REVIEW 6 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
Signed reviews
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.
Forward citations
Cited by 6 Pith papers
-
Experience-Calibrated Contrastive Decoding for Mitigating Hallucinations in LM-Based Text-to-Speech
Experience-Calibrated Contrastive Decoding, a training-free decoding method that strengthens text alignment signals, reduces speech hallucination errors across four LM-based TTS models and nine languages.
-
A Distributional Framework for Generative Modeling of Molecular Crystals
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...
-
Ergodic Generative Flows
Ergodic Generative Flows use finitely many ergodic diffeomorphisms to give universal, tractable generative flows on tori and spheres, with a reward-free imitation learning loss.
-
Efficient Diversity-Preserving Diffusion Alignment via Gradient-Informed GFlowNets
A gradient-informed GFlowNet objective, residual nabla-DB, finetunes diffusion models to sample according to a reward while preserving diversity and prior knowledge.
-
Nabla-R2D3: Effective and Efficient 3D Diffusion Alignment with 2D Rewards
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.
-
Adaptive Destruction Processes for Diffusion Samplers
Learnable destruction processes with decoupled variances improve few-step discrete-time diffusion samplers on benchmarks and in GAN latent space.
Discussion (0). Continue with ORCID to comment.