An abstract framework for neural flows with composition and separation structures is proven to universally approximate any operator, recovering ResNet and plain architectures via discretization.
hub
The Eleventh International Conference on Learning Representations , year=
22 Pith papers cite this work. Polarity classification is still indexing.
22
Pith papers citing it
hub tools
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
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.
BodyReLux achieves photorealistic, temporally consistent full-body video relighting via a diffusion model with token-based lighting conditioning trained on a hybrid static-dynamic capture dataset.
Kernel-gradient drifting reformulates drifting models via kernel gradients to yield identifiable one-step generation with smoothed score matching and KL descent on Euclidean, Riemannian, and discrete spaces.
Semi-discrete Flow Matching produces terminal assignment regions that are topologically simple (open, simply connected, homeomorphic to the ball under assumption) yet geometrically distinct from optimal transport Laguerre cells, as they can be non-convex with curved boundaries.
TRACE creates valid conformal prediction sets for complex generative models by scoring outputs via averaged denoising or velocity errors along stochastic transport paths instead of likelihoods.
A general framework reduces flow matching on symmetric spaces to flow matching on a Lie algebra subspace, linearizing geodesics.
TimeTok is a unified framework using hierarchical tokenization for granularity-controllable time-series generation that achieves state-of-the-art performance in standard tasks and shows transferability across heterogeneous datasets.
Image editing models fail zero-shot visual planning on abstract mazes and queen puzzles but generalize after finetuning, yet still cannot match human zero-shot efficiency.
OM-Path frames DGP inference as learning a deterministic transport map from reference to posterior inducing variables using probability-flow ODE on Doob-bridged SDE with Onsager-Machlup path regularization, yielding statistically significant gains over DBVI on power and protein UCI datasets.
COAST applies contrastive conceptors to steer VLA hidden states into task-specific success subspaces, yielding over 20% simulation and 40% real-robot success rate gains across three distinct policies.
Text embeddings in MM-DiTs encode a detectable omission signal for missing concepts; amplifying it via OSI reduces concept omission in text-to-image outputs on FLUX.1-Dev and SD3.5-Medium.
DRIFT enables stable offline-to-online fine-tuning of CTMC policies in discrete RL via advantage-weighted discrete flow matching, path-space regularization, and candidate-set approximation.
Coupled initial noises in diffusion models, with designed dependence but unchanged marginal Gaussians, improve generated image diversity on Stable Diffusion variants while preserving quality and alignment.
Derives RAM, a reward-adjusted consistency loss extending diffusion pretraining regression to efficient KL-regularized RL post-training, achieving peak rewards up to 50x faster than Flow-GRPO on Stable Diffusion 3.5M.
USB solves the Branching Schrödinger Bridge problem to enable simulation-free inference of stochastic discrete branching dynamics from single-cell omics snapshots.
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.
A generative framework using latent heteroscedastic Gaussian process approximated via Hilbert space methods plus optimal transport to model population trends and infer trajectories in temporal scRNA-seq data.
TAPE applies temporal-aware token pruning with smoothing, reselection, and timestep scheduling to speed up video diffusion models while preserving visual fidelity and coherence.
AFIL trains dual action generators on success and failure rollouts from a pretrained VLA to steer diffusion policies away from failure modes during inference.
LHSD estimates local intrinsic dimension in high-D spaces by spectral filtering of the log-density Hessian via SLQ to isolate zero-curvature tangent directions.
PPM injects parametric structural priors into generative models via a learnable mapping to improve probabilistic forecasts on non-stationary MTS data.
citing papers explorer
-
Neural Flow Operators can Approximate any Operator: Abstract Frameworks and Universal Approximations
An abstract framework for neural flows with composition and separation structures is proven to universally approximate any operator, recovering ResNet and plain architectures via discretization.
-
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.
-
BodyReLux: Temporally Consistent Full-Body Video Relighting
BodyReLux achieves photorealistic, temporally consistent full-body video relighting via a diffusion model with token-based lighting conditioning trained on a hybrid static-dynamic capture dataset.
-
Kernel-Gradient Drifting Models
Kernel-gradient drifting reformulates drifting models via kernel gradients to yield identifiable one-step generation with smoothed score matching and KL descent on Euclidean, Riemannian, and discrete spaces.
-
Tessellations of Semi-Discrete Flow Matching
Semi-discrete Flow Matching produces terminal assignment regions that are topologically simple (open, simply connected, homeomorphic to the ball under assumption) yet geometrically distinct from optimal transport Laguerre cells, as they can be non-convex with curved boundaries.
-
TRACE: Transport Alignment Conformal Prediction via Diffusion and Flow Matching Models
TRACE creates valid conformal prediction sets for complex generative models by scoring outputs via averaged denoising or velocity errors along stochastic transport paths instead of likelihoods.
-
Flow Matching on Symmetric Spaces
A general framework reduces flow matching on symmetric spaces to flow matching on a Lie algebra subspace, linearizing geodesics.
-
TimeTok: Granularity-Controllable Time-Series Generation via Hierarchical Tokenization
TimeTok is a unified framework using hierarchical tokenization for granularity-controllable time-series generation that achieves state-of-the-art performance in standard tasks and shows transferability across heterogeneous datasets.
-
Probing Visual Planning in Image Editing Models
Image editing models fail zero-shot visual planning on abstract mazes and queen puzzles but generalize after finetuning, yet still cannot match human zero-shot efficiency.
-
Onsager-Machlup Posterior Transport for Deep Gaussian Processes
OM-Path frames DGP inference as learning a deterministic transport map from reference to posterior inducing variables using probability-flow ODE on Doob-bridged SDE with Onsager-Machlup path regularization, yielding statistically significant gains over DBVI on power and protein UCI datasets.
-
Contrastive Conceptor Activation Steering (COAST): Unlocking Vision-Language-Action Models through Hidden States
COAST applies contrastive conceptors to steer VLA hidden states into task-specific success subspaces, yielding over 20% simulation and 40% real-robot success rate gains across three distinct policies.
-
Diagnosing and Correcting Concept Omission in Multimodal Diffusion Transformers
Text embeddings in MM-DiTs encode a detectable omission signal for missing concepts; amplifying it via OSI reduces concept omission in text-to-image outputs on FLUX.1-Dev and SD3.5-Medium.
-
Discrete Flow Matching for Offline-to-Online Reinforcement Learning
DRIFT enables stable offline-to-online fine-tuning of CTMC policies in discrete RL via advantage-weighted discrete flow matching, path-space regularization, and candidate-set approximation.
-
Couple to Control: Joint Initial Noise Design in Diffusion Models
Coupled initial noises in diffusion models, with designed dependence but unchanged marginal Gaussians, improve generated image diversity on Stable Diffusion variants while preserving quality and alignment.
-
Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow-Matching Models
Derives RAM, a reward-adjusted consistency loss extending diffusion pretraining regression to efficient KL-regularized RL post-training, achieving peak rewards up to 50x faster than Flow-GRPO on Stable Diffusion 3.5M.
-
Beyond Continuity: Simulation-free Reconstruction of Discrete Branching Dynamics from Single-cell Snapshots
USB solves the Branching Schrödinger Bridge problem to enable simulation-free inference of stochastic discrete branching dynamics from single-cell omics snapshots.
-
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.
-
Modeling Temporal scRNA-seq Data with Latent Gaussian Process and Optimal Transport
A generative framework using latent heteroscedastic Gaussian process approximated via Hilbert space methods plus optimal transport to model population trends and infer trajectories in temporal scRNA-seq data.
-
Temporal Aware Pruning for Efficient Diffusion-based Video Generation
TAPE applies temporal-aware token pruning with smoothing, reselection, and timestep scheduling to speed up video diffusion models while preserving visual fidelity and coherence.
-
Failing Forward: Adaptive Failure-Informed Learning for Vision-Language-Action Models
AFIL trains dual action generators on success and failure rollouts from a pretrained VLA to steer diffusion policies away from failure modes during inference.
-
Local Hessian Spectral Filtering for Robust Intrinsic Dimension Estimation
LHSD estimates local intrinsic dimension in high-D spaces by spectral filtering of the log-density Hessian via SLQ to isolate zero-curvature tangent directions.
-
Parametric Prior Mapping Framework for Non-stationary Probabilistic Time Series Forecasting
PPM injects parametric structural priors into generative models via a learnable mapping to improve probabilistic forecasts on non-stationary MTS data.