Related papers: TinyFusion: Diffusion Transformers Learned Shallow
Deep learning models have been widely used during the last decade due to their outstanding learning and abstraction capacities. However, one of the main challenges any scientist has to face using deep learning models is to establish the…
Diffusion models are now the undisputed state-of-the-art for image generation and image restoration. However, they require large amounts of computational power for training and inference. In this paper, we propose lightweight diffusion…
The ever-increasing fine-tuning cost of large-scale pre-trained models gives rise to the importance of dataset pruning, which aims to reduce dataset size while maintaining task performance. However, existing dataset pruning methods require…
Structured pruning is a standard tool for compressing deep neural networks, but its practical performance depends on how sparsity is allocated across layers. We propose FAIR-Pruner, a search-free framework for adaptive layer-wise structured…
The sparsely gated mixture of experts (MoE) architecture sends different inputs to different subnetworks, i.e., experts, through trainable routers. MoE reduces the training computation significantly for large models, but its deployment can…
The impressive performance of deep learning architectures is associated with a massive increase in model complexity. Millions of parameters need to be tuned, with training and inference time scaling accordingly, together with energy…
Denoising diffusion models have been a mainstream approach for image generation, however, training these models often suffers from slow convergence. In this paper, we discovered that the slow convergence is partly due to conflicting…
As one of the most successful generative models, diffusion models have demonstrated remarkable efficacy in synthesizing high-quality images. These models learn the underlying high-dimensional data distribution in an unsupervised manner.…
Diffusion Policy is a powerful technique tool for learning end-to-end visuomotor robot control. It is expected that Diffusion Policy possesses scalability, a key attribute for deep neural networks, typically suggesting that increasing model…
Neural network pruning is an essential approach for reducing the computational complexity of deep models so that they can be well deployed on resource-limited devices. Compared with conventional methods, the recently developed dynamic…
State-of-the-art text-to-image diffusion models (DMs) achieve remarkable quality, yet their massive parameter scale (8-11B) poses significant challenges for inferences on resource-constrained devices. In this paper, we present…
Current structural pruning methods face two significant limitations: (i) they often limit pruning to finer-grained levels like channels, making aggressive parameter reduction challenging, and (ii) they focus heavily on parameter and FLOP…
Deep learning has been able to outperform humans in terms of classification accuracy in many tasks. However, to achieve robustness to adversarial perturbations, the best methodologies require to perform adversarial training on a much larger…
Diffusion Transformers have emerged as the preeminent models for a wide array of generative tasks, demonstrating superior performance and efficacy across various applications. The promising results come at the cost of slow inference, as…
Scene flow estimation, which aims to predict per-point 3D displacements of dynamic scenes, is a fundamental task in the computer vision field. However, previous works commonly suffer from unreliable correlation caused by locally constrained…
This paper introduces LLM-Streamline, a pioneer work on layer pruning for large language models (LLMs). It is based on the observation that different layers have varying impacts on hidden states, enabling the identification of less…
Data pruning is the problem of identifying a core subset that is most beneficial to training and discarding the remainder. While pruning strategies are well studied for discriminative models like those used in classification, little…
To reduce computational overhead while maintaining model performance, model pruning techniques have been proposed. Among these, structured pruning, which removes entire convolutional channels or layers, significantly enhances computational…
Tokenizing images into compact visual representations is a key step in learning efficient and high-quality image generative models. We present a simple diffusion tokenizer (DiTo) that learns compact visual representations for image…
\textit{Nature is infinitely resolution-free}. In the context of this reality, existing diffusion models, such as Diffusion Transformers, often face challenges when processing image resolutions outside of their trained domain. To address…