mlsanityData to 7 Oct 2026

Flash Invariant Point Attention

arXiv 2505.11580 ↗First posted 16 May 2025cs.LG cs.AI q-bio.BMcited by 1

Not on the map. Why?

Abstract (arXiv)

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 limits the input sequence length. We introduce FlashIPA, a factorized reformulation of IPA that leverages hardware-efficient FlashAttention to achieve linear scaling in GPU memory and wall-clock time with sequence length. FlashIPA matches or exceeds standard IPA performance while substantially reducing computational costs. FlashIPA extends training to previously unattainable lengths, and we demonstrate this by re-training generative models without length restrictions and generating structures of thousands of residues. FlashIPA is available at https://github.com/flagshippioneering/flash_ipa.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 16 of its 32 references that are in the map. First posted on arXiv 16 May 2025.

Builds on

16 of 32 references.

References · 16

  1. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  2. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  3. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,551
  4. 2024Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Designcited by 294
  5. 2023SE(3) diffusion model with application to protein backbone generationcited by 214
  6. 2023SE(3)-Stochastic Flow Matching for Protein Backbone Generationcited by 147
  7. 2023Generating Novel, Designable, and Diverse Protein Structures by Equivariantly Diffusing Oriented Residue Cloudscited by 53
  8. 2024Improved motif-scaffolding with SE(3) flow matchingcited by 43
  9. 2024Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Backbone Generationcited by 36
  10. 2023gRNAde: Geometric Deep Learning for 3D RNA inverse designcited by 18
  11. 2022Accurate RNA 3D structure prediction using a language model-based deep learning approachcited by 16
  12. 2024Generating Highly Designable Proteins with Geometric Algebra Flow Matchingcited by 7
4 more
  1. 2024P2DFlow: A Protein Ensemble Generative Model with SE(3) Flow Matchingcited by 6
  2. 2024De novo antibody design with SE(3) diffusioncited by 5
  3. 2024RNA-FrameFlow: Flow Matching for de novo 3D RNA Backbone Designcited by 5
  4. 2024Floating Anchor Diffusion Model for Multi-motif Scaffoldingcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Design-CP: Context Parallelism for Design of Protein Nanoparticlescited by 0