相关论文: Analysis of DAWNBench, a Time-to-Accuracy Machine …

The advancements in generative modeling, particularly the advent of diffusion models, have sparked a fundamental question: how can these models be effectively used for discriminative tasks? In this work, we find that generative models can…

Machine learning models for text classification often excel on in-distribution (ID) data but struggle with unseen out-of-distribution (OOD) inputs. Most techniques for improving OOD robustness are not applicable to settings where the model…

Inverse problems in partial differential equations (PDEs) involve estimating the physical parameters of a system from observed spatiotemporal solution fields. Neural networks are well-suited for PDE parameter estimation due to their…

Fine-tuning on task-specific question-answer pairs is a predominant method for enhancing the performance of instruction-tuned large language models (LLMs) on downstream tasks. However, in certain specialized domains, such as healthcare or…

Deep learning models perform poorly when domain shifts exist between training and test data. Test-time adaptation (TTA) is a paradigm to mitigate this issue by adapting pre-trained models using only unlabeled test samples. However, existing…

Many optimizers have been proposed for training deep neural networks, and they often have multiple hyperparameters, which make it tricky to benchmark their performance. In this work, we propose a new benchmarking protocol to evaluate both…

Model quantization has emerged as an indispensable technique to accelerate deep learning inference. While researchers continue to push the frontier of quantization algorithms, existing quantization work is often unreproducible and…

With the increasing artificial intelligence application, deep neural network (DNN) has become an emerging task. However, to train a good deep learning model will suffer from enormous computation cost and energy consumption. Recently,…

Contrastive Language-Image Pretraining (CLIP) excels at learning generalizable image representations but often falls short in zero-shot inference on certain downstream datasets. Test-time adaptation (TTA) mitigates this issue by adjusting…

Although it has been extensively explored in theory, decentralized learning is not yet green-lighted for production use, largely due to a lack of stability, scalability, and generality in large scale DNN training. To shed light on the…

TensorDash is a hardware level technique for enabling data-parallel MAC units to take advantage of sparsity in their input operand streams. When used to compose a hardware accelerator for deep learning, TensorDash can speedup the training…

These days, although deep neural networks (DNNs) have achieved a noticeable progress in a wide range of research area, it lacks the adaptability to be employed in the real-world applications because of the environment discrepancy problem.…

Speech enhancement models should meet very low latency requirements typically smaller than 5 ms for hearing assistive devices. While various low-latency techniques have been proposed, comparing these methods in a controlled setup using DNNs…

Domain shift is a common problem in the realistic world, where training data and test data follow different data distributions. To deal with this problem, fully test-time adaptation (TTA) leverages the unlabeled data encountered during test…

We present RETA (Relative Timing Analysis), a differential timing analysis technique to verify the impact of an update on the execution time of embedded software. Timing analysis is computationally expensive and labor intensive. Software…

With new accelerator hardware for DNN, the computing power for AI applications has increased rapidly. However, as DNN algorithms become more complex and optimized for specific applications, latency requirements remain challenging, and it is…

Tuning tensor program generation involves searching for various possible program transformation combinations for a given program on target hardware to optimize the tensor program execution. It is already a complex process because of the…

Recently, test time adaptation (TTA) has attracted increasing attention due to its power of handling the distribution shift issue in the real world. Unlike what has been developed for convolutional neural networks (CNNs) for image data, TTA…

Despite the empirical success in various domains, it has been revealed that deep neural networks are vulnerable to maliciously perturbed input data that much degrade their performance. This is known as adversarial attacks. To counter…

Training deep neural networks with Stochastic Gradient Descent, or its variants, requires careful choice of both learning rate and batch size. While smaller batch sizes generally converge in fewer training epochs, larger batch sizes offer…