Flux Matching generalizes score-based generative modeling by using a weaker objective that admits infinitely many non-conservative vector fields with the data as stationary distribution, enabling new design choices beyond traditional score matching.
hub Canonical reference
Geodiff: A geo- metric diffusion model for molecular conformation generation
Canonical reference. 100% of citing Pith papers cite this work as background.
19
Pith papers citing it
Background
100% of classified citations
hub tools
citation-role summary
background 6
citation-polarity summary
roles
background 6polarities
background 6representative citing papers
Formalizes video world models as group actions on states and uses latent regularization with synthesized supervision to enforce consistency, introducing GAC and GAR metrics that improve structural correctness in SOTA models.
MM-SOLD is a training-free particle sampler whose large-particle limit converges to a moment-matched Gibbs distribution obtained by exponentially tilting a score-smoothed target.
h-MINT improves ligand-protein binding affinity prediction by 2-4% and virtual screening metrics by 1-3% via overlapping fragment tokenization and hierarchical modeling.
Large language models exhibit distinct creative patterns in molecule generation, including higher constraint satisfaction when more constraints are added, and this is the first work to reframe molecule generation abilities as creativity.
TDPM is a diffusion-based generative recommender that disentangles user preferences into period and point components to enable time-aware diffusion on semantic indices, reporting up to 29% gains on HR@20 and NDCG@20 over baselines on three datasets.
CrysLDNet combines VAE and latent diffusion pretraining on unlabeled crystals to improve graph encoder performance on property prediction by about 4-5% on JARVIS and MP datasets.
DiffATS trains diffusion models directly on aligned Tucker tensor primitives that are proven to be homeomorphisms, delivering efficient unconditional and conditional generation across images, videos, and PDE data with high compression.
EDMolGPT generates molecules from low-resolution electron density for de novo structure-based drug design, claiming better performance than pocket-based methods on 101 targets.
LENSEs improves representation-conditioned molecule generation by jointly training a multi-level representation head, perceptual loss, and REPA alignment on pretrained encoders, yielding 97.28% validity and 98.51% stability on GEOM-DRUG.
FlashMol produces chemically valid 3D molecules in 4 steps via distribution matching distillation with respaced timesteps and Jensen-Shannon regularization, matching or exceeding 1000-step teacher performance on QM9 and GEOM-DRUG.
SymDrift makes drifting models produce symmetry-invariant samples in one step via symmetrized coordinate drifts or G-invariant embeddings, outperforming prior one-shot baselines on molecular benchmarks and cutting compute by up to 40x.
A new interests burn-down diffusion process models decaying user interests for personalized collaborative filtering and outperforms prior generative methods in the StageCF implementation.
PerFlow decouples observation conditioning from physics enforcement in rectified flows using constraint-preserving projections and invariance guarantees for fast, physics-consistent reconstruction of spatiotemporal dynamics.
LEGO-MOF maps MOF linkers to an equivariant latent space for continuous editing and uses test-time optimization to achieve a 147.5% average boost in pure CO2 uptake while preserving structural validity.
MolDA is a multimodal molecular model that uses a discrete large language diffusion backbone plus a hybrid graph encoder to achieve better global coherence and validity than autoregressive approaches.
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.
DPM-Solver++ enables high-quality guided sampling of diffusion models in 15-20 steps via data-prediction ODE solving and multistep stabilization.
Reusing source latent spaces in diffusion models under distribution shift produces target score error set by principal-angle misalignment and diffusion-time-amplified ambient noise.
citing papers explorer
-
World Models as Group Actions
Formalizes video world models as group actions on states and uses latent regularization with synthesized supervision to enforce consistency, introducing GAC and GAR metrics that improve structural correctness in SOTA models.