Related papers: EvoFlows: Evolutionary Edit-Based Flow-Matching fo…

Proteins are complex biomolecules that perform a variety of crucial functions within living organisms. Designing and generating novel proteins can pave the way for many future synthetic biology applications, including drug discovery.…

Molecular structure generation is a fundamental problem that involves determining the 3D positions of molecules' constituents. It has crucial biological applications, such as molecular docking, protein folding, and molecular design. Recent…

Flow Matching has limited ability in achieving one-step generation due to its reliance on learned curved trajectories. Previous studies have attempted to address this limitation by either modifying the coupling distribution to prevent…

Computational models starting from large ensembles of evolutionarily related protein sequences capture a representation of protein families and learn constraints associated to protein structure and function. They thus open the possibility…

The transition from static Large Language Models (LLMs) to self-improving agents is hindered by the lack of structured reasoning in traditional evolutionary approaches. Existing methods often struggle with premature convergence and…

Designing protein sequences that fold into a target 3D structure, known as protein inverse folding, is a fundamental challenge in protein engineering. While recent deep learning methods have achieved impressive performance by recovering…

Flow-matching models have enabled high-quality text-to-speech synthesis, but their iterative sampling process during inference incurs substantial computational cost. Although distillation is widely used to reduce the number of inference…

Natural protein sequences somehow encode the structural forms that these molecules adopt. Recent developments in structure-prediction are agnostic to the mechanisms by which proteins fold and represent them as static objects. However, the…

Natural protein sequences contain a record of their history. A common constraint in a given protein family is the ability to fold to specific structures, and it has been shown possible to infer the main native ensemble by analyzing…

Sparse Mixture-of-Experts (MoE) models can outperform dense large language models at similar computation by activating only a small set of experts per token. However, stacking many expert modules introduces substantial parameter memory,…

We introduce a data-driven epistatic model of protein evolution, capable of generating evolutionary trajectories spanning very different time scales reaching from individual mutations to diverged homologs. Our in silico evolution…

Automated machine learning (AutoML) systems propose an end-to-end solution to a given machine learning problem, creating either fixed or flexible pipelines. Fixed pipelines are task independent constructs: their general composition remains…

Recent developments in next generation sequencing technology have led to the creation of extensive, open-source protein databases consisting of hundreds of millions of sequences. To render these sequences applicable in biomedical…

Protein language models often take into consideration the alignment between a protein sequence and its textual description. However, they do not take structural information into consideration. Traditional methods treat sequence and…

Most existing sequence generation models produce outputs in one pass, usually left-to-right. However, this is in contrast with a more natural approach that humans use in generating content; iterative refinement and editing. Recent work has…

Accurate protein structure prediction from amino-acid sequences is critical to better understanding the protein function. Recent advances in this area largely benefit from more precise inter-residue distance and orientation predictions,…

Proteins adopt multiple structural conformations to perform their diverse biological functions, and understanding these conformations is crucial for advancing drug discovery. Traditional physics-based simulation methods often struggle with…

Data augmentation has long been a cornerstone for reducing overfitting in vision models, with methods like AutoAugment automating the design of task-specific augmentations. Recent advances in generative models, such as conditional diffusion…

Time series classification is a fundamental machine learning task with broad real-world applications. Although many deep learning methods have proven effective in learning time-series data for classification, they were originally developed…

We present OneFlow, the first non-autoregressive multimodal model that enables variable-length and concurrent mixed-modal generation. Unlike autoregressive models that enforce rigid causal ordering between text and image generation, OneFlow…