Quotient-space diffusion models generate correct symmetric distributions by removing redundancy on the quotient space, simplifying learning and improving results on small molecules and proteins under SE(3) symmetry.
hub
Advances in Neural Information Processing Systems , volume=
21 Pith papers cite this work. Polarity classification is still indexing.
21
Pith papers citing it
hub tools
citation-role summary
background 3
method 1
citation-polarity summary
representative citing papers
ConTact introduces a contact-then-act architecture with distance-biased cross-attention and contact-weighted loss for antibody CDR design, reporting 5-6% better backbone RMSD and superior contact metrics on CHIMERA-Bench splits.
Object functionalization is cast as neural graph completion over a functional graph of parts, contacts, and motions, followed by geometry realization that also rectifies erroneous motions, demonstrated on furniture with a new paired dataset.
AnyBand-Diff is a spectral-prior-guided diffusion model that unifies remote sensing image generation and band repair while maintaining radiometric fidelity through physics-guided sampling and multi-scale losses.
STMD distills the full transition map of diffusion sampling SDEs into a conditional Mean Flow model to enable fast one- or few-step stochastic sampling without teacher models or bi-level optimization.
SSDMs introduce an intrinsic score-based diffusion framework on the Fubini-Study manifold to sample quantum pure-state ensembles without classical re-preparation.
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.
AgForce improves antigen-conditioned antibody design by using framework dropout, gated bottlenecks, hyperbolic cross attention, MDN sequence head with Potts-like coupling, annealed MCL, and antigen cycle consistency to achieve 8% better amino acid recovery and superior binding metrics on CHIMERA-BEN
EvoStruct integrates evolutionary priors from a protein language model with structural priors from an E(3)-equivariant GNN to raise amino acid recovery by 16% and diversity by 2.3x on CHIMERA-Bench while cutting perplexity 43%.
LLapDiff generates horizon-wide forecasts and imputations for irregular time series by modeling latent dynamics with learnable poles in the Laplace domain and a gap-aware summarizer.
FLASH Policy uses sparse Legendre polynomial trajectory fitting and history-anchored flow matching to enable single-step inference for visuomotor control, reporting 31.4 ms per-episode latency and >=92% success on five simulated plus two real manipulation tasks.
Scaling pretrained representations improves label-free OOD detection on frozen backbones, causing performance gaps between global and local detectors to vanish across vision and language tasks.
Training and sampling in static scalar energy generative models are two instances of the same Lyapunov-driven density transport dynamics on Wasserstein space, differing only by initial condition, which yields a finite stopping criterion for Langevin sampling and additive composition rules that keep
GeoTopoDiff transfers diffusion priors to a mixed graph state space with topology-aware constraints from sparse slices, cutting morphology errors by 19.8% and transport errors by 36.5% on PTFE and sandstone samples.
Embedding selection mechanisms into generative simulators enables amortized Bayesian inference to produce debiased, well-calibrated posteriors without tractable likelihoods.
A neural estimator trained on self-computed mutual information from masked diffusion model hidden states predicts the full pairwise MI matrix in one forward pass to enable faster parallel decoding of conditionally independent variables.
CameraCtrl enables accurate camera pose control in video diffusion models through a trained plug-and-play module and dataset choices emphasizing diverse camera trajectories with matching appearance.
A single-objective rectified flow variant uses neural ODEs trained by regression to monotonically decrease a fixed convex transport cost while preserving marginal distributions.
APEX is an assumption-free image quality metric using Sliced Wasserstein Distance on CLIP and DINOv2 embeddings that claims superior robustness to degradations and cross-dataset stability.
RAFT aligns generative models by ranking samples with a reward model and fine-tuning only on the top-ranked outputs, reporting gains on reward scores and automated metrics for LLMs and diffusion models.
citing papers explorer
-
Quotient-Space Diffusion Models
Quotient-space diffusion models generate correct symmetric distributions by removing redundancy on the quotient space, simplifying learning and improving results on small molecules and proteins under SE(3) symmetry.
-
ConTact: Contact-First Antibody CDR Design via Explicit Interface Reasoning
ConTact introduces a contact-then-act architecture with distance-biased cross-attention and contact-weighted loss for antibody CDR design, reporting 5-6% better backbone RMSD and superior contact metrics on CHIMERA-Bench splits.
-
Functionalization via Structure Completion and Motion Rectification
Object functionalization is cast as neural graph completion over a functional graph of parts, contacts, and motions, followed by geometry realization that also rectifies erroneous motions, demonstrated on furniture with a new paired dataset.
-
AnyBand-Diff: A Unified Remote Sensing Image Generation and Band Repair Framework with Spectral Priors
AnyBand-Diff is a spectral-prior-guided diffusion model that unifies remote sensing image generation and band repair while maintaining radiometric fidelity through physics-guided sampling and multi-scale losses.
-
Stochastic Transition-Map Distillation for Fast Probabilistic Inference
STMD distills the full transition map of diffusion sampling SDEs into a conditional Mean Flow model to enable fast one- or few-step stochastic sampling without teacher models or bi-level optimization.
-
Stochastic Schr\"odinger Diffusion Models for Pure-State Ensemble Generation
SSDMs introduce an intrinsic score-based diffusion framework on the Fubini-Study manifold to sample quantum pure-state ensembles without classical re-preparation.
-
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.
-
AgForce Enables Antigen-conditioned Generative Antibody Design
AgForce improves antigen-conditioned antibody design by using framework dropout, gated bottlenecks, hyperbolic cross attention, MDN sequence head with Potts-like coupling, annealed MCL, and antigen cycle consistency to achieve 8% better amino acid recovery and superior binding metrics on CHIMERA-BEN
-
EvoStruct: Bridging Evolutionary and Structural Priors for Antibody CDR Design via Protein Language Model Adaptation
EvoStruct integrates evolutionary priors from a protein language model with structural priors from an E(3)-equivariant GNN to raise amino acid recovery by 16% and diversity by 2.3x on CHIMERA-Bench while cutting perplexity 43%.
-
Latent Laplace Diffusion for Irregular Multivariate Time Series
LLapDiff generates horizon-wide forecasts and imputations for irregular time series by modeling latent dynamics with learnable poles in the Laplace domain and a gap-aware summarizer.
-
FLASH: Efficient Visuomotor Policy via Sparse Sampling
FLASH Policy uses sparse Legendre polynomial trajectory fitting and history-anchored flow matching to enable single-step inference for visuomotor control, reporting 31.4 ms per-episode latency and >=92% success on five simulated plus two real manipulation tasks.
-
Scaling Pretrained Representations Enables Label-Free Out-of-Distribution Detection Without Fine-Tuning
Scaling pretrained representations improves label-free OOD detection on frozen backbones, causing performance gaps between global and local detectors to vanish across vision and language tasks.
-
Energy Generative Modeling: A Lyapunov-based Energy Matching Perspective
Training and sampling in static scalar energy generative models are two instances of the same Lyapunov-driven density transport dynamics on Wasserstein space, differing only by initial condition, which yields a finite stopping criterion for Langevin sampling and additive composition rules that keep
-
GeoTopoDiff: Learning Geometry--Topology Graph Priors through Boundary-Constrained Mixed Diffusion for Sparse-Slice 3D Porous Reconstruction
GeoTopoDiff transfers diffusion priors to a mixed graph state space with topology-aware constraints from sparse slices, cutting morphology errors by 19.8% and transport errors by 36.5% on PTFE and sandstone samples.
-
Overcoming Selection Bias in Statistical Studies With Amortized Bayesian Inference
Embedding selection mechanisms into generative simulators enables amortized Bayesian inference to produce debiased, well-calibrated posteriors without tractable likelihoods.
-
Neural Estimation of Pairwise Mutual Information in Masked Discrete Sequence Models
A neural estimator trained on self-computed mutual information from masked diffusion model hidden states predicts the full pairwise MI matrix in one forward pass to enable faster parallel decoding of conditionally independent variables.
-
CameraCtrl: Enabling Camera Control for Text-to-Video Generation
CameraCtrl enables accurate camera pose control in video diffusion models through a trained plug-and-play module and dataset choices emphasizing diverse camera trajectories with matching appearance.
-
Rectified Flow: A Marginal Preserving Approach to Optimal Transport
A single-objective rectified flow variant uses neural ODEs trained by regression to monotonically decrease a fixed convex transport cost while preserving marginal distributions.
-
APEX: Assumption-free Projection-based Embedding eXamination Metric for Image Quality Assessment
APEX is an assumption-free image quality metric using Sliced Wasserstein Distance on CLIP and DINOv2 embeddings that claims superior robustness to degradations and cross-dataset stability.
-
RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment
RAFT aligns generative models by ranking samples with a reward model and fine-tuning only on the top-ranked outputs, reporting gains on reward scores and automated metrics for LLMs and diffusion models.
- LASER: Learning Active Sensing for Continuum Field Reconstruction