:: Library Catalog

Copertina

Salvato in:

Dettagli Bibliografici
Autori principali:	Jing, Xuepeng, Lu, Wenhuan, Meng, Hao, Yu, Zhizhi, Wei, Jianguo
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence
Accesso online:	https://arxiv.org/abs/2603.24936
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

DenseGRPO: From Sparse to Dense Reward for Flow Matching Model Alignment
di: Deng, Haoyou, et al.
Pubblicazione: (2026)

You Only Speak Once to See
di: Yang, Wenhao, et al.
Pubblicazione: (2024)

GRPO-Guard: Mitigating Implicit Over-Optimization in Flow Matching via Regulated Clipping
di: Wang, Jing, et al.
Pubblicazione: (2025)

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

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

Smart-GRPO: Smartly Sampling Noise for Efficient RL of Flow-Matching Models
di: Yu, Benjamin, et al.
Pubblicazione: (2025)

Stepwise Credit Assignment for GRPO on Flow-Matching Models
di: Savani, Yash, et al.
Pubblicazione: (2026)

FlowCast: Trajectory Forecasting for Scalable Zero-Cost Speculative Flow Matching
di: Bajpai, Divya Jyoti, et al.
Pubblicazione: (2026)

Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning
di: Wang, Yibin, et al.
Pubblicazione: (2025)

Multi-GRPO: Multi-Group Advantage Estimation for Text-to-Image Generation with Tree-Based Trajectories and Multiple Rewards
di: Lyu, Qiang, et al.
Pubblicazione: (2025)

DiverseGRPO: Mitigating Mode Collapse in Image Generation via Diversity-Aware GRPO
di: Liu, Henglin, et al.
Pubblicazione: (2025)

EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO
di: Guan, Wei, et al.
Pubblicazione: (2025)

TempFlow-GRPO: When Timing Matters for GRPO in Flow Models
di: He, Xiaoxuan, et al.
Pubblicazione: (2025)

Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO
di: Tong, Yunze, et al.
Pubblicazione: (2026)

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

SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization
di: Rong, Xuankun, et al.
Pubblicazione: (2025)

GuideFlow: Constraint-Guided Flow Matching for Planning in End-to-End Autonomous Driving
di: Liu, Lin, et al.
Pubblicazione: (2025)

Accelerating Rectified Flow Models via Trajectory-Aware Caching
di: Liu, Xiao, et al.
Pubblicazione: (2026)

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

DanceGRPO: Unleashing GRPO on Visual Generation
di: Xue, Zeyue, et al.
Pubblicazione: (2025)

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

MedLoc-R1: Performance-Aware Curriculum Reward Scheduling for GRPO-Based Medical Visual Grounding
di: Yang, Guangjing, et al.
Pubblicazione: (2026)

Identity-GRPO: Optimizing Multi-Human Identity-preserving Video Generation via Reinforcement Learning
di: Meng, Xiangyu, et al.
Pubblicazione: (2025)

Rethinking Reward Signals in Video GRPO: When Scores Become Targets
di: Li, Rui, et al.
Pubblicazione: (2025)

CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching
di: Chen, Chen, et al.
Pubblicazione: (2025)

Robust Dataset Distillation by Matching Adversarial Trajectories
di: Lai, Wei, et al.
Pubblicazione: (2025)

From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space
di: Bu, Jiazi, et al.
Pubblicazione: (2026)

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

Flow Priors for Linear Inverse Problems via Iterative Corrupted Trajectory Matching
di: Zhang, Yasi, et al.
Pubblicazione: (2024)

Reward-Aware Trajectory Shaping for Few-step Visual Generation
di: Li, Rui, et al.
Pubblicazione: (2026)

MAR-GRPO: Stabilized GRPO for AR-diffusion Hybrid Image Generation
di: Ma, Xiaoxiao, et al.
Pubblicazione: (2026)

Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation
di: Lu, Yunhong, et al.
Pubblicazione: (2025)

MotionGRPO: Overcoming Low Intra-Group Diversity in GRPO-Based Egocentric Motion Recovery
di: Yao, Nanjie, et al.
Pubblicazione: (2026)

Image Aesthetic Reasoning via HCM-GRPO: Empowering Compact Model for Superior Performance
di: Hu, Zhiyuan, et al.
Pubblicazione: (2025)

MoFlow: One-Step Flow Matching for Human Trajectory Forecasting via Implicit Maximum Likelihood Estimation based Distillation
di: Fu, Yuxiang, et al.
Pubblicazione: (2025)

GoalFlow: Goal-Driven Flow Matching for Multimodal Trajectories Generation in End-to-End Autonomous Driving
di: Xing, Zebin, et al.
Pubblicazione: (2025)

Training-Free Reward-Guided Image Editing via Trajectory Optimal Control
di: Chang, Jinho, et al.
Pubblicazione: (2025)

Geometry-Aware Image Flow Matching
di: Lee, Junho, et al.
Pubblicazione: (2026)

Neighbor GRPO: Contrastive ODE Policy Optimization Aligns Flow Models
di: He, Dailan, et al.
Pubblicazione: (2025)

Regulating Anatomy-Aware Rewards via Trajectory-Integral Feedback for Volumetric Computed Tomography Analysis
di: Lin, Tianwei, et al.
Pubblicazione: (2026)