Image de couverture de livre

Euphonium: Steering Video Flow Matching via Process Reward Gradient Guided Stochastic Dynamics

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhong, Ruizhe, Lian, Jiesong, Mi, Xiaoyue, Zhou, Zixiang, Zhou, Yuan, Lu, Qinglin, Yan, Junchi
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

SoliReward: Mitigating Susceptibility to Reward Hacking and Annotation Noise in Video Generation Reward Models
par: Lian, Jiesong, et autres
Publié: (2025)

Video Generation Models Are Good Latent Reward Models
par: Mi, Xiaoyue, et autres
Publié: (2025)

SARA: Semantically Adaptive Relational Alignment for Video Diffusion Models
par: Lian, Jiesong, et autres
Publié: (2026)

RulePlanner: All-in-One Reinforcement Learner for Unifying Design Rules in 3D Floorplanning
par: Zhong, Ruizhe, et autres
Publié: (2026)

UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactions
par: Zhang, Guozhen, et autres
Publié: (2025)

HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation for Multiple Characters
par: Chen, Yi, et autres
Publié: (2025)

Stochastic Process Learning via Operator Flow Matching
par: Shi, Yaozhong, et autres
Publié: (2025)

USV: Unified Sparsification for Accelerating Video Diffusion Models
par: Wu, Xinjian, et autres
Publié: (2025)

TIGFlow-GRPO: Trajectory Forecasting via Interaction-Aware Flow Matching and Reward-Guided Optimization
par: Jing, Xuepeng, et autres
Publié: (2026)

Stabilizing Policy Gradients for Stochastic Differential Equations via Consistency with Perturbation Process
par: Zhou, Xiangxin, et autres
Publié: (2024)

Policy-DRIFT: Dynamic Reward-Informed Flow Trajectory Steering
par: Mahajan, Atharva, et autres
Publié: (2026)

Matching the Statistical Query Lower Bound for $k$-Sparse Parity Problems with Sign Stochastic Gradient Descent
par: Kou, Yiwen, et autres
Publié: (2024)

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering
par: Li, Yichen, et autres
Publié: (2025)

FlowErase-RL: Rethinking Concept Erasure as Reward Optimization in Flow Matching Models
par: Sun, Yi, et autres
Publié: (2026)

Audio-visual Controlled Video Diffusion with Masked Selective State Spaces Modeling for Natural Talking Head Generation
par: Hong, Fa-Ting, et autres
Publié: (2025)

On uniformly quasiconformal Anosov diffeomorphisms with two dimensional distributions
par: Zhang, Jiesong
Publié: (2023)

Flow Diverse and Efficient: Learning Momentum Flow Matching via Stochastic Velocity Field Sampling
par: Ma, Zhiyuan, et autres
Publié: (2025)

OmniV2V: Versatile Video Generation and Editing via Dynamic Content Manipulation
par: Liang, Sen, et autres
Publié: (2025)

Video Diffusion Alignment via Reward Gradients
par: Prabhudesai, Mihir, et autres
Publié: (2024)

STRIDE: Structured Lagrangian and Stochastic Residual Dynamics via Flow Matching
par: Kotecha, Prakrut, et autres
Publié: (2026)

Arbitrary Generative Video Interpolation
par: Zhang, Guozhen, et autres
Publié: (2025)

PreRoutGNN for Timing Prediction with Order Preserving Partition: Global Circuit Pre-training, Local Delay Learning and Attentional Cell Modeling
par: Zhong, Ruizhe, et autres
Publié: (2024)

Online $b$-Matching with Stochastic Rewards
par: Albers, Susanne, et autres
Publié: (2024)

HunyuanVideo-HOMA: Generic Human-Object Interaction in Multimodal Driven Human Animation
par: Huang, Ziyao, et autres
Publié: (2025)

Can LLMs Guide Their Own Exploration? Gradient-Guided Reinforcement Learning for LLM Reasoning
par: Liang, Zhenwen, et autres
Publié: (2025)

HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation
par: Hu, Teng, et autres
Publié: (2025)

Flow Matching: Markov Kernels, Stochastic Processes and Transport Plans
par: Wald, Christian, et autres
Publié: (2025)

Process Reward Agents for Steering Knowledge-Intensive Reasoning
par: Sohn, Jiwoong, et autres
Publié: (2026)

PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and Enhancement
par: Hu, Teng, et autres
Publié: (2025)

Bounded cohomology of diffeomorphism groups of higher dimensional spheres
par: Zhou, Zixiang
Publié: (2024)

MuSteerNet: Human Reaction Generation from Videos via Observation-Reaction Mutual Steering
par: Zhou, Yuan, et autres
Publié: (2026)

Pack and Force Your Memory: Long-form and Consistent Video Generation
par: Wu, Xiaofei, et autres
Publié: (2025)

When Stochastic Rewards Reduce to Deterministic Rewards in Online Bipartite Matching
par: Udwani, Rajan
Publié: (2023)

New Evidence of the Two-Phase Learning Dynamics of Neural Networks
par: Zhou, Zhanpeng, et autres
Publié: (2025)

Steering Large Reasoning Models towards Concise Reasoning via Flow Matching
par: Li, Yawei, et autres
Publié: (2026)

FlowRL: Matching Reward Distributions for LLM Reasoning
par: Zhu, Xuekai, et autres
Publié: (2025)

Dynamic Transition from Branched Flow of Light to Beam Steering in Disordered Nematic Liquid Crystal
par: Xiao Yu, et autres
Publié: (2024)

Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation
par: Lu, Yunhong, et autres
Publié: (2025)

Generalized Einstein-Podolsky-Rosen Steering Paradox
par: Liu, Zhi-Jie, et autres
Publié: (2024)

Flow Matching Policy Gradients
par: McAllister, David, et autres
Publié: (2025)