OctoT2I uses a no-supervision PSEL loop to discover model capability frontiers and route T2I tasks, reaching 0.96 GenEval score with 90.3% speedup over Flow-GRPO.
8 Sana-sprint: One-step diffusion with continuous-time consis- tency distillation
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 1
baseline 1
method 1
citation-polarity summary
representative citing papers
Noise optimization during sampling recovers diversity in mode-collapsed diffusion models while preserving output fidelity.
Distilled one-step consistency model from optimal-transport flow-matching teacher reconstructs high-fidelity dynamical system flows from low-fidelity data with 12x speedup, half the parameters, and 23.1% better SSIM than scratch-trained baselines.
By requiring and using highly discriminative LLM text features, the work enables the first effective one-step text-conditioned image generation with MeanFlow.
The work introduces rCM, a score-regularized continuous-time consistency model that matches DMD2 quality on large models up to 14B parameters while improving diversity and enabling 1-4 step sampling.
R3D2 trains a lightweight diffusion model on synthetic placements of 3DGS-generated assets to produce photorealistic insertions with consistent illumination into autonomous driving scenes.
RATS lets few-step visual generators surpass multi-step teachers by shaping trajectories with reward-based adaptive guidance instead of strict imitation.
Woosh is a new publicly released foundation model optimized for high-quality sound effect generation from text or video, showing competitive or better results than open alternatives like Stable Audio Open.
Stabilizes MeanFlow for large-scale diffusion distillation via discrete warm-up and trajectory alignment, reporting better results on FLUX.1-dev and HunyuanImage 3.0.
citing papers explorer
-
OctoT2I: A Self-Evolving Agentic Text-to-Image Router
OctoT2I uses a no-supervision PSEL loop to discover model capability frontiers and route T2I tasks, reaching 0.96 GenEval score with 90.3% speedup over Flow-GRPO.
-
It's Never Too Late: Noise Optimization for Collapse Recovery in Trained Diffusion Models
Noise optimization during sampling recovers diversity in mode-collapsed diffusion models while preserving output fidelity.
-
Physical Fidelity Reconstruction via Improved Consistency-Distilled Flow Matching for Dynamical Systems
Distilled one-step consistency model from optimal-transport flow-matching teacher reconstructs high-fidelity dynamical system flows from low-fidelity data with 12x speedup, half the parameters, and 23.1% better SSIM than scratch-trained baselines.
-
Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation
By requiring and using highly discriminative LLM text features, the work enables the first effective one-step text-conditioned image generation with MeanFlow.
-
Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency
The work introduces rCM, a score-regularized continuous-time consistency model that matches DMD2 quality on large models up to 14B parameters while improving diversity and enabling 1-4 step sampling.
-
R3D2: Realistic 3D Asset Insertion via Diffusion for Autonomous Driving Simulation
R3D2 trains a lightweight diffusion model on synthetic placements of 3DGS-generated assets to produce photorealistic insertions with consistent illumination into autonomous driving scenes.
-
Reward-Aware Trajectory Shaping for Few-step Visual Generation
RATS lets few-step visual generators surpass multi-step teachers by shaping trajectories with reward-based adaptive guidance instead of strict imitation.
-
Woosh: A Sound Effects Foundation Model
Woosh is a new publicly released foundation model optimized for high-quality sound effect generation from text or video, showing competitive or better results than open alternatives like Stable Audio Open.
-
Stabilizing, Scaling & Enhancing MeanFlow for Large-scale Diffusion Distillation
Stabilizes MeanFlow for large-scale diffusion distillation via discrete warm-up and trajectory alignment, reporting better results on FLUX.1-dev and HunyuanImage 3.0.