UOTIP learns an unbalanced optimal transport map from noisy to clean distributions for unpaired inverse problems, incorporating a likelihood cost and proving existence/uniqueness via quadratic cost satisfying the twist condition.
hub
Advances in neural information processing systems , volume=
31 Pith papers cite this work. Polarity classification is still indexing.
31
Pith papers citing it
hub tools
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
A multi-exposure video model predicts bracketed linear SDR sequences from single nonlinear SDR input, which a merging model combines into HDR video preserving shadow and highlight detail.
DirectTryOn achieves state-of-the-art one-step virtual try-on performance by applying pure conditional transport, garment preservation loss, and self-consistency loss to straighten trajectories in pretrained generative models.
A single-network implicit neural optimal transport method that solves the c-transform via proximal fixed-point iteration for stable, non-adversarial training.
Polyphonia improves zero-shot stem-specific timbre transfer in polyphonic music by 15.5% target alignment via acoustic-informed attention calibration that uses probabilistic priors to set coarse boundaries.
MaMi-HOI counters geometric forgetting in diffusion models via a Geometry-Aware Proximity Adapter for precise contacts and a Kinematic Harmony Adapter for natural whole-body postures in human-object interactions.
VAnim creates open-domain text-to-SVG animations via sparse state updates on a persistent DOM tree, identification-first planning, and rendering-aware RL with a new 134k-example benchmark.
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.
ELSA3D introduces elastic semantic anchoring via sparse anchor tokens and a scale-aware octree tokenizer to unify 3D generation and captioning at reduced computational cost.
DiT-Pruning squares the weight term in the pruning saliency metric and adapts per-layer versus per-channel granularity, claiming strong quality retention for diffusion transformers at high sparsity.
IDEA is a TTA framework for VLN that builds a dynamic asset library from Fisher-weighted soft prompts and domain coordinates, then uses convex-hull projection for cross-domain bridging and training-free adaptation.
SGD is reformulated via a master equation from discrete updates, producing a discrete Fokker-Planck equation that predicts non-stationary variance growth proportional to learning rate in flat Hessian directions.
Higher-order Langevin dynamics reduce memorization in diffusion models by governing data trajectories with a low-pass-filtered score whose smoothness increases with order.
Proposes a KL-informed robust optimal transport divergence with stochastic estimation and bootstrap-based SBI for robust inference under joint geometric and TV contamination.
VoxScene is a new anchor-conditioned voxel diffusion model that synthesizes collision-free 3D indoor scene arrangements via discrete volumetric occupancies and uses the grids for asset retrieval.
AdaEraser introduces token-wise adaptive attention suppression in diffusion denoising to enable high-quality training-free object removal by modulating suppression according to evolving self-attention maps.
GeoQuery replaces corrupted rendering features with geometry-aligned proxy queries and restricts cross-view attention to local windows, enabling robust diffusion-based refinement under extreme view sparsity.
Recursive generative retraining with heterogeneous rewards converges to a stable distribution satisfying a weighted Nash bargaining solution, preserving diversity under stated conditions.
A technique for parametric stylistic control in latent diffusion models learns disentangled directions from synthetic datasets and applies them via guidance composition while preserving semantics.
VIAR embeds an implicit equilibrium layer in next-scale AR image models, reporting FID 2.16 on ImageNet 256 with 38.4% of VAR’s parameters and a per-scale inference compute knob.
TripoSG generates high-fidelity 3D meshes from input images via a large-scale rectified flow transformer and hybrid-trained 3D VAE on a custom 2-million-sample dataset, claiming state-of-the-art fidelity and generalization.
VisionReward learns multi-dimensional human preferences for image and video generation via hierarchical assessment and linear weighting, outperforming VideoScore by 17.2% in prediction accuracy and yielding 31.6% higher win rates in text-to-video models.
DPOP is a new loss function that prevents DPO from lowering preferred response likelihoods and outperforms standard DPO on diverse datasets, MT-Bench, and enables Smaug-72B to exceed 80% on the Open LLM Leaderboard.
A single-objective rectified flow variant uses neural ODEs trained by regression to monotonically decrease a fixed convex transport cost while preserving marginal distributions.
citing papers explorer
-
UOTIP: Unbalanced Optimal Transport Map for Unpaired Inverse Problems
UOTIP learns an unbalanced optimal transport map from noisy to clean distributions for unpaired inverse problems, incorporating a likelihood cost and proving existence/uniqueness via quadratic cost satisfying the twist condition.
-
Generating HDR Video from SDR Video
A multi-exposure video model predicts bracketed linear SDR sequences from single nonlinear SDR input, which a merging model combines into HDR video preserving shadow and highlight detail.
-
DirectTryOn: One-Step Virtual Try-On via Straightened Conditional Transport
DirectTryOn achieves state-of-the-art one-step virtual try-on performance by applying pure conditional transport, garment preservation loss, and self-consistency loss to straighten trajectories in pretrained generative models.
-
Implicit Neural Optimal Transport via Fixed-Point Optimization
A single-network implicit neural optimal transport method that solves the c-transform via proximal fixed-point iteration for stable, non-adversarial training.
-
Polyphonia: Zero-Shot Timbre Transfer in Polyphonic Music with Acoustic-Informed Attention Calibration
Polyphonia improves zero-shot stem-specific timbre transfer in polyphonic music by 15.5% target alignment via acoustic-informed attention calibration that uses probabilistic priors to set coarse boundaries.
-
MaMi-HOI: Harmonizing Global Kinematics and Local Geometry for Human-Object Interaction Generation
MaMi-HOI counters geometric forgetting in diffusion models via a Geometry-Aware Proximity Adapter for precise contacts and a Kinematic Harmony Adapter for natural whole-body postures in human-object interactions.
-
VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animation
VAnim creates open-domain text-to-SVG animations via sparse state updates on a persistent DOM tree, identification-first planning, and rendering-aware RL with a new 134k-example benchmark.
-
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.
-
ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation
ELSA3D introduces elastic semantic anchoring via sparse anchor tokens and a scale-aware octree tokenizer to unify 3D generation and captioning at reduced computational cost.
-
Post-Training Pruning for Diffusion Transformers
DiT-Pruning squares the weight term in the pruning saliency metric and adapts per-layer versus per-channel granularity, claiming strong quality retention for diffusion transformers at high sparsity.
-
Turning Adaptation into Assets: Cross-Domain Bridging for Online Vision-Language Navigation
IDEA is a TTA framework for VLN that builds a dynamic asset library from Fisher-weighted soft prompts and domain coordinates, then uses convex-hull projection for cross-domain bridging and training-free adaptation.
-
Why SGD is not Brownian Motion: A New Perspective on Stochastic Dynamics
SGD is reformulated via a master equation from discrete updates, producing a discrete Fokker-Planck equation that predicts non-stationary variance growth proportional to learning rate in flat Hessian directions.
-
Reducing Diffusion Model Memorization with Higher Order Langevin Dynamics
Higher-order Langevin dynamics reduce memorization in diffusion models by governing data trajectories with a low-pass-filtered score whose smoothness increases with order.
-
Robust Simulation Based Inference Through Robust Optimal Transport
Proposes a KL-informed robust optimal transport divergence with stochastic estimation and bootstrap-based SBI for robust inference under joint geometric and TV contamination.
-
VoxScene: Anchor-Conditioned Voxel Diffusion for Indoor Scene Arrangement
VoxScene is a new anchor-conditioned voxel diffusion model that synthesizes collision-free 3D indoor scene arrangements via discrete volumetric occupancies and uses the grids for asset retrieval.
-
AdaEraser: Training-Free Object Removal via Adaptive Attention Suppression
AdaEraser introduces token-wise adaptive attention suppression in diffusion denoising to enable high-quality training-free object removal by modulating suppression according to evolving self-attention maps.
-
GeoQuery: Geometry-Query Diffusion for Sparse-View Reconstruction
GeoQuery replaces corrupted rendering features with geometry-aligned proxy queries and restricts cross-view attention to local windows, enabling robust diffusion-based refinement under extreme view sparsity.
-
Curated Synthetic Data Doesn't Have to Collapse: A Theoretical Study of Generative Retraining with Pluralistic Preferences
Recursive generative retraining with heterogeneous rewards converges to a stable distribution satisfying a weighted Nash bargaining solution, preserving diversity under stated conditions.
-
Stylistic Attribute Control in Latent Diffusion Models
A technique for parametric stylistic control in latent diffusion models learns disentangled directions from synthetic datasets and applies them via guidance composition while preserving semantics.
-
Visual Implicit Autoregressive Modeling
VIAR embeds an implicit equilibrium layer in next-scale AR image models, reporting FID 2.16 on ImageNet 256 with 38.4% of VAR’s parameters and a per-scale inference compute knob.
-
TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models
TripoSG generates high-fidelity 3D meshes from input images via a large-scale rectified flow transformer and hybrid-trained 3D VAE on a custom 2-million-sample dataset, claiming state-of-the-art fidelity and generalization.
-
VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation
VisionReward learns multi-dimensional human preferences for image and video generation via hierarchical assessment and linear weighting, outperforming VideoScore by 17.2% in prediction accuracy and yielding 31.6% higher win rates in text-to-video models.
-
Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive
DPOP is a new loss function that prevents DPO from lowering preferred response likelihoods and outperforms standard DPO on diverse datasets, MT-Bench, and enables Smaug-72B to exceed 80% on the Open LLM Leaderboard.
-
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.
-
ERPPO: Entropy Regularization-based Proximal Policy Optimization
ERPPO adds a DSA-based ambiguity estimator to MAPPO and switches between L1 and L2 entropy regularization to improve exploration and stability in non-stationary multi-dimensional observations.
-
Lossless Anti-Distillation Sampling
LADS is a sampling method that keeps benign user generations statistically identical to the original model while forcing correlated samples across a distiller's multiple accounts, provably worsening their generalization via uniform convergence bounds.
-
Mutual Enhancement Between Global Tokens and Patch Tokens: From Theory to Practice
TaTok is a theoretically grounded adaptive tokenization method that uses global tokens and cumulative conditional entropy filtering to reduce redundancy while improving reconstruction quality over fixed-rate patch tokenization.
-
Active Sampling for Ultra-Low-Bit-Rate Video Compression via Conditional Controlled Diffusion
ActDiff-VC partitions video into segments, transmits adaptive keyframes and budget-aware point trajectories, and reconstructs frames via conditional diffusion, reporting up to 64.6% bitrate reduction at matched NIQE on UVG and MCL-JCV.
-
MIRA: A Score for Conditional Distribution Accuracy and Model Comparison
MIRA is a new analytic score for conditional distribution accuracy derived from equal probability mass assignment, enabling Bayesian model comparison via direct posterior validation.
-
Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments
SPG-Layout combines statistical object priors with hierarchical large-object-first placement to produce physically plausible text-driven 3D scenes in non-Manhattan rooms and outperforms baselines on a new 500-scene benchmark.
- Unifying Deep Stochastic Processes for Image Enhancement