tool in Machine Learning. This paper focuses on their control. While many approaches aim at disentangling the data through the coordinate-wise control of their latent…

A major challenge in quantum computing is its application to large real-world datasets due to scarce quantum hardware resources. One approach to enabling tractable quantum models for such datasets involves finding low-dimensional…

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…

Text-to-Motion (T2M) generation aims to synthesize realistic and semantically aligned human motion sequences from natural language descriptions. However, current approaches face dual challenges: Generative models (e.g., diffusion models)…

Trajectory-controlled human motion generation aims to synthesize realistic human motions conditioned on both textual descriptions and spatial trajectories. However, existing methods suffer from two critical limitations: first, the conflict…

Human-motion generation is a long-standing challenging task due to the requirement of accurately modeling complex and diverse dynamic patterns. Most existing methods adopt sequence models such as RNN to directly model transitions in the…

We propose an algorithm, guided variational autoencoder (Guided-VAE), that is able to learn a controllable generative model by performing latent representation disentanglement learning. The learning objective is achieved by providing…

The variational autoencoder (VAE) framework is a popular option for training unsupervised generative models, featuring ease of training and latent representation of data. The objective function of VAE does not guarantee to achieve the…

Human motion generation aims to generate natural human pose sequences and shows immense potential for real-world applications. Substantial progress has been made recently in motion data collection technologies and generation methods, laying…

Generative pre-trained models have demonstrated remarkable effectiveness in language and vision domains by learning useful representations. In this paper, we extend the scope of this effectiveness by showing that visual robot manipulation…

Variational Autoencoders and Generative Adversarial Networks remained the state-of-the-art (SOTA) generative models until 2022. Now they are superseded by diffusion-based models. Efforts to improve traditional models have stagnated as a…

Large Vision Language Models (VLMs) effectively bridge the modality gap through extensive pretraining, acquiring sophisticated visual representations aligned with language. However, it remains underexplored whether these representations,…