FMRG reformulates guidance as deterministic optimal control, deriving a single-trajectory method using the flow map that matches or exceeds baselines on reward-guided generation and inverse problems with 3 NFEs at text-to-image scale.
Title resolution pending
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
citation-role summary
background 3
dataset 1
citation-polarity summary
representative citing papers
Oracle Noise optimizes diffusion model noise on a Riemannian hypersphere guided by key prompt words to preserve the Gaussian prior, eliminate norm inflation, and achieve faster semantic alignment than Euclidean methods.
Z²-Sampling implicitly realizes zero-cost zigzag trajectories for curvature-aware semantic alignment in diffusion models by reducing multi-step paths via operator dualities and temporal caching while synthesizing a directional derivative penalty.
A training-free speculative decoding method for block-based autoregressive video diffusion uses a quality router on worst-frame ImageReward scores to accept drafter proposals, achieving up to 2.09x speedup at 95.7% quality retention.
PixGS is a single-stage pixel-space diffusion model that directly produces high-quality 3D Gaussian Splats from text or images in ~1s, outperforming multi-stage latent methods on standard benchmarks.
FlowWM trains a flow-matching model in frozen DINOv3 feature space, using a one-step projection for temporal and task-driven losses, improving stochastic future prediction on a Waymo-derived benchmark.
SAMG uses spatially adaptive guidance scales derived from a geometric analysis of classifier-free guidance to resolve the detail-artifact dilemma in diffusion-based image and video generation.
VASR separates continuation and residual variance in reward-guided diffusion SMC, using optimal mass allocation and systematic resampling to achieve up to 26% better FID scores and faster runtimes than prior SMC and MCTS methods.
Listener-augmented GRPO uses an independent frozen VLM to provide dense confidence scores on reasoning traces, yielding 67.4% accuracy on ImageReward, up to +6% OOD gains on 1.2M-vote human data, and fewer reasoning contradictions.
DDPO uses policy gradients on the denoising process to optimize diffusion models for arbitrary rewards like human feedback or compressibility.
A reinforcement-learning agent that picks high-error trajectory segments during consistency distillation improves few-step text-to-image generation on FLUX and SDXL.
VRPO applies generative representation policy optimization to dynamically align diffusion features with pretrained visual encoders, claiming +1.8 FID gains and 2.3x faster training versus REPA.
BiDPO extends Diffusion DPO to bimodal preferences and adds region-aware guidance, improving compositional fidelity in text-to-image generation over prior methods.
Edit-GRPO decouples editing and preservation objectives via region-specific signals in a policy optimization framework to improve locality in image editing tasks.
citing papers explorer
-
How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance
FMRG reformulates guidance as deterministic optimal control, deriving a single-trajectory method using the flow map that matches or exceeds baselines on reward-guided generation and inverse problems with 3 NFEs at text-to-image scale.
-
Oracle Noise: Faster Semantic Spherical Alignment for Interpretable Latent Optimization
Oracle Noise optimizes diffusion model noise on a Riemannian hypersphere guided by key prompt words to preserve the Gaussian prior, eliminate norm inflation, and achieve faster semantic alignment than Euclidean methods.
-
$Z^2$-Sampling: Zero-Cost Zigzag Trajectories for Semantic Alignment in Diffusion Models
Z²-Sampling implicitly realizes zero-cost zigzag trajectories for curvature-aware semantic alignment in diffusion models by reducing multi-step paths via operator dualities and temporal caching while synthesizing a directional derivative penalty.
-
Speculative Decoding for Autoregressive Video Generation
A training-free speculative decoding method for block-based autoregressive video diffusion uses a quality router on worst-frame ImageReward scores to accept drafter proposals, achieving up to 2.09x speedup at 95.7% quality retention.
-
PixGS: Pixel-Space Diffusion for Direct 3D Gaussian Splat Generation
PixGS is a single-stage pixel-space diffusion model that directly produces high-quality 3D Gaussian Splats from text or images in ~1s, outperforming multi-stage latent methods on standard benchmarks.
-
Flow Matching in Feature Space for Stochastic World Modeling
FlowWM trains a flow-matching model in frozen DINOv3 feature space, using a one-step projection for temporal and task-driven losses, improving stochastic future prediction on a Waymo-derived benchmark.
-
Delta Score Matters! Spatial Adaptive Multi Guidance in Diffusion Models
SAMG uses spatially adaptive guidance scales derived from a geometric analysis of classifier-free guidance to resolve the detail-artifact dilemma in diffusion-based image and video generation.
-
VASR: Variance-Aware Systematic Resampling for Reward-Guided Diffusion
VASR separates continuation and residual variance in reward-guided diffusion SMC, using optimal mass allocation and systematic resampling to achieve up to 26% better FID scores and faster runtimes than prior SMC and MCTS methods.
-
Listener-Rewarded Thinking in VLMs for Image Preferences
Listener-augmented GRPO uses an independent frozen VLM to provide dense confidence scores on reasoning traces, yielding 67.4% accuracy on ImageReward, up to +6% OOD gains on 1.2M-vote human data, and fewer reasoning contradictions.
-
Training Diffusion Models with Reinforcement Learning
DDPO uses policy gradients on the denoising process to optimize diffusion models for arbitrary rewards like human feedback or compressibility.
-
Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Reinforcement Learning
A reinforcement-learning agent that picks high-error trajectory segments during consistency distillation improves few-step text-to-image generation on FLUX and SDXL.
-
Improving Visual Representation Alignment Generation with GRPO
VRPO applies generative representation policy optimization to dynamically align diffusion features with pretrained visual encoders, claiming +1.8 FID gains and 2.3x faster training versus REPA.
-
Compositional Text-to-Image Generation Via Region-aware Bimodal Direct Preference Optimization
BiDPO extends Diffusion DPO to bimodal preferences and adds region-aware guidance, improving compositional fidelity in text-to-image generation over prior methods.
-
Edit-GRPO: A Locality-Preserving Policy Optimization Framework for Image Editing
Edit-GRPO decouples editing and preservation objectives via region-specific signals in a policy optimization framework to improve locality in image editing tasks.