Related papers: Predictive Feature Caching for Training-free Accel…

Machine-learning force fields can deliver accurate molecular dynamics (MD) at high computational cost. For SO(3)-equivariant models such as MACE, there is little systematic evidence on whether reduced-precision arithmetic and GPU-optimized…

Graphics Processing Units (GPUs) were once used solely for graphical computation tasks but with the increase in the use of machine learning applications, the use of GPUs to perform general-purpose computing has increased in the last few…

Stochastic gradient descent algorithms for training linear and kernel predictors are gaining more and more importance, thanks to their scalability. While various methods have been proposed to speed up their convergence, the model selection…

Generating molecular graphs with desired chemical properties driven by deep graph generative models provides a very promising way to accelerate drug discovery process. Such graph generative models usually consist of two steps: learning…

Recent advances in geometric deep learning and generative modeling have enabled the design of novel proteins with a wide range of desired properties. However, current state-of-the-art approaches are typically restricted to generating…

Thanks to the recent development of deep generative models, it is becoming possible to generate high-quality images with both fidelity and diversity. However, the training of such generative models requires a large dataset. To reduce the…

A method is presented for accelerating inference in transformer language models by exploiting the low effective rank of the token activation manifold at each layer. The method decomposes each activation vector into a subspace component and…

Flow matching has recently emerged as a promising alternative to diffusion-based generative models, offering faster sampling and simpler training by learning continuous flows governed by ordinary differential equations. Despite growing…

While generative modeling has achieved remarkable success on tasks like natural language-conditioned image generation, enabling model adaptation from example data points remains a relatively underexplored and challenging problem. To this…

Compressing neural networks without retraining is vital for deployment at scale. We study calibration-free compression through the lens of projection geometry: structured pruning is an axis-aligned projection, whereas model folding performs…

This paper introduces ECHO-LLaMA, an efficient LLaMA architecture designed to improve both the training speed and inference throughput of LLaMA architectures while maintaining its learning capacity. ECHO-LLaMA transforms LLaMA models into…

We propose a framework using normalizing-flow based models, SELF-Referencing Embedded Strings, and multi-objective optimization that efficiently generates small molecules. With an initial training set of only 100 small molecules, FastFlows…

Generative Adversarial Networks (GANs) produce high-quality images but are challenging to train. They need careful regularization, vast amounts of compute, and expensive hyper-parameter sweeps. We make significant headway on these issues by…

The evolution of 3D generative modeling has been notably propelled by the adoption of 2D diffusion models. Despite this progress, the cumbersome optimization process per se presents a critical hurdle to efficiency. In this paper, we…

Approximate computing offers promising energy efficiency benefits for error-tolerant applications, but discovering optimal approximations requires extensive design space exploration (DSE). Predicting the accuracy of circuits composed of…

Although machine learning has been successfully used to propose novel molecules that satisfy desired properties, it is still challenging to explore a large chemical space efficiently. In this paper, we present a conditional molecular design…

Gene finding is the task of identifying the locations of coding sequences within the vast amount of genetic code contained in the genome. With an ever increasing quantity of raw genome sequences, gene finding is an important avenue towards…

Pretraining molecular representations is crucial for drug and material discovery. Recent methods focus on learning representations from geometric structures, effectively capturing 3D position information. Yet, they overlook the rich…

Learning from the data stored in a database is an important function increasingly available in relational engines. Methods using lower precision input data are of special interest given their overall higher efficiency but, in databases,…

Backfilling is the process of re-extracting all gallery embeddings from upgraded models in image retrieval systems. It inevitably requires a prohibitively large amount of computational cost and even entails the downtime of the service.…