Related papers: Retrosynthesis Prediction with Local Template Retr…

Deep neural networks have achieved state-of-the-art results in various vision and/or language tasks. Despite the use of large training datasets, most models are trained by iterating over single input-output pairs, discarding the remaining…

In silico tools are important for generating novel hypotheses and exploring alternatives in de novo metabolic pathway design. However, while many computational frameworks have been proposed for retrobiosynthesis, few successful examples of…

Transfer learning with models pretrained on ImageNet has become a standard practice in computer vision. Transfer learning refers to fine-tuning pretrained weights of a neural network on a downstream task, typically unrelated to ImageNet.…

We propose a supervised machine learning approach for boosting existing signal and image recovery methods and demonstrate its efficacy on example of image reconstruction in computed tomography. Our technique is based on a local nonlinear…

Various template-based and template-free approaches have been proposed for single-step retrosynthesis prediction in recent years. While these approaches demonstrate strong performance from a data-driven metrics standpoint, many model…

We present a scheme to obtain an inexpensive and reliable estimate of the uncertainty associated with the predictions of a machine-learning model of atomic and molecular properties. The scheme is based on resampling, with multiple models…

Classical neural network approximation results take the form: for every function $f$ and every error tolerance $\epsilon > 0$, one constructs a neural network whose architecture and weights depend on $\epsilon$. This paper introduces a…

Typical Magnetic Resonance Imaging (MRI) scan may take 20 to 60 minutes. Reducing MRI scan time is beneficial for both patient experience and cost considerations. Accelerated MRI scan may be achieved by acquiring less amount of k-space data…

We present a deep learning-based method for estimating the neutrino energy of charged-current neutrino-argon interactions. We employ a recurrent neural network (RNN) architecture for neutrino energy estimation in the MicroBooNE experiment,…

Autoregressive language models accumulate errors due to their fixed, irrevocable left-to-right token generation. To address this, we propose a new sampling method called Resample-Previous-Tokens (RPT). RPT mitigates error accumulation by…

Finding a template in a search image is an important task underlying many computer vision applications. Recent approaches perform template matching in a deep feature-space, produced by a convolutional neural network (CNN), which is found to…

Large decoder-only language models (LMs) can be largely improved in terms of perplexity by retrieval (e.g., RETRO), but its impact on text generation quality and downstream task accuracy is unclear. Thus, it is still an open question: shall…

Reliably predicting the products of chemical reactions presents a fundamental challenge in synthetic chemistry. Existing machine learning approaches typically produce a reaction product by sequentially forming its subparts or intermediate…

Protein inverse folding aims to design an amino acid sequence that will fold into a given backbone structure, serving as a central task in protein design. Two main paradigms have been widely explored. Template-based methods exploit…

While interests in tabular deep learning has significantly grown, conventional tree-based models still outperform deep learning methods. To narrow this performance gap, we explore the innovative retrieval mechanism, a methodology that…

Predicting click-through rates (CTR) is a fundamental task for Web applications, where a key issue is to devise effective models for feature interactions. Current methodologies predominantly concentrate on modeling feature interactions…

The size of a website's active user base directly affects its value. Thus, it is important to monitor and influence a user's likelihood to return to a site. Essential to this is predicting when a user will return. Current state of the art…

We reproduce the central claims of Test-Time Training on Nearest Neighbors for Large Language Models (Hardt and Sun, 2024), which proposes adapting a language model at inference time by fine-tuning on retrieved nearest-neighbor sequences.…

Kernel Density Estimation (KDE) is a nonparametric method for estimating the shape of a density function, given a set of samples from the distribution. Recently, locality-sensitive hashing, originally proposed as a tool for nearest neighbor…

In the wake of the explosive growth in smartphones and cyberphysical systems, there has been an accelerating shift in how data is generated away from centralised data towards on-device generated data. In response, machine learning…