Pith. sign in

REVIEW 3 cited by

Unifying Generative Models with GFlowNets and Beyond

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 2209.02606 v2 pith:ZZWIW6ZQ submitted 2022-09-06 cs.LG cs.AIstat.ML

classification cs.LGcs.AIstat.ML
keywords generativeunifyinginferencemodelsprovidesalgorithmsbeyonddeep
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

There are many frameworks for deep generative modeling, each often presented with their own specific training algorithms and inference methods. Here, we demonstrate the connections between existing deep generative models and the recently introduced GFlowNet framework, a probabilistic inference machine which treats sampling as a decision-making process. This analysis sheds light on their overlapping traits and provides a unifying viewpoint through the lens of learning with Markovian trajectories. Our framework provides a means for unifying training and inference algorithms, and provides a route to shine a unifying light over many generative models. Beyond this, we provide a practical and experimentally verified recipe for improving generative modeling with insights from the GFlowNet perspective.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. A Distributional Framework for Generative Modeling of Molecular Crystals

    cond-mat.mtrl-sci 2026-07 conditional novelty 7.0 of 10

    MXtalGFlow combines a canonical crystal parameterization with energy-based GFlowNet training to sample thermodynamic distributions of molecular crystals, recovering known polymorphs and predicting new competitive pack...

  2. Nabla-R2D3: Effective and Efficient 3D Diffusion Alignment with 2D Rewards

    cs.GR 2025-06 conditional novelty 6.0 of 10

    Nabla-R2D3 aligns 3D-native diffusion models with human preferences by backpropagating multi-view 2D reward gradients through the denoising process, improving reward without destroying the pretrained 3D prior.

  3. Adaptive Destruction Processes for Diffusion Samplers

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Learnable destruction processes with decoupled variances improve few-step discrete-time diffusion samplers on benchmarks and in GAN latent space.

Pith tools