activity
20242026
collaborators

6 papers

cs.LG2026

Native Multi-Dimensional Subquadratic Operators via Input Dependent Long Convolutions

David R. Wessels, Farhad Ramezanghorbani, David W. Romero +9

Subquadratic alternatives to attention require compromises when applied to multi-dimensional data: standard convolutions lack global receptive fields and input dependency, while re…

cs.LG2026

PairSAE: Mechanistic Interpretability from Pair Representations in Protein Co-Folding

Giosue Migliorini, Aristofanis Rontogiannis, Grigori Guitchounts +3

Foundation models for structural biology have achieved remarkable performance in predicting biomolecular structure and show promise for the design of proteins and small molecules.…

cs.CL2026

Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

NVIDIA, :, Aaron Blakeman +571

We introduce Nemotron 3 Ultra, a 550 billion total and 55 billion active parameter Mixture-of-Experts Hybrid Mamba-Attention language model. We pre-trained Nemotron 3 Ultra on 20 t…

cs.LG2025

Flash Invariant Point Attention

Andrew Liu, Axel Elaldi, Nicholas T Franklin +4

Invariant Point Attention (IPA) is a key algorithm for geometry-aware modeling in structural biology, central to many protein and RNA models. However, its quadratic complexity limi…

cs.LG2025

Bio2Token: All-atom tokenization of any biomolecular structure with Mamba

Andrew Liu, Axel Elaldi, Nathan Russell +1

Efficient encoding and representation of large 3D molecular structures with high fidelity is critical for biomolecular design applications. Despite this, many representation learni…

cs.LG2024

Improving Inverse Folding for Peptide Design with Diversity-regularized Direct Preference Optimization

Ryan Park, Darren J. Hsu, C. Brian Roland +5

Inverse folding models play an important role in structure-based design by predicting amino acid sequences that fold into desired reference structures. Models like ProteinMPNN, a m…