Pith. sign in

REVIEW 7 cited by

Swallowing the Bitter Pill: Simplified Scalable Conformer 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

arxiv 2311.17932 v3 pith:P53OZXM4 submitted 2023-11-27 physics.chem-ph cs.LG

classification physics.chem-phcs.LG
keywords modelconformermolecularstructurediffusiondirectlyformulationfunctions
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We present a novel way to predict molecular conformers through a simple formulation that sidesteps many of the heuristics of prior works and achieves state of the art results by using the advantages of scale. By training a diffusion generative model directly on 3D atomic positions without making assumptions about the explicit structure of molecules (e.g. modeling torsional angles) we are able to radically simplify structure learning, and make it trivial to scale up the model sizes. This model, called Molecular Conformer Fields (MCF), works by parameterizing conformer structures as functions that map elements from a molecular graph directly to their 3D location in space. This formulation allows us to boil down the essence of structure prediction to learning a distribution over functions. Experimental results show that scaling up the model capacity leads to large gains in generalization performance without enforcing inductive biases like rotational equivariance. MCF represents an advance in extending diffusion models to handle complex scientific problems in a conceptually simple, scalable and effective manner.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Quotient-Space Diffusion Models

    cs.LG 2026-04 unverdicted novelty 8.0 of 10

    Quotient-space diffusion models generate correct symmetric distributions by removing redundancy on the quotient space, simplifying learning and improving results on small molecules and proteins under SE(3) symmetry.

  2. Mat\'ern Noise for Triangulation-Agnostic Flow Matching on Meshes

    cs.GR 2026-05 unverdicted novelty 7.0 of 10

    Proposes discretized Matérn process noise for triangulation-agnostic flow matching on meshes with PoissonNet denoiser, tested on elastic states and humanoid poses for meshes exceeding one million triangles.

  3. Quotient-Space Diffusion Models

    cs.LG 2026-04 unverdicted novelty 6.0 of 10

    Quotient-space diffusion models handle symmetries by diffusing on the space of equivalent configurations under group actions like SE(3), reducing learning complexity and guaranteeing correct sampling for molecular generation.

  4. Energy-Guided Generative Modeling for Low-Energy Molecular Structure Discovery

    cs.LG 2025-12 unverdicted novelty 6.0 of 10

    EnFlow integrates flow-based conformer generation with energy landscape modeling to enable joint ensemble generation and ground-state identification using only 1-2 ODE steps.

  5. FunPhase: A Periodic Functional Autoencoder for Motion Generation via Phase Manifolds

    cs.CV 2025-12 conditional novelty 6.0 of 10

    FunPhase encodes motion clips as sinusoidal phase functions and decodes them continuously in space and time, enabling reconstruction, generation, super-resolution, and body completion across skeletons.

  6. Feynman-Kac-Flow: Inference Steering of Conditional Flow Matching to an Energy-Tilted Posterior

    cs.LG 2025-09 conditional novelty 6.0 of 10

    Feynman-Kac particle steering, previously diffusion-only, is derived for conditional flow matching and used to generate chirality-correct chemical transition states.

  7. Equivariance and Augmentation for Bayesian Neural Networks

    cs.LG 2026-06 unverdicted novelty 5.0 of 10

    Derives exact equivariance conditions for augmented BNNs under variational inference and proposes orbit expansion symmetrization that outperforms baselines on equivariance and accuracy.

Pith tools