Rectified flow learns straight-path neural ODEs for distribution transport, yielding efficient generative models and domain transfers that work well even with a single simulation step.
Dual diffusion implicit bridges for image-to-image translation
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Timage generates text query overlays on images via Constrained Schrödinger Bridge to boost fine-grained spatial reasoning in vision-language models, outperforming larger systems on VMCBench with a 7B backbone.
Flow Reversal Steering steers flow matching generalist policies by reversing suboptimal actions to nearby better modes, enabling improved zero-shot control, quick distillation, and RL bootstrapping in robotic manipulation.
OT-Bridge Editor uses geometrically constrained entropic optimal transport to synthesize CAG images with precise stenosis, improving downstream detection by 27.8% on ARCADE and 23.0% on a multi-center dataset.
Doloris introduces dual conditional diffusion implicit bridges plus a sparsity masking strategy to model unpaired single-cell perturbation responses and reports state-of-the-art results on public datasets.
A saliency-guided warp-unwarp method reallocates spatial representation to preserve fine structures in latent diffusion models for image-to-image translation.
A hybrid gradient-descent-plus-fixed-point method for inverting DDIM improves initial latent recovery and reconstruction accuracy over prior techniques on three datasets, with a new self-interpolation test exposing weaknesses in existing approaches.
T-CLIP introduces a physics-aware thermal captioning dataset (IR-Cap) and a decoupled dual-LoRA adaptation of CLIP that improves cross-modal retrieval on thermal benchmarks by separating scene-level and object-level thermal understanding.
DMSM proposes a self-supervised dual-domain multi-path diffusion framework for accelerated MRI reconstruction that removes the need for fully sampled training data while providing uncertainty maps.
Stochastic image enhancement methods are shown to be variants of a shared SDE differing in drift, diffusion, terminal distributions and boundary conditions, with controlled experiments revealing no single dominant family and a new modular library released.
MedShift applies flow matching and Schrödinger bridges for class-conditional unpaired translation between synthetic and real skull X-rays, benchmarked on the new X-DigiSkull dataset.
A principled monograph showing that variational, score-based, and flow-based diffusion models are instances of one continuous-time transport backbone, with sampling equal to solving a differential equation governed by the Fokker–Planck equation.
citing papers explorer
-
Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
Rectified flow learns straight-path neural ODEs for distribution transport, yielding efficient generative models and domain transfers that work well even with a single simulation step.
-
Timage: A Generative Text-in-Image Paradigm for Fine-Tuning Vision-Language Models
Timage generates text query overlays on images via Constrained Schrödinger Bridge to boost fine-grained spatial reasoning in vision-language models, outperforming larger systems on VMCBench with a 7B backbone.
-
Improving Robotic Generalist Policies via Flow Reversal Steering
Flow Reversal Steering steers flow matching generalist policies by reversing suboptimal actions to nearby better modes, enabling improved zero-shot control, quick distillation, and RL bootstrapping in robotic manipulation.
-
Geometrically Constrained Stenosis Editing in Coronary Angiography via Entropic Optimal Transport
OT-Bridge Editor uses geometrically constrained entropic optimal transport to synthesize CAG images with precise stenosis, improving downstream detection by 27.8% on ARCADE and 23.0% on a multi-center dataset.
-
Doloris: Dual Conditional Diffusion Implicit Bridges with Sparsity Masking Strategy for Unpaired Single-Cell Perturbation Estimation
Doloris introduces dual conditional diffusion implicit bridges plus a sparsity masking strategy to model unpaired single-cell perturbation responses and reports state-of-the-art results on public datasets.
-
WarpI2I: Image Warping for Image-to-Image Translation
A saliency-guided warp-unwarp method reallocates spatial representation to preserve fine structures in latent diffusion models for image-to-image translation.
-
Inverting the Generation Process of Denoising Diffusion Implicit Models: Empirical Evaluation and a Novel Method
A hybrid gradient-descent-plus-fixed-point method for inverting DDIM improves initial latent recovery and reconstruction accuracy over prior techniques on three datasets, with a new self-interpolation test exposing weaknesses in existing approaches.
-
T-CLIP: Enabling Thermal Perception for Contrastive Language-Image Pretraining
T-CLIP introduces a physics-aware thermal captioning dataset (IR-Cap) and a decoupled dual-LoRA adaptation of CLIP that improves cross-modal retrieval on thermal benchmarks by separating scene-level and object-level thermal understanding.
-
Dual-domain Multi-path Self-supervised Diffusion Model for Accelerated MRI Reconstruction
DMSM proposes a self-supervised dual-domain multi-path diffusion framework for accelerated MRI reconstruction that removes the need for fully sampled training data while providing uncertainty maps.
-
Unifying Deep Stochastic Processes for Image Enhancement
Stochastic image enhancement methods are shown to be variants of a shared SDE differing in drift, diffusion, terminal distributions and boundary conditions, with controlled experiments revealing no single dominant family and a new modular library released.
-
MedShift: Implicit Conditional Transport for X-Ray Domain Adaptation
MedShift applies flow matching and Schrödinger bridges for class-conditional unpaired translation between synthetic and real skull X-rays, benchmarked on the new X-DigiSkull dataset.
-
The Principles of Diffusion Models
A principled monograph showing that variational, score-based, and flow-based diffusion models are instances of one continuous-time transport backbone, with sampling equal to solving a differential equation governed by the Fokker–Planck equation.