Breaking the Bottlenecks: Scalable Diffusion Models for 3D Molecular Generation

• URL: http://arxiv.org/abs/2601.08963v1
• Date: Tue, 13 Jan 2026 20:09:44 GMT
• Title: Breaking the Bottlenecks: Scalable Diffusion Models for 3D Molecular Generation
• Authors: Adrita Das, Peiran Jiang, Dantong Zhu, Barnabas Poczos, Jose Lugo-Martinez,
• Abstract summary: Diffusion models have emerged as a powerful class of generative models for molecular design.<n>Their use remains constrained by long sampling trajectories, variance in the reverse process, and limited structural awareness in denoising dynamics.<n>The Directly Denoising Diffusion Model mitigates these inefficiencies by replacing reverse MCMC updates with deterministic denoising step.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion models have emerged as a powerful class of generative models for molecular design, capable of capturing complex structural distributions and achieving high fidelity in 3D molecule generation. However, their widespread use remains constrained by long sampling trajectories, stochastic variance in the reverse process, and limited structural awareness in denoising dynamics. The Directly Denoising Diffusion Model (DDDM) mitigates these inefficiencies by replacing stochastic reverse MCMC updates with deterministic denoising step, substantially reducing inference time. Yet, the theoretical underpinnings of such deterministic updates have remained opaque. In this work, we provide a principled reinterpretation of DDDM through the lens of the Reverse Transition Kernel (RTK) framework by Huang et al. 2024, unifying deterministic and stochastic diffusion under a shared probabilistic formalism. By expressing the DDDM reverse process as an approximate kernel operator, we show that the direct denoising process implicitly optimizes a structured transport map between noisy and clean samples. This perspective elucidates why deterministic denoising achieves efficient inference. Beyond theoretical clarity, this reframing resolves several long-standing bottlenecks in molecular diffusion. The RTK view ensures numerical stability by enforcing well-conditioned reverse kernels, improves sample consistency by eliminating stochastic variance, and enables scalable and symmetry-preserving denoisers that respect SE(3) equivariance. Empirically, we demonstrate that RTK-guided deterministic denoising achieves faster convergence and higher structural fidelity than stochastic diffusion models, while preserving chemical validity across GEOM-DRUGS dataset. Code, models, and datasets are publicly available in our project repository.

Related papers

• Neural Diffusion Intensity Models for Point Process Data [4.1419700571838405]
  We introduce a variational framework for Cox processes driven by neural SDEs.<n>We show that conditioning on point process observations preserves the diffusion structure of the latent intensity with an explicit drift correction.
  arXiv  Detail & Related papers  (2026-02-27T15:21:06Z)
• Unrolled Networks are Conditional Probability Flows in MRI Reconstruction [13.185194525641478]
  We introduce flow ODEs to MRI reconstruction by theoretically proving that unrolled networks are discrete implementations of conditional probability flow ODEs.<n>This connection provides explicit formulations for parameters and clarifies how intermediate states should evolve.<n>We propose Flow-Aligned Training (FLAT), which derives unrolled parameters from the ODE discretization and aligns intermediate reconstructions with the ideal ODE trajectory to improve stability and convergence.
  arXiv  Detail & Related papers  (2025-12-02T18:48:10Z)
• Diffusion Models are Molecular Dynamics Simulators [0.0]
  We prove that a denoising diffusion sampler equipped with a sequential bias across the batch dimension is exactly an Euler-Maruyama integrator for overdamped Langevin dynamics.<n>Each reverse denoising step, with its associated spring stiffness, can be interpreted as one step of a differential equation with an effective time step set jointly by the noise schedule and that stiffness.<n>The learned score then plays the role of the gradient of a learned energy, yielding a precise correspondence between diffusion sampling and Langevin time evolution.
  arXiv  Detail & Related papers  (2025-11-21T19:48:32Z)
• 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)
• SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation [62.14510717860079]
  We propose a Synergistic Diffusion-Autoregression paradigm that unifies the training efficiency of autoregressive models with the parallel inference capability of diffusion.<n>SDAR performs a lightweight paradigm conversion that transforms a well-trained autoregressive (AR) model into a blockwise diffusion model through brief, data-efficient adaptation.<n>Building on this insight, SDAR achieves efficient AR-to-diffusion conversion with minimal cost, preserving AR-level performance while enabling parallel generation.
  arXiv  Detail & Related papers  (2025-10-07T17:29:28Z)
• Continuously Augmented Discrete Diffusion model for Categorical Generative Modeling [87.34677262370924]
  Standard discrete diffusion models treat all unobserved states identically by mapping them to an absorbing [MASK] token.<n>This creates an 'information void' where semantic information that could be inferred from unmasked tokens is lost between denoising steps.<n>We introduce Continuously Augmented Discrete Diffusion, a framework that augments the discrete state space with a paired diffusion in a continuous latent space.
  arXiv  Detail & Related papers  (2025-10-01T18:00:56Z)
• Interleaved Gibbs Diffusion: Generating Discrete-Continuous Data with Implicit Constraints [30.624303845550575]
  Interleaved Gibbs Diffusion (IGD) is a novel generative modeling framework for discrete-continuous data.<n>IGD generalizes discrete time Gibbs sampling type Markov chain for the case of discrete-continuous generation.<n>It achieves state-of-the-art results without relying on domain-specific inductive biases.
  arXiv  Detail & Related papers  (2025-02-19T05:51:24Z)
• Soft Mixture Denoising: Beyond the Expressive Bottleneck of Diffusion Models [76.46246743508651]
  We show that current diffusion models actually have an expressive bottleneck in backward denoising. We introduce soft mixture denoising (SMD), an expressive and efficient model for backward denoising.
  arXiv  Detail & Related papers  (2023-09-25T12:03:32Z)
• Fast Diffusion Model [122.36693015093041]
  Diffusion models (DMs) have been adopted across diverse fields with their abilities in capturing intricate data distributions. In this paper, we propose a Fast Diffusion Model (FDM) to significantly speed up DMs from a DM optimization perspective.
  arXiv  Detail & Related papers  (2023-06-12T09:38:04Z)
• A Geometric Perspective on Diffusion Models [57.27857591493788]
  We inspect the ODE-based sampling of a popular variance-exploding SDE. We establish a theoretical relationship between the optimal ODE-based sampling and the classic mean-shift (mode-seeking) algorithm.
  arXiv  Detail & Related papers  (2023-05-31T15:33:16Z)
• Modiff: Action-Conditioned 3D Motion Generation with Denoising Diffusion Probabilistic Models [58.357180353368896]
  We propose a conditional paradigm that benefits from the denoising diffusion probabilistic model (DDPM) to tackle the problem of realistic and diverse action-conditioned 3D skeleton-based motion generation. We are a pioneering attempt that uses DDPM to synthesize a variable number of motion sequences conditioned on a categorical action.
  arXiv  Detail & Related papers  (2023-01-10T13:15:42Z)

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.