paper-with-me

홈 › Papers

Stabilizing Consistency Training: A Flow Map Analysis and Self-Distillation

2026-01-30 · Youngjoong Kim, Duhoe Kim, Woosung Kim, Jaesik Park arxiv

Consistency models have been proposed for fast generative modeling, achieving results competitive with diffusion and flow models. However, these methods exhibit inherent instability and limited reproducibility when training from scratch, motivating subsequent work to explain and stabilize these issues. While these efforts have provided valuable insights, the explanations remain fragmented, and the theoretical relationships remain unclear. In this work, we provide a theoretical examination of consistency models by analyzing them from a flow map-based perspective. This joint analysis clarifies how training stability and convergence behavior can give rise to degenerate solutions. Building on these insights, we revisit self-distillation as a practical remedy for certain forms of suboptimal convergence and reformulate it to avoid excessive gradient norms for stable optimization. We demonstrate that our strategy extends beyond image generation to diffusion-based policy learning, without reliance on pretrained diffusion models for initialization, illustrating its broader applicability.

📄 PDF Abstract BibTeX arXiv:2601.22679

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Similar Papers 제목 키워드 기반

Semantic Granularity Navigation in Image Editing

2026-05-20 · Liangsi Lu, Minzhe Guo, Xuhang Chen, Yang Shi arxiv

Despite the generative capabilities of diffusion and flow models, real-image editing remains constrained by a persistent trade-off between semantic editability and structural fidelity. We trace a primary cause of this li…

Image Editing

Stability Analysis Framework for Particle-based Distance GANs with Wasserstein Gradient Flow

2023-07-04 · Chuqi Chen, Yue Wu, Yang Xiang

In this paper, we investigate the training process of generative networks that use a type of probability density distance named particle-based distance as the objective function, e.g. MMD GAN, Cram\'er GAN, EIEG GAN. How…

AnchorFlow: Training-Free 3D Editing via Latent Anchor-Aligned Flows

2025-11-27 · Zhenglin Zhou, Fan Ma, Chengzhuo Gui, Xiaobo Xia 외 arxiv

Training-free 3D editing aims to modify 3D shapes based on human instructions without model finetuning. It plays a crucial role in 3D content creation. However, existing approaches often struggle to produce strong or geo…

Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers

2025-10-13 · Wenhan Ma, Hailin Zhang, Liang Zhao, Yifan Song 외 arxiv

Reinforcement learning (RL) has emerged as a crucial approach for enhancing the capabilities of large language models. However, in Mixture-of-Experts (MoE) models, the routing mechanism often introduces instability, even…

Reinforcement Learning

Test-Time Self-Adaptive Conditioning for Stable Audio-Driven Talking-Head Generation

2026-05-25 · Zhicheng Zhang, Lei Wang, Yu Zhang, Yongsheng Gao arxiv

Audio-driven talking-head generation has achieved remarkable progress with recent models such as AniTalker, FLOAT, and Sonic. Despite their success, most existing approaches rely on a single static reference image to con…

Video Generation