REVIEW 10 cited by
SE(3)-Stochastic Flow Matching for Protein Backbone Generation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
The computational design of novel protein structures has the potential to impact numerous scientific disciplines greatly. Toward this goal, we introduce FoldFlow, a series of novel generative models of increasing modeling power based on the flow-matching paradigm over $3\mathrm{D}$ rigid motions -- i.e. the group $\text{SE}(3)$ -- enabling accurate modeling of protein backbones. We first introduce FoldFlow-Base, a simulation-free approach to learning deterministic continuous-time dynamics and matching invariant target distributions on $\text{SE}(3)$. We next accelerate training by incorporating Riemannian optimal transport to create FoldFlow-OT, leading to the construction of both more simple and stable flows. Finally, we design FoldFlow-SFM, coupling both Riemannian OT and simulation-free training to learn stochastic continuous-time dynamics over $\text{SE}(3)$. Our family of FoldFlow, generative models offers several key advantages over previous approaches to the generative modeling of proteins: they are more stable and faster to train than diffusion-based approaches, and our models enjoy the ability to map any invariant source distribution to any invariant target distribution over $\text{SE}(3)$. Empirically, we validate FoldFlow, on protein backbone generation of up to $300$ amino acids leading to high-quality designable, diverse, and novel samples.
Forward citations
Cited by 10 Pith papers
-
Spectral Diffusion for Protein Dynamics
Diffusion over DCT spectral volumes of Cα displacements yields fast, temperature-conditioned protein trajectories with RMSF Pearson r of 0.844 on held-out mdCATH.
-
GraspMeanFlow: SE(3)-Equivariant MeanFlow for Few-Step 6-DoF Grasp Generation
An SE(3)-equivariant average-velocity flow generates 6-DoF grasps in one or a few function evaluations, matching iterative flow baselines on ACRONYM.
-
Exploring the Alignment of Generation and Understanding in Protein Structure Modeling
Aligning a protein diffusion generator's internal representations to a pretrained structure encoder (ProteinMPNN) raises the MotifBench motif-scaffolding score from 39.2 to 47.1 (~20% relative) over the Protpardelle-1...
-
Design-CP: Context Parallelism for Design of Protein Nanoparticles
Context-parallel inference for RFdiffusion 3 enables end-to-end all-atom design of large symmetric protein nanoparticles on multi-GPU hardware without retraining.
-
Native Extrapolation Awareness in Flow-Based Conditional Generation
A contrastive flow-matching objective makes off-manifold conditions produce curved trajectories, so path curvature (the DOT score) separates invalid from valid inputs.
-
Platonic Transformers: A Solid Choice For Equivariance
Platonic Transformers achieve exact equivariance to translations plus discrete Platonic-solid rotations by lifting features into multiple reference frames and sharing one RoPE attention across them, with a linear-time...
-
Train-Once Plan-Anywhere Kinodynamic Motion Planning via Diffusion Trees
A flow-matching policy guides RRT tree expansion, preserving completeness while raising success rates on out-of-distribution kinodynamic planning tasks.
-
FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocities
A 1.5B unified multimodal model trained with discrete flow matching and metric-induced probability paths matches autoregressive baselines of similar size on generation and understanding benchmarks.
-
Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders
Training flow matching along sphere geodesics with a curvature-aware loss weight lets standard DiT-B converge on DINOv2 features (FID 3.37 with guidance), contradicting the need for width scaling.
-
VARD: Efficient and Dense Fine-Tuning for Diffusion Models with Value-based RL
VARD fine-tunes diffusion models by backpropagating through a learned value function that assigns dense, differentiable reward estimates to every intermediate denoising step, with KL regularization keeping the model n...
Discussion (0). Sign in to comment.