A control-theoretic linear program yields value-driven transport policies for generative modeling with straight paths and simulation-free training.
hub Canonical reference
Denoising diffusion probabilistic models
Canonical reference. 71% of citing Pith papers cite this work as background.
23
Pith papers citing it
Background
71% of classified citations
hub tools
citation-role summary
background 5
method 2
citation-polarity summary
representative citing papers
TCE bridges domain gaps in offline RL by selectively using source data or generating target-aligned transitions via a dual score-based model, outperforming baselines in experiments.
SpecEdit accelerates diffusion-based image editing up to 10x by using a low-resolution draft to identify edit-relevant tokens via semantic discrepancies for selective high-resolution denoising.
LeapAlign fine-tunes flow matching models by constructing two consecutive leaps that skip multiple ODE steps with randomized timesteps and consistency weighting, enabling stable updates at any generation step.
Diffusion models generate joint pairs of Lagrangian trajectories that reproduce turbulent pair separation statistics, including deviations from Richardson scaling, while preserving single-particle properties.
CARD uses radix decomposition to enable autoregressive modeling of molecular coordinates as a zero-free-energy reference distribution, delivering classical accuracy for absolute free energy on unseen systems at ~40x speedup.
A new evaluation framework using latent diffusion on frozen vision backbones shows video-pretrained models consistently outperform image-based ones in forecasting entire trajectories across abstraction levels.
BulletGen enhances 4D dynamic scene reconstruction from monocular videos by supervising Gaussian optimization with diffusion-generated frames aligned at a bullet-time step, achieving SOTA on novel-view synthesis and tracking.
2ndMatch finetunes pruned diffusion models via second-order Jacobian matching inspired by Finite-Time Lyapunov Exponents to reduce the quality gap with dense models on image generation tasks.
Latent Wavelet Diffusion uses wavelet energy map masking and a scale-consistent VAE to improve detail fidelity in 2K-4K image generation without extra inference overhead.
DreamPolicy integrates an autoregressive diffusion world model with policy learning to produce a single scalable policy that generalizes to unseen composite terrains for humanoid locomotion.
DanceGRPO applies GRPO to visual generation tasks to achieve stable policy optimization across diffusion models, rectified flows, multiple tasks, and diverse reward models, outperforming prior RL methods.
Mogao presents a causal unified model with deep fusion, dual encoders, and interleaved position embeddings that achieves strong performance on multi-modal understanding, text-to-image generation, and coherent interleaved outputs including zero-shot editing.
SkyReels-V2 produces infinite-length film videos via MLLM-based captioning, progressive pretraining, motion RL, and diffusion forcing with non-decreasing noise schedules.
HybridVLA unifies diffusion and autoregression in a single VLA model via collaborative training and ensemble to raise robot manipulation success rates by 14% in simulation and 19% in real-world tasks.
GR-2 pre-trains on web-scale videos then fine-tunes on robot data to reach 97.7% average success across over 100 manipulation tasks with strong generalization to new scenes and objects.
Presents Instant3D for rapid text/image-to-3D generation via multi-view diffusion plus feed-forward reconstruction, and FastMap for 10x faster structure-from-motion with comparable accuracy.
COinCO is a new dataset of inpainted COCO images with in- and out-of-context objects, enabling context reasoning, object prediction from scenes, and improved fake image detection.
A diffusion model variant that adds structured non-zero-mean noise via modified forward/reverse processes, yielding an ELBO loss analogous to offset noise but with time-dependent coefficients, and showing gains on synthetic high-dimensional data.
Step1X-Edit integrates a multimodal LLM with a diffusion decoder, trained on a custom high-quality dataset, to deliver image editing performance that surpasses open-source baselines and approaches proprietary models on the new GEdit-Bench.
Hunyuan3D 2.0 scales flow-based diffusion transformers and texture synthesis models to generate high-resolution textured 3D assets that outperform prior state-of-the-art in geometry, alignment, and texture quality.
Hunyuan3D 2.1 is a two-part system with DiT for shape generation and Paint for texture synthesis that produces high-fidelity 3D assets with PBR materials.
citing papers explorer
-
Generative Modeling by Value-Driven Transport
A control-theoretic linear program yields value-driven transport policies for generative modeling with straight paths and simulation-free training.
-
Bridging Domain Gaps with Target-Aligned Generation for Offline Reinforcement Learning
TCE bridges domain gaps in offline RL by selectively using source data or generating target-aligned transitions via a dual score-based model, outperforming baselines in experiments.
-
SpecEdit: Training-Free Acceleration for Diffusion based Image Editing via Semantic Locking
SpecEdit accelerates diffusion-based image editing up to 10x by using a low-resolution draft to identify edit-relevant tokens via semantic discrepancies for selective high-resolution denoising.
-
LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories
LeapAlign fine-tunes flow matching models by constructing two consecutive leaps that skip multiple ODE steps with randomized timesteps and consistency weighting, enabling stable updates at any generation step.
-
Turbulent pair dispersion with Stochastic Generative Diffusion Models
Diffusion models generate joint pairs of Lagrangian trajectories that reproduce turbulent pair separation statistics, including deviations from Richardson scaling, while preserving single-particle properties.
-
CARD: Coarse-to-fine Autoregressive Modeling with Radix-based Decomposition for Transferable Free Energy Estimation
CARD uses radix decomposition to enable autoregressive modeling of molecular coordinates as a zero-free-energy reference distribution, delivering classical accuracy for absolute free energy on unseen systems at ~40x speedup.
-
Frozen Forecasting: A Unified Evaluation
A new evaluation framework using latent diffusion on frozen vision backbones shows video-pretrained models consistently outperform image-based ones in forecasting entire trajectories across abstraction levels.
-
BulletGen: Improving 4D Reconstruction with Bullet-Time Generation
BulletGen enhances 4D dynamic scene reconstruction from monocular videos by supervising Gaussian optimization with diffusion-generated frames aligned at a bullet-time step, achieving SOTA on novel-view synthesis and tracking.
-
2ndMatch: Finetuning Pruned Diffusion Models via Second-Order Jacobian Matching
2ndMatch finetunes pruned diffusion models via second-order Jacobian matching inspired by Finite-Time Lyapunov Exponents to reduce the quality gap with dense models on image generation tasks.
-
Latent Wavelet Diffusion For Ultra-High-Resolution Image Synthesis
Latent Wavelet Diffusion uses wavelet energy map masking and a scale-consistent VAE to improve detail fidelity in 2K-4K image generation without extra inference overhead.
-
DreamPolicy: A Unified World-model Policy for Scalable Humanoid Locomotion
DreamPolicy integrates an autoregressive diffusion world model with policy learning to produce a single scalable policy that generalizes to unseen composite terrains for humanoid locomotion.
-
DanceGRPO: Unleashing GRPO on Visual Generation
DanceGRPO applies GRPO to visual generation tasks to achieve stable policy optimization across diffusion models, rectified flows, multiple tasks, and diverse reward models, outperforming prior RL methods.
-
Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation
Mogao presents a causal unified model with deep fusion, dual encoders, and interleaved position embeddings that achieves strong performance on multi-modal understanding, text-to-image generation, and coherent interleaved outputs including zero-shot editing.
-
SkyReels-V2: Infinite-length Film Generative Model
SkyReels-V2 produces infinite-length film videos via MLLM-based captioning, progressive pretraining, motion RL, and diffusion forcing with non-decreasing noise schedules.
-
HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model
HybridVLA unifies diffusion and autoregression in a single VLA model via collaborative training and ensemble to raise robot manipulation success rates by 14% in simulation and 19% in real-world tasks.
-
GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation
GR-2 pre-trains on web-scale videos then fine-tunes on robot data to reach 97.7% average success across over 100 manipulation tasks with strong generalization to new scenes and objects.
-
Efficient 3D Content Reconstruction and Generation
Presents Instant3D for rapid text/image-to-3D generation via multi-view diffusion plus feed-forward reconstruction, and FastMap for 10x faster structure-from-motion with comparable accuracy.
-
Common Inpainted Objects In-N-Out of Context
COinCO is a new dataset of inpainted COCO images with in- and out-of-context objects, enabling context reasoning, object prediction from scenes, and improved fake image detection.
-
A Probabilistic Formulation of Offset Noise in Diffusion Models
A diffusion model variant that adds structured non-zero-mean noise via modified forward/reverse processes, yielding an ELBO loss analogous to offset noise but with time-dependent coefficients, and showing gains on synthetic high-dimensional data.
-
Step1X-Edit: A Practical Framework for General Image Editing
Step1X-Edit integrates a multimodal LLM with a diffusion decoder, trained on a custom high-quality dataset, to deliver image editing performance that surpasses open-source baselines and approaches proprietary models on the new GEdit-Bench.
-
Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation
Hunyuan3D 2.0 scales flow-based diffusion transformers and texture synthesis models to generate high-resolution textured 3D assets that outperform prior state-of-the-art in geometry, alignment, and texture quality.
-
Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material
Hunyuan3D 2.1 is a two-part system with DiT for shape generation and Paint for texture synthesis that produces high-fidelity 3D assets with PBR materials.
- Training-Free Inference for High-Resolution Sinogram Completion