REVIEW 5 cited by
Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matching
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
read the original abstract
We introduce Adjoint Sampling, a highly scalable and efficient algorithm for learning diffusion processes that sample from unnormalized densities, or energy functions. It is the first on-policy approach that allows significantly more gradient updates than the number of energy evaluations and model samples, allowing us to scale to much larger problem settings than previously explored by similar methods. Our framework is theoretically grounded in stochastic optimal control and shares the same theoretical guarantees as Adjoint Matching, being able to train without the need for corrective measures that push samples towards the target distribution. We show how to incorporate key symmetries, as well as periodic boundary conditions, for modeling molecules in both cartesian and torsional coordinates. We demonstrate the effectiveness of our approach through extensive experiments on classical energy functions, and further scale up to neural network-based energy models where we perform amortized conformer generation across many molecular systems. To encourage further research in developing highly scalable sampling methods, we plan to open source these challenging benchmarks, where successful methods can directly impact progress in computational chemistry.
Forward citations
Cited by 5 Pith papers
-
Generative Modeling via Kernelized Stochastic Interpolants
The drift of a stochastic interpolant is estimated by solving a P×P linear system from feature gradients, enabling training-free generation and training-free combination of pretrained generative models.
-
FlowBack-Adjoint: Physics-Aware and Energy-Guided Conditional Flow-Matching for All-Atom Protein Backmapping
FlowBack-Adjoint fine-tunes a flow-matching backmapping model with molecular mechanics energy gradients, reducing clashes and bond errors and producing lower-energy all-atom protein reconstructions.
-
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.
-
Integration Matters: Rollout-Based Training for Constrained Diffusion Models
Rollout-based fine-tuning with a learned adaptive guidance scaling yields near-zero constraint violations while preserving sample fidelity in constrained diffusion models.
-
Towards Adaptive External Communication in Autonomous Vehicles: A Conceptual Design Framework
A three-layer framework (input, processing, output) for adaptive external human-machine interfaces in autonomous vehicles is introduced to systematize design and analysis.
Discussion (0). Sign in to comment.