Related papers: PaMM: Periodic Motif Memory for Atomistic Models w…

Graph Neural Networks (GNNs) have shown remarkable success in molecular tasks, yet their interpretability remains challenging. Traditional model-level explanation methods like XGNN and GNNInterpreter often fail to identify valid…

Inspired by the masked language modeling (MLM) in natural language processing tasks, the masked image modeling (MIM) has been recognized as a strong self-supervised pre-training method in computer vision. However, the high random mask ratio…

A fundamental objective of materials modeling is identifying atomic structures that align with experimental observables. Conventional approaches for disordered materials involve sampling from thermodynamic ensembles and hoping for an…

Reward models (RMs) are central to aligning large language models (LLMs) with human preferences, powering RLHF and advanced decoding strategies. While most prior work focuses on single-step generation, real-world applications increasingly…

With the emergence of Foundational Machine Learning Interatomic Potential (FMLIP) models trained on extensive datasets, transferring data between different ML architectures has become increasingly important. In this work, we examine the…

Protein-protein interactions (PPIs) are fundamental to numerous cellular processes, and their characterization is vital for understanding disease mechanisms and guiding drug discovery. While protein language models (PLMs) have demonstrated…

Evidence Accumulation Models (EAMs) have been widely used to investigate speeded decision-making processes, but they have largely neglected the role of predictive processes emphasized by theories of the predictive brain. In this paper, we…

Improving the generalization ability of Vision-Language Pre-trained Models (VLMs) under test-time data distribution shifts remains a critical challenge. The existing Test-Time Adaptation (TTA) methods fall short in fully leveraging the…

The Mixture of Experts (MoE) framework has become a popular architecture for large language models due to its superior performance over dense models. However, training MoEs from scratch in a large-scale regime is prohibitively expensive.…

Universal machine learned interatomic potentials (uMLIPs) embody a growing area of interest due to their transferability across the periodic table, displaying an error of about 0.6 kcal/mol against the Matbench Discovery test set. However,…

We present an automated approach for identifying and annotating motifs and domains in protein sequences, using pretrained Protein Language Models (PLMs) and Concept Activation Vectors (CAVs), adapted from interpretability research in…

SO(3) equivariant graph neural networks have become the dominant paradigm for atomistic foundation models, achieving high accuracy and data efficiency by building rotational symmetry directly into the architecture. Yet the computational…

Most machine learning models for molecular property prediction rely on a single molecular representation (either a sequence, a graph, or a 3D structure) and treat molecular geometry as static. We present MolFM-Lite, a multi-modal model that…

We present Advancing Front Mapping (AFM), a provably robust algorithm for the computation of surface mappings to simple base domains. Given an input mesh and a convex or star-shaped target domain, AFM installs a (possibly refined) version…

Masked image modeling (MIM) has attracted much research attention due to its promising potential for learning scalable visual representations. In typical approaches, models usually focus on predicting specific contents of masked patches,…

A general, variational approach to derive low-order reduced systems is presented. The approach is based on the concept of optimal parameterizing manifold (OPM) that substitutes the more classical notions of invariant or slow manifold when…

Foundation models are reshaping EEG analysis, yet an important problem of EEG tokenization remains a challenge. This paper presents TFM-Tokenizer, a novel tokenization framework that learns a vocabulary of time-frequency motifs from…

Elastic network models (ENMs) are valuable and efficient tools for characterizing the collective internal dynamics of proteins based on the knowledge of their native structures. The increasing evidence that the biological functionality of…

We study learning of recurrent neural networks that produce temporal sequences consisting of the concatenation of re-usable "motifs". In the context of neuroscience or robotics, these motifs would be the motor primitives from which complex…

Large Language Models (LLMs) perform well on reasoning benchmarks but often fail when inputs alter slightly, raising concerns about the extent to which their success relies on memorization. This issue is especially acute in Chain-of-Thought…