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.
Scaling rectified flow transformers for high-resolution image synthesis
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
method 2
citation-polarity summary
fields
cs.CV 7roles
method 2polarities
use method 2representative citing papers
Edit-R1 builds a CoT-based reasoning reward model (RRM) via SFT and GCPO, then applies it with GRPO to improve image editing models such as FLUX.1-kontext.
Seedance 1.5 pro is a joint audio-visual generation model achieving high synchronization via dual-branch diffusion transformer and post-training optimizations.
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.
A post-adaptation pipeline on 3D foundation models yields higher-fidelity, faster, animation-ready single-image 3D characters than prior open methods on reported benchmarks.
Seedance 1.0 generates 5-second 1080p videos in about 41 seconds with claimed superior motion quality, prompt adherence, and multi-shot consistency compared to prior models.
This review organizes literature on large multimodal models and object-centric vision into four themes—understanding, referring segmentation, editing, and generation—while summarizing paradigms, strategies, and challenges like instance permanence and consistent interaction.
citing papers explorer
-
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.
-
Leveraging Verifier-Based Reinforcement Learning in Image Editing
Edit-R1 builds a CoT-based reasoning reward model (RRM) via SFT and GCPO, then applies it with GRPO to improve image editing models such as FLUX.1-kontext.
-
Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Model
Seedance 1.5 pro is a joint audio-visual generation model achieving high synchronization via dual-branch diffusion transformer and post-training optimizations.
-
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.
-
DreamCharacter-1: From 3D Generative Foundation Models to Product-Ready Character Generation
A post-adaptation pipeline on 3D foundation models yields higher-fidelity, faster, animation-ready single-image 3D characters than prior open methods on reported benchmarks.
-
Seedance 1.0: Exploring the Boundaries of Video Generation Models
Seedance 1.0 generates 5-second 1080p videos in about 41 seconds with claimed superior motion quality, prompt adherence, and multi-shot consistency compared to prior models.
-
LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation
This review organizes literature on large multimodal models and object-centric vision into four themes—understanding, referring segmentation, editing, and generation—while summarizing paradigms, strategies, and challenges like instance permanence and consistent interaction.