The Laplace-Fisher Gate Identity supplies the variance-optimal matrix blending coefficients for Tweedie and target-score estimators under an OU diffusion, enabling improved finite-reference score estimation and posterior density surrogates.
Adjoint sampling: Highly scalable diffusion samplers via adjoint matching
10 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
10
Pith papers citing it
1
external citations · external index
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 10roles
background 1polarities
background 1representative citing papers
CDM amortizes SMC inference for reward-tilted discrete diffusion by training a parameterized twist function on contrastive samples with closed-form kernels.
A new adjoint matching framework formulates flow model alignment as optimal control, enabling direct regression training and terminal-trajectory truncation for efficiency gains on models like SiT-XL and FLUX.
CliqueFlowmer combines clique-based model-based optimization with transformer and flow models to generate materials that optimize target properties better than generative baselines.
Presents adjoint matching for scalable max-ent RL training of diffusion policies, enabling simulation-free optimization.
Establishes convergence guarantees for overparameterized 2-layer ReLU networks in flow matching, generalization bounds for the velocity-field objective, and Wasserstein guarantees for generated samples, using multi-task representation learning bounds.
SURGE is an unbiased particle filter that fuses diffusion-model simulations with noisy observations via sequential Monte Carlo reweighting over diffusion trajectories.
URGE performs unbiased inference-time scaling for diffusion models by attaching multiplicative path weights from Girsanov estimation and resampling trajectories, with a proven equivalence to prior particle-wise SMC schemes.
Tempered sequential Monte Carlo samples from a Boltzmann-tilted distribution over controllers to optimize trajectories and policies under differentiable dynamics.
Energy-Weighted Flow Matching reformulates conditional flow matching with importance sampling to enable continuous normalizing flows to model Boltzmann distributions from energy evaluations alone, with iterative and annealed variants showing competitive performance on benchmarks.
citing papers explorer
-
Laplace-Fisher Gate Identities for Optimal Matrix-Gated Blended Score Estimation
The Laplace-Fisher Gate Identity supplies the variance-optimal matrix blending coefficients for Tweedie and target-score estimators under an OU diffusion, enabling improved finite-reference score estimation and posterior density surrogates.
-
Contrastive Distribution Matching for Amortized Sequential Monte Carlo in Discrete Diffusion
CDM amortizes SMC inference for reward-tilted discrete diffusion by training a parameterized twist function on contrastive samples with closed-form kernels.
-
Improved techniques for fine-tuning flow models via adjoint matching: a deterministic control pipeline
A new adjoint matching framework formulates flow model alignment as optimal control, enabling direct regression training and terminal-trajectory truncation for efficiency gains on models like SiT-XL and FLUX.
-
Offline Materials Optimization with CliqueFlowmer
CliqueFlowmer combines clique-based model-based optimization with transformer and flow models to generate materials that optimize target properties better than generative baselines.
-
Scalable Maximum Entropy Reinforcement Learning for Diffusion Policies via Adjoint Matching
Presents adjoint matching for scalable max-ent RL training of diffusion policies, enabling simulation-free optimization.
-
A Theory on Flow Matching with Neural Networks
Establishes convergence guarantees for overparameterized 2-layer ReLU networks in flow matching, generalization bounds for the velocity-field objective, and Wasserstein guarantees for generated samples, using multi-task representation learning bounds.
-
SURGE: Approximation and Training Free Particle Filter for Diffusion Surrogate
SURGE is an unbiased particle filter that fuses diffusion-model simulations with noisy observations via sequential Monte Carlo reweighting over diffusion trajectories.
-
Simple Approximation and Derivative Free Inference-Time Scaling for Diffusion Models via Sequential Monte Carlo on Path Measures
URGE performs unbiased inference-time scaling for diffusion models by attaching multiplicative path weights from Girsanov estimation and resampling trajectories, with a proven equivalence to prior particle-wise SMC schemes.
-
Tempered Sequential Monte Carlo for Trajectory and Policy Optimization with Differentiable Dynamics
Tempered sequential Monte Carlo samples from a Boltzmann-tilted distribution over controllers to optimize trajectories and policies under differentiable dynamics.
-
Energy-Weighted Flow Matching: Unlocking Continuous Normalizing Flows for Efficient and Scalable Boltzmann Sampling
Energy-Weighted Flow Matching reformulates conditional flow matching with importance sampling to enable continuous normalizing flows to model Boltzmann distributions from energy evaluations alone, with iterative and annealed variants showing competitive performance on benchmarks.