Related papers: Low-N Protein Activity Optimization with FolDE
We propose CLAD -- a Constrained Latent Action Diffusion model for vision-language procedure planning in instructional videos. Procedure planning is the challenging task of predicting intermediate actions given a visual observation of a…
Undetected overfitting can occur when there are significant redundancies between training and validation data. We describe AVE, a new measure of training-validation redundancy for ligand-based classification problems that accounts for the…
As the maximum likelihood method is the most commonly used method for parameters estimation being unbiased, consistent, efficient, and asymptotically normal, MLE is used to fit the new distribution (MBUW). But in small to moderate sample…
Emerging technologies such as Reconfigurable Intelligent Surfaces (RIS) make it possible to optimize some parameters of wireless channels. Conventional approaches require relating the channel and its programmable parameters via a simple…
An AI-powered quality engineering platform uses artificial intelligence to boost software quality assessments through automated defect prediction and optimized performance alongside improved feature extraction. Existing models result in…
Investigating conformational landscapes of proteins is a crucial way to understand their biological functions and properties. AlphaFlow stands out as a sequence-conditioned generative model that introduces flexibility into structure…
Recent advances in language models have enabled framing molecule generation as sequence modeling. However, existing approaches often rely on single-objective reinforcement learning, limiting their applicability to real-world drug design,…
MoE-PEFT methods combine Mixture of Experts with parameter-efficient fine-tuning for multi-task adaptation, but require separate adapters per expert causing trainable parameters to scale linearly with expert count and limiting applicability…
We present Unified Latent Dynamics (ULD), a novel reinforcement learning algorithm that unifies the efficiency of model-free methods with the representational strengths of model-based approaches, without incurring planning overhead. By…
Despite considerable progress, ab initio protein structure prediction remains suboptimal. A crowdsourcing approach is the online puzzle video game Foldit, that provided several useful results that matched or even outperformed…
Multimodal optimization requires finding many optima rather than merely keeping a diverse population. Yet most niching-based evolutionary algorithms rely on distances or density estimators without explicitly recovering the underlying…
Differential Evolution (DE) is one of the most successful and powerful evolutionary algorithms for global optimization problem. The most important operator in this algorithm is mutation operator which parents are selected randomly to…
Differential evolution (DE) is an effective population-based metaheuristic algorithm for solving complex optimisation problems. However, the performance of DE is sensitive to the mutation operator. In this paper, we propose a novel DE…
We develop nested automatic differentiation (AD) algorithms for exact inference and learning in integer latent variable models. Recently, Winner, Sujono, and Sheldon showed how to reduce marginalization in a class of integer latent variable…
The performance of Large Language Models (LLMs) on downstream tasks is fundamentally constrained by the capabilities acquired during pre-training. However, traditional benchmarks like MMLU often fail to reflect a base model's plasticity in…
Pool-based Active Learning (AL) has achieved great success in minimizing labeling cost by sequentially selecting informative unlabeled samples from a large unlabeled data pool and querying their labels from oracle/annotators. However,…
Large language models (LLMs) with the Mixture-of-Experts (MoE) architecture achieve high cost-efficiency by selectively activating a subset of the parameters. Despite the inference efficiency of MoE LLMs, the training of extensive experts…
Developing effective representations of protein structures is essential for advancing protein science, particularly for protein generative modeling. Current approaches often grapple with the complexities of the SE(3) manifold, rely on…
The field of protein folding research has been greatly advanced by deep learning methods, with AlphaFold2 (AF2) demonstrating exceptional performance and atomic-level precision. As co-evolution is integral to protein structure prediction,…
Language models of code have demonstrated state-of-the-art performance across various software engineering and source code analysis tasks. However, their demanding computational resource requirements and consequential environmental…