Cover Image

MixFlow Training: Alleviating Exposure Bias with Slowed Interpolation Mixture

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Hui, Lyu, Jiayue, Wang, Fu-Yun, Cheng, Kaihui, Zhu, Siyu, Wang, Jingdong
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ReflexFlow: Rethinking Learning Objective for Exposure Bias Alleviation in Flow Matching
by: Huang, Guanbo, et al.
Published: (2025)

MixFlow: Mixed Source Distributions Improve Rectified Flows
by: Nayal, Nazir, et al.
Published: (2026)

Prompt Reinjection: Alleviating Prompt Forgetting in Multimodal Diffusion Transformers
by: Yao, Yuxuan, et al.
Published: (2026)

Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation
by: Cui, Jiahao, et al.
Published: (2024)

Pyramidal Patchification Flow for Visual Generation
by: Li, Hui, et al.
Published: (2025)

OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation
by: Li, Hui, et al.
Published: (2024)

Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer
by: Cui, Jiahao, et al.
Published: (2024)

MoLE: Enhancing Human-centric Text-to-image Diffusion via Mixture of Low-rank Experts
by: Zhu, Jie, et al.
Published: (2024)

Seeing Fast and Slow: Learning the Flow of Time in Videos
by: Wu, Yen-Siang, et al.
Published: (2026)

Training-Free Unsupervised Prompt for Vision-Language Models
by: Long, Sifan, et al.
Published: (2024)

Region-Aware Exposure Consistency Network for Mixed Exposure Correction
by: Liu, Jin, et al.
Published: (2024)

BAMI: Training-Free Bias Mitigation in GUI Grounding
by: Zhang, Borui, et al.
Published: (2026)

Unified-EGformer: Exposure Guided Lightweight Transformer for Mixed-Exposure Image Enhancement
by: Adhikarla, Eashan, et al.
Published: (2024)

Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps
by: Li, Mingxiao, et al.
Published: (2023)

MS-DETR: Efficient DETR Training with Mixed Supervision
by: Zhao, Chuyang, et al.
Published: (2024)

Head-wise Adaptive Rotary Positional Encoding for Fine-Grained Image Generation
by: Li, Jiaye, et al.
Published: (2025)

SlotMemory: Object-Centric KV Memory for Streaming Long-Video Generation
by: Dou, Weijia, et al.
Published: (2026)

Parameter Interpolation Adversarial Training for Robust Image Classification
by: Liu, Xin, et al.
Published: (2025)

Elucidating the Exposure Bias in Diffusion Models
by: Ning, Mang, et al.
Published: (2023)

ReMix: Training Generalized Person Re-identification on a Mixture of Data
by: Mamedov, Timur, et al.
Published: (2024)

MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE
by: Li, Junzhe, et al.
Published: (2025)

SHIELD: Suppressing Hallucinations In LVLM Encoders via Bias and Vulnerability Defense
by: Huang, Yiyang, et al.
Published: (2025)

The Thinking Pixel: Recursive Sparse Reasoning in Multimodal Diffusion Latents
by: Sun, Yuwei, et al.
Published: (2026)

Unmasking Bias in Diffusion Model Training
by: Yu, Hu, et al.
Published: (2023)

Med-UniC: Unifying Cross-Lingual Medical Vision-Language Pre-Training by Diminishing Bias
by: Wan, Zhongwei, et al.
Published: (2023)

VidLBEval: Benchmarking and Mitigating Language Bias in Video-Involved LVLMs
by: Yang, Yiming, et al.
Published: (2025)

AID: Attention Interpolation of Text-to-Image Diffusion
by: He, Qiyuan, et al.
Published: (2024)

Towards Unified Multi-granularity Text Detection with Interactive Attention
by: Wan, Xingyu, et al.
Published: (2024)

Towards Low-Latency Event Stream-based Visual Object Tracking: A Slow-Fast Approach
by: Wang, Shiao, et al.
Published: (2025)

Flow-GRPO: Training Flow Matching Models via Online RL
by: Liu, Jie, et al.
Published: (2025)

Bi-Anchor Interpolation Solver for Accelerating Generative Modeling
by: Chen, Hongxu, et al.
Published: (2026)

Mitigating Gender Bias in Face Recognition Using the von Mises-Fisher Mixture Model
by: Conti, Jean-Rémy, et al.
Published: (2022)

TriCLIP-3D: A Unified Parameter-Efficient Framework for Tri-Modal 3D Visual Grounding based on CLIP
by: Li, Fan, et al.
Published: (2025)

Animate Your Thoughts: Decoupled Reconstruction of Dynamic Natural Vision from Slow Brain Activity
by: Lu, Yizhuo, et al.
Published: (2024)

D-CoDe: Scaling Image-Pretrained VLMs to Video via Dynamic Compression and Question Decomposition
by: Huang, Yiyang, et al.
Published: (2025)

VFIMamba: Video Frame Interpolation with State Space Models
by: Zhang, Guozhen, et al.
Published: (2024)

CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet Upcycling
by: Zhang, Jihai, et al.
Published: (2024)

Composed Vision-Language Retrieval for Skin Cancer Case Search via Joint Alignment of Global and Local Representations
by: Wang, Yuheng, et al.
Published: (2026)

BiasEdit: A Training-Free Bias-Detect-and-Edit Framework for Learning Fair Visual Classifiers
by: Seo, Jungwook, et al.
Published: (2026)

ViTime: Foundation Model for Time Series Forecasting Powered by Vision Intelligence
by: Yang, Luoxiao, et al.
Published: (2024)