Few-step Cofolding with All-Atom Flow Maps

• URL: http://arxiv.org/abs/2606.08375v1
• Date: Sun, 07 Jun 2026 00:06:15 GMT
• Title: Few-step Cofolding with All-Atom Flow Maps
• Abstract summary: Denoiser Cofolding All-Atom Flowmap (DeCAF)<n>We build DeCAF on a denoiser-based formulation of flow maps with endpoint losses that naturally support SE(3) rigid alignment.<n>We introduce a purpose-built inference-time framework that improves sampling through reward-guided search.
• Score: 13.124878986088738
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: All-atom generative modeling of 3D biomolecular complexes has emerged as the dominant paradigm for predicting the structure of proteins and protein-ligand systems. Generating structures at the atomic level of fidelity, however, typically requires expensive iterative diffusion rollouts, making both conventional deployment and inference-time search techniques computationally costly. In this paper, we introduce the Denoiser Cofolding All-Atom Flowmap (DeCAF) framework for distilling state-of-the-art all-atom cofolding models into all-atom flow maps that produce high-quality samples in only a few inference steps. We build DeCAF on a denoiser-based formulation of flow maps with endpoint losses that naturally support SE(3) rigid alignment, which we show is critical for training accurate models. We further derive a simple change of variables that lets DeCAF operate in the σ-space noise schedule of EDM-style architectures, enabling direct distillation from pretrained cofolding diffusion models. Equipped with DeCAF's flowmap lookahead, we introduce a purpose-built inference-time framework that improves sampling through reward-guided search. Empirically, DeCAF-Boltz statistically improves over Boltz-1x in both accuracy (RMSD) and physical validity scores of protein-ligand poses at strict NFE budgets on the challenging Runs N' Poses, while also showing a more optimal Pareto frontier across all inference compute budgets on PoseBusters. Distilling the state-of-the-art Pearl cofolding model, DeCAF-Pearl outperforms diffusion-based cofolding models and matches its teacher on success rate while using 5x fewer NFEs. We release our code at https://github.com/genesistherapeutics/decaf.

Related papers

• APO: Unsupervised Atomic Policy Optimization for 3D Structure Prediction of Atomic Systems [64.56252173115246]
  We propose (Atomic Policy Optimization) a fully unsupervised alignment framework that eliminates the need for ground-truth reference structures.<n>APO adapts group-relative policy optimization to 3D atomic environments, utilizing a novel dual-reward mechanism.<n>Our results suggest that intrinsic physical consistency can serve as a superior guide for alignment compared to noisy, supervised coordinate matching.
  arXiv  Detail & Related papers  (2026-07-30T17:21:58Z)
• From Atoms to Entropy: Optimal Noise Allocation for Diffusion Training in the Convex Regime [52.459513910242485]
  We develop a general statistical framework for studying optimal noise-level allocation in diffusion training.<n>We show that the optimized training schedule admits an atomic minimizer, concentrated on finitely many noise levels.<n>We then evaluate the entropic schedule in larger-scale experiments, where full schedule optimization is currently intractable.
  arXiv  Detail & Related papers  (2026-07-10T20:59:06Z)
• Fine-Tuning Diffusion Models for Molecular Generation via Reinforcement Learning and Fast Sampling [22.66917124518062]
  Existing generative approaches often rely on costly post-hoc processing during Sampling or require carefully curated datasets during training.<n>We propose FTDiff, a reinforcement learning fine-tuning framework tailored for diffusion-based molecular generation under structural constraints.<n>We show that FTDiff consistently outperforms prior methods, without requiring expensive post-hoc optimization or intricate data engineering.
  arXiv  Detail & Related papers  (2026-05-31T13:11:48Z)
• DCFold: Efficient Protein Structure Generation with Single Forward Pass [21.891664351023223]
  We propose DCFold, a single-step generative model that attains AlphaFold3-level accuracy.<n>Our Dual Consistency training framework, which incorporates a novel Temporal Geodesic Matching (TGM) scheduler, enables DCFold to achieve a 15x acceleration in inference.
  arXiv  Detail & Related papers  (2026-05-18T06:05:56Z)
• Diff-ES: Stage-wise Structural Diffusion Pruning via Evolutionary Search [40.67449277026597]
  We introduce textbfDiff-ES, a stage-wise structural textbfDiff-usion pruning framework via textbfEvolutionary textbfSearch.<n>Our framework naturally integrates with existing structured pruning methods for diffusion models including depth and width pruning.<n>Experiments on DiT and SDXL demonstrate that Diff-ES consistently achieves wall-clock speedups while incurring minimal degradation in generation quality.
  arXiv  Detail & Related papers  (2026-03-05T12:18:40Z)
• VEDA: 3D Molecular Generation via Variance-Exploding Diffusion with Annealing [4.288647933894182]
  VEDA is a framework that combines variance-exploding diffusion with annealing to generate 3D structures.<n>On the QM9 and GEOM-DRUGS datasets, VEDA matches the sampling efficiency of flow-based models.<n>VEDA's generated structures are remarkably stable, as measured by their relaxation energy.
  arXiv  Detail & Related papers  (2025-11-11T05:45:37Z)
• Score Distillation of Flow Matching Models [67.86066177182046]
  We extend Score identity Distillation (SiD) to pretrained text-to-image flow-matching models.<n>SiD works out of the box across these models, in both data-free and data-aided settings.<n>This provides the first systematic evidence that score distillation applies broadly to text-to-image flow matching models.
  arXiv  Detail & Related papers  (2025-09-29T17:45:48Z)
• Acc3D: Accelerating Single Image to 3D Diffusion Models via Edge Consistency Guided Score Distillation [49.202383675543466]
  We present Acc3D to tackle the challenge of accelerating the diffusion process to generate 3D models from single images.<n>To derive high-quality reconstructions through few-step inferences, we emphasize the critical issue of regularizing the learning of score function in states of random noise.
  arXiv  Detail & Related papers  (2025-03-20T09:18:10Z)
• Memory-Efficient Fine-Tuning for Quantized Diffusion Model [12.875837358532422]
  We introduce TuneQDM, a memory-efficient fine-tuning method for quantized diffusion models. Our method consistently outperforms the baseline in both single-/multi-subject generations.
  arXiv  Detail & Related papers  (2024-01-09T03:42:08Z)
• Adaptive Training Meets Progressive Scaling: Elevating Efficiency in Diffusion Models [52.1809084559048]
  We propose a novel two-stage divide-and-conquer training strategy termed TDC Training.<n>It groups timesteps based on task similarity and difficulty, assigning highly customized denoising models to each group, thereby enhancing the performance of diffusion models.<n>While two-stage training avoids the need to train each model separately, the total training cost is even lower than training a single unified denoising model.
  arXiv  Detail & Related papers  (2023-12-20T03:32:58Z)
• SE(3)-Stochastic Flow Matching for Protein Backbone Generation [54.951832422425454]
  We introduce FoldFlow, a series of novel generative models of increasing modeling power based on the flow-matching paradigm over $3mathrmD$ rigid motions. Our family of FoldFlowgenerative models offers several advantages over previous approaches to the generative modeling of proteins.
  arXiv  Detail & Related papers  (2023-10-03T19:24:24Z)
• Protein Design with Guided Discrete Diffusion [67.06148688398677]
  A popular approach to protein design is to combine a generative model with a discriminative model for conditional sampling. We propose diffusioN Optimized Sampling (NOS), a guidance method for discrete diffusion models. NOS makes it possible to perform design directly in sequence space, circumventing significant limitations of structure-based methods.
  arXiv  Detail & Related papers  (2023-05-31T16:31:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.