Imagen de Portada

Flow-OPD: On-Policy Distillation for Flow Matching Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Fang, Zhen, Huang, Wenxuan, Zeng, Yu, Zhao, Yiming, Chen, Shuang, Feng, Kaituo, Lin, Yunlong, Chen, Lin, Chen, Zehui, Cao, Shaosheng, Zhao, Feng
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Models
por: Huang, Wenxuan, et al.
Publicado: (2026)

OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents
por: Chen, Shuang, et al.
Publicado: (2026)

Vision-DeepResearch Benchmark: Rethinking Visual and Textual Search for Multimodal Large Language Models
por: Zeng, Yu, et al.
Publicado: (2026)

VCR-Bench: A Comprehensive Evaluation Framework for Video Chain-of-Thought Reasoning
por: Qi, Yukun, et al.
Publicado: (2025)

DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models
por: Li, Quanhao, et al.
Publicado: (2026)

UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision
por: Han, Ruiyan, et al.
Publicado: (2026)

Flow Distillation Sampling: Regularizing 3D Gaussians with Pre-trained Matching Priors
por: Chen, Lin-Zhuo, et al.
Publicado: (2025)

SuperFlow: Training Flow Matching Models with RL on the Fly
por: Chen, Kaijie, et al.
Publicado: (2025)

DualVLA: Building a Generalizable Embodied Agent via Partial Decoupling of Reasoning and Action
por: Fang, Zhen, et al.
Publicado: (2025)

RAW-Flow: Advancing RGB-to-RAW Image Reconstruction with Deterministic Latent Flow Matching
por: Liu, Zhen, et al.
Publicado: (2026)

VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation
por: Zhao, Yiming, et al.
Publicado: (2026)

SCOPE: Structured Decomposition and Conditional Skill Orchestration for Complex Image Generation
por: Ren, Tianfei, et al.
Publicado: (2026)

Towards Fine-grained Large Object Segmentation 1st Place Solution to 3D AI Challenge 2020 -- Instance Segmentation Track
por: Chen, Zehui, et al.
Publicado: (2020)

The Coupling Within: Flow Matching via Distilled Normalizing Flows
por: Berthelot, David, et al.
Publicado: (2026)

Laplacian Multi-scale Flow Matching for Generative Modeling
por: Zhao, Zelin, et al.
Publicado: (2026)

Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching
por: Liu, Enshu, et al.
Publicado: (2024)

Coefficients-Preserving Sampling for Reinforcement Learning with Flow Matching
por: Wang, Feng, et al.
Publicado: (2025)

Gen-Searcher: Reinforcing Agentic Search for Image Generation
por: Feng, Kaituo, et al.
Publicado: (2026)

V2P-Bench: Evaluating Video-Language Understanding with Visual Prompts for Better Human-Model Interaction
por: Zhao, Yiming, et al.
Publicado: (2025)

Beyond Optimal Transport: Model-Aligned Coupling for Flow Matching
por: Lin, Yexiong, et al.
Publicado: (2025)

Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation
por: Yuan, Qianhao, et al.
Publicado: (2026)

DFM-VLA: Iterative Action Refinement for Robot Manipulation via Discrete Flow Matching
por: Chen, Jiayi, et al.
Publicado: (2026)

OP-GRPO: Efficient Off-Policy GRPO for Flow-Matching Models
por: Zhang, Liyu, et al.
Publicado: (2026)

VITA: Vision-to-Action Flow Matching Policy
por: Gao, Dechen, et al.
Publicado: (2025)

Score Distillation of Flow Matching Models
por: Zhou, Mingyuan, et al.
Publicado: (2025)

AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation
por: Gu, Yuchao, et al.
Publicado: (2026)

CurveFlow: Curvature-Guided Flow Matching for Image Generation
por: Luo, Yan, et al.
Publicado: (2025)

Adversarial Flow Models
por: Lin, Shanchuan, et al.
Publicado: (2025)

SnapFlow: One-Step Action Generation for Flow-Matching VLAs via Progressive Self-Distillation
por: Luan, Wuyang, et al.
Publicado: (2026)

Point-DETR3D: Leveraging Imagery Data with Spatial Point Prior for Weakly Semi-supervised 3D Object Detection
por: Gao, Hongzhi, et al.
Publicado: (2024)

Flow Mismatching: Unsupervised Anomaly Detection via Velocity Discrepancies in Flow Matching Models
por: Chen, Shengzhe, et al.
Publicado: (2026)

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning
por: Wang, Qiuchen, et al.
Publicado: (2025)

FlowComposer: Composable Flows for Compositional Zero-Shot Learning
por: He, Zhenqi, et al.
Publicado: (2026)

SenseFlow: Scaling Distribution Matching for Flow-based Text-to-Image Distillation
por: Ge, Xingtong, et al.
Publicado: (2025)

FREPix: Frequency-Heterogeneous Flow Matching for Pixel-Space Image Generation
por: Lin, Mingfeng, et al.
Publicado: (2026)

Are We on the Right Way for Evaluating Large Vision-Language Models?
por: Chen, Lin, et al.
Publicado: (2024)

Continuous Adversarial Flow Models
por: Lin, Shanchuan, et al.
Publicado: (2026)

Video-OPD: Efficient Post-Training of Multimodal Large Language Models for Temporal Video Grounding via On-Policy Distillation
por: Li, Jiaze, et al.
Publicado: (2026)

FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching
por: Ren, Sucheng, et al.
Publicado: (2024)

Leveraging Diffusion Model and Image Foundation Model for Improved Correspondence Matching in Coronary Angiography
por: Zhao, Lin, et al.
Publicado: (2025)