Related papers: DiT-HC: Enabling Efficient Training of Visual Gene…

Diffusion Transformers (DiTs) have demonstrated remarkable generative capabilities, particularly benefiting from Transformer architectures that enhance visual and artistic fidelity. However, their inherently sequential denoising process…

Micro-macro models provide a powerful tool to study the relationship between microscale mechanisms and emergent macroscopic behavior. However, the detailed microscopic modeling may require tracking and evolving a high-dimensional…

Large language models (LLMs) such as OpenAI's ChatGPT and Google's Gemini have demonstrated unprecedented capabilities of autoregressive AI models across multiple tasks triggering disruptive technology innovations around the world. However,…

Many of the most performant deep learning models today in fields like language and image understanding are fine-tuned models that contain billions of parameters. In anticipation of workloads that involve serving many of such large models to…

We present EPIC, an AI-driven platform designed to augment operational data analytics. EPIC employs a hierarchical multi-agent architecture where a top-level large language model provides query processing, reasoning and synthesis…

Although Diffusion Transformer (DiT) has emerged as a predominant architecture for image and video generation, its iterative denoising process results in slow inference, which hinders broader applicability and development. Caching-based…

Existing approaches to train neural networks that use large images require to either crop or down-sample data during pre-processing, use small batch sizes, or split the model across devices mainly due to the prohibitively limited memory…

Visual generation quality has been greatly promoted with the rapid advances in diffusion transformers (DiTs), which is attributed to the scaling of model size and complexity. However, these attributions also hinder the practical deployment…

To respond to the need of efficient training and inference of deep neural networks, a plethora of domain-specific hardware architectures have been introduced, such as Google Tensor Processing Units and NVIDIA Tensor Cores. A common feature…

Privacy-preserving computation techniques like homomorphic encryption (HE) and secure multi-party computation (SMPC) enhance data security by enabling processing on encrypted data. However, the significant computational and CPU-DRAM data…

Deep learning techniques have become widely utilized in histopathology image classification due to their superior performance. However, this success heavily relies on the availability of substantial labeled data, which necessitates…

The trend in industry is towards heterogeneous multicore processors (HMCs), including chips with CPUs and massively-threaded throughput-oriented processors (MTTOPs) such as GPUs. Although current homogeneous chips tightly couple the cores…

Optimal deployment of deep neural networks (DNNs) on state-of-the-art Systems-on-Chips (SoCs) is crucial for tiny machine learning (TinyML) at the edge. The complexity of these SoCs makes deployment non-trivial, as they typically contain…

The growing demand for computational resources in machine learning has made efficient resource allocation a critical challenge, especially in heterogeneous hardware clusters where devices vary in capability, age, and energy efficiency.…

Generative Pre-trained Transformer (GPT) is a state-of-the-art machine learning model capable of generating human-like text through natural language processing (NLP). GPT is trained on massive amounts of text data and uses deep learning…

Recent advances in diffusion models have demonstrated remarkable capabilities in video generation. However, the computational intensity remains a significant challenge for practical applications. While feature caching has been proposed to…

This article presents an automatic approach to quickly derive a good solution for hardware resource partition and task granularity for task-based parallel applications on heterogeneous many-core architectures. Our approach employs a…

In recent years, large language models have demonstrated remarkable performance across various natural language processing (NLP) tasks. However, deploying these models for real-world applications often requires efficient inference solutions…

The quality of the latent space in visual tokenizers (e.g., VAEs) is crucial for modern generative models. However, the standard reconstruction-based training paradigm produces a latent space that is biased towards low-level information,…

The rapid growth of large language models (LLMs) has outpaced the evolution of single-GPU hardware, making model scale increasingly constrained by memory capacity rather than computation. While modern training systems extend GPU memory…