相关论文: Efficient Training for Human Video Generation with…

This paper introduces EasyAnimate, an efficient and high quality video generation framework that leverages diffusion transformers to achieve high-quality video production, encompassing data processing, model training, and end-to-end…

Despite their success, large pretrained vision models remain vulnerable to catastrophic forgetting when adapted to new tasks in class-incremental settings. Parameter-efficient fine-tuning (PEFT) alleviates this by restricting trainable…

Generative modeling has recently shown remarkable promise for visuomotor policy learning, enabling flexible and expressive control across diverse embodied AI tasks. However, existing generative policies often struggle with data…

Video generation models have demonstrated remarkable performance, yet their broader adoption remains constrained by slow inference speeds and substantial computational costs, primarily due to the iterative nature of the denoising process.…

Direct Preference Optimization (DPO) has been successfully used to align large language models (LLMs) according to human preferences, and more recently it has also been applied to improving the quality of text-to-image diffusion models.…

Evolutionary Reinforcement Learning (EvoRL) has emerged as a promising approach to overcoming the limitations of traditional reinforcement learning (RL) by integrating the Evolutionary Computation (EC) paradigm with RL. However, the…

Scaling video diffusion transformers is fundamentally bottlenecked by two compounding costs: the expensive quadratic complexity of attention per step, and the iterative sampling steps. In this work, we propose EFlow, an efficient few-step…

Video diffusion models are able to generate high-quality videos by learning strong spatial-temporal priors on large-scale datasets. In this paper, we aim to investigate whether such priors derived from a generative process are suitable for…

In recent years, diffusion models have gained popularity for their ability to generate higher-quality images in comparison to GAN models. However, like any other large generative models, these models require a huge amount of data,…

Video generation has been advancing rapidly, and diffusion transformer (DiT) based models have demonstrated remark- able capabilities. However, their practical deployment is of- ten hindered by slow inference speeds and high memory con-…

Perceptual studies demonstrate that conditional diffusion models excel at reconstructing video content aligned with human visual perception. Building on this insight, we propose a video compression framework that leverages conditional…

Video generation models have made significant progress in simulating future states, showcasing their potential as world simulators in embodied scenarios. However, existing models often lack robust understanding, limiting their ability to…

Traditional end-to-end (E2E) training of deep networks necessitates storing intermediate activations for back-propagation, resulting in a large memory footprint on GPUs and restricted model parallelization. As an alternative, greedy local…

Training on edge devices poses several challenges as these devices are generally resource-constrained, especially in terms of power. State-of-the-art techniques at the device level reduce the GPU frequency to enforce power constraints,…

Ego-to-exo video generation refers to generating the corresponding exocentric video according to the egocentric video, providing valuable applications in AR/VR and embodied AI. Benefiting from advancements in diffusion model techniques,…

Temporal Interaction Graphs (TIGs) are widely employed to model intricate real-world systems such as financial systems and social networks. To capture the dynamism and interdependencies of nodes, existing TIG embedding models need to…

Applying deep reinforcement learning (RL) on real systems suffers from slow data sampling. We propose an enhanced generative adversarial network (EGAN) to initialize an RL agent in order to achieve faster learning. The EGAN utilizes the…

While text-to-video diffusion models have made significant strides, many still face challenges in generating videos with temporal consistency. Within diffusion frameworks, guidance techniques have proven effective in enhancing output…

Diffusion models have achieved remarkable success in generating high quality image and video data. More recently, they have also been used for image compression with high perceptual quality. In this paper, we present a novel approach to…

Machine learning is the dominant approach to artificial intelligence, through which computers learn from data and experience. In the framework of supervised learning, a necessity for a computer to learn from data accurately and efficiently…