Generalizes neural transport methods for free energy estimation to any state space with added algebraic and group-theoretic results on time reversal and h-transforms.
Score- based generative modeling with critically-damped langevin diffusion
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
Latent Consistency Models enable high-fidelity text-to-image generation in 2-4 steps by directly predicting solutions to the probability flow ODE in latent space, distilled from pre-trained LDMs.
A quantization technique for diffusion models that aligns sampling trajectories to preserve high-order sampler performance under quantization noise.
Biased noise sampling for rectified flows combined with a bidirectional text-image transformer architecture yields state-of-the-art high-resolution text-to-image results that scale predictably with model size.
Introduces higher-order Langevin dynamics with auxiliary variables as a defense that mixes randomness early to reduce membership inference success on diffusion models, measured via AUROC and FID on toy and speech data.
citing papers explorer
-
Free energy Estimation on Any State Space
Generalizes neural transport methods for free energy estimation to any state space with added algebraic and group-theoretic results on time reversal and h-transforms.
-
Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
Latent Consistency Models enable high-fidelity text-to-image generation in 2-4 steps by directly predicting solutions to the probability flow ODE in latent space, distilled from pre-trained LDMs.
-
Sampling-Aware Quantization for Diffusion Models
A quantization technique for diffusion models that aligns sampling trajectories to preserve high-order sampler performance under quantization noise.
-
Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
Biased noise sampling for rectified flows combined with a bidirectional text-image transformer architecture yields state-of-the-art high-resolution text-to-image results that scale predictably with model size.
-
Defending Diffusion Models Against Membership Inference Attacks via Higher-Order Langevin Dynamics
Introduces higher-order Langevin dynamics with auxiliary variables as a defense that mixes randomness early to reduce membership inference success on diffusion models, measured via AUROC and FID on toy and speech data.