Cover Image

Rethinking Test Time Scaling for Flow-Matching Generative Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yu, Qingtao, Song, Changlin, Sun, Minghao, Yu, Zhengyang, Verma, Vinay Kumar, Roy, Soumya, Negi, Sumit, Li, Hongdong, Campbell, Dylan
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

TaTToo: Tool-Grounded Thinking PRM for Test-Time Scaling in Tabular Reasoning
by: Zou, Jiaru, et al.
Published: (2025)

ADROIT: A Self-Supervised Framework for Learning Robust Representations for Active Learning
by: Banerjee, Soumya, et al.
Published: (2025)

Rethinking Dense Optical Flow without Test-Time Scaling
by: Chanda, Praroop, et al.
Published: (2026)

Probability Density Geodesics in Image Diffusion Latent Space
by: Yu, Qingtao, et al.
Published: (2025)

FastFlow: Accelerating The Generative Flow Matching Models with Bandit Inference
by: Bajpai, Divya Jyoti, et al.
Published: (2026)

NOVO: Unlearning-Compliant Vision Transformers
by: Roy, Soumya, et al.
Published: (2025)

BiFM: Bidirectional Flow Matching for Few-Step Image Editing and Generation
by: Dai, Yasong, et al.
Published: (2026)

Flow Generator Matching
by: Huang, Zemin, et al.
Published: (2024)

Extreme Amodal Face Detection
by: Song, Changlin, et al.
Published: (2025)

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

AutoRefiner: Improving Autoregressive Video Diffusion Models via Reflective Refinement Over the Stochastic Sampling Path
by: Yu, Zhengyang, et al.
Published: (2025)

Tuning Real-World Image Restoration at Inference: A Test-Time Scaling Paradigm for Flow Matching Models
by: Bai, Purui, et al.
Published: (2026)

FlowErase-RL: Rethinking Concept Erasure as Reward Optimization in Flow Matching Models
by: Sun, Yi, et al.
Published: (2026)

Best of Both Worlds: Hybrid SNN-ANN Architecture for Event-based Optical Flow Estimation
by: Negi, Shubham, et al.
Published: (2023)

VERSE: Virtual-Gradient Aware Streaming Lifelong Learning with Anytime Inference
by: Banerjee, Soumya, et al.
Published: (2023)

Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning
by: Wang, Ziyang, et al.
Published: (2025)

Uncertainty-Aware Vision-Language Segmentation for Medical Imaging
by: Das, Aryan, et al.
Published: (2026)

Efficient Text-Guided Convolutional Adapter for the Diffusion Model
by: Das, Aryan, et al.
Published: (2026)

Flow Matching Posterior Sampling: A Training-free Conditional Generation for Flow Matching
by: Song, Kaiyu, et al.
Published: (2024)

FOCUS: Forcing In-Context Object Localization through Visual Support Constraints and Policy Optimization
by: Karim, Mohammed Asad, et al.
Published: (2026)

Reliable or Deceptive? Investigating Gated Features for Smooth Visual Explanations in CNNs
by: Mitra, Soham, et al.
Published: (2024)

IMPUS: Image Morphing with Perceptually-Uniform Sampling Using Diffusion Models
by: Yang, Zhaoyuan, et al.
Published: (2023)

Flow Matching-enabled Test-Time Refinement for Unsupervised Cardiac MR Registration
by: Fu, Yunguan, et al.
Published: (2026)

UniFlowRestore: A General Video Restoration Framework via Flow Matching and Prompt Guidance
by: Sun, Shuning, et al.
Published: (2025)

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

RISSOLE: Parameter-efficient Diffusion Models via Block-wise Generation and Retrieval-Guidance
by: Mukherjee, Avideep, et al.
Published: (2024)

Rethinking Polyp Segmentation from an Out-of-Distribution Perspective
by: Ji, Ge-Peng, et al.
Published: (2023)

Multi-Scale Generative Modeling with Heat Dissipation Flow Matching
by: Ma, Jun, et al.
Published: (2026)

Refracting Reality: Generating Images with Realistic Transparent Objects
by: Yin, Yue, et al.
Published: (2025)

PADS: Plug-and-Play 3D Human Pose Analysis via Diffusion Generative Modeling
by: Ji, Haorui, et al.
Published: (2024)

Frequency-Aware Flow Matching for High-Quality Image Generation
by: Ren, Sucheng, et al.
Published: (2026)

From Contrast to Consistency: Rethinking Event-based Continuous-Time Optical Flow Estimation
by: Hu, Rui, et al.
Published: (2026)

Pyramidal Flow Matching for Efficient Video Generative Modeling
by: Jin, Yang, et al.
Published: (2024)

Beyond Imitation: Constraint-Aware Trajectory Generation with Flow Matching For End-to-End Autonomous Driving
by: Liu, Lin, et al.
Published: (2025)

MoiréXNet: Adaptive Multi-Scale Demoiréing with Linear Attention Test-Time Training and Truncated Flow Matching Prior
by: Li, Liangyan, et al.
Published: (2025)

TrojFlow: Flow Models are Natural Targets for Trojan Attacks
by: Qi, Zhengyang, et al.
Published: (2024)

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

FASTER: Rethinking Real-Time Flow VLAs
by: Lu, Yuxiang, et al.
Published: (2026)

SubFlow: Sub-mode Conditioned Flow Matching for Diverse One-Step Generation
by: Lin, Yexiong, et al.
Published: (2026)

Convolutional Prompting meets Language Models for Continual Learning
by: Roy, Anurag, et al.
Published: (2024)