Copertina

Principled RL for Flow Matching Emerges from the Chunk-level Policy Optimization

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Luo, Yifu, Sun, Haoyuan, Hu, Xinhao, Du, Penghui, Fan, Keyu, Li, Bo, Du, Sinan, Wan, Xu, Chen, Zhiyu, Xia, Bo, Zhang, Tiantian, Chang, Yongzhe, Yu, Changqian, Gai, Kun, Wang, Xueqian
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Reinforcement Learning Meets Masked Generative Models: Mask-GRPO for Text-to-Image Generation
di: Luo, Yifu, et al.
Pubblicazione: (2025)

Generalizing Alignment Paradigm of Text-to-Image Generation with Preferences through $f$-divergence Minimization
di: Sun, Haoyuan, et al.
Pubblicazione: (2024)

A Method on Searching Better Activation Functions
di: Sun, Haoyuan, et al.
Pubblicazione: (2024)

Wavelet Fourier Diffuser: Frequency-Aware Diffusion Model for Reinforcement Learning
di: Luo, Yifu, et al.
Pubblicazione: (2025)

Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models
di: Sun, Haoyuan, et al.
Pubblicazione: (2025)

DEER: A Delay-Resilient Framework for Reinforcement Learning with Variable Delays
di: Xia, Bo, et al.
Pubblicazione: (2024)

UACER: An Uncertainty-Adaptive Critic Ensemble Framework for Robust Adversarial Reinforcement Learning
di: Wu, Jiaxi, et al.
Pubblicazione: (2025)

Embodied Co-Design for Rapidly Evolving Agents: Taxonomy, Frontiers, and Challenges
di: Wang, Yuxing, et al.
Pubblicazione: (2025)

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

Go Beyond Black-box Policies: Rethinking the Design of Learning Agent for Interpretable and Verifiable HVAC Control
di: An, Zhiyu, et al.
Pubblicazione: (2024)

IS-Diff: Improving Diffusion-Based Inpainting with Better Initial Seed
di: Lyu, Yongzhe, et al.
Pubblicazione: (2025)

SSCFormer: Push the Limit of Chunk-wise Conformer for Streaming ASR Using Sequentially Sampled Chunks and Chunked Causal Convolution
di: Wang, Fangyuan, et al.
Pubblicazione: (2022)

VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstruction
di: Du, Sinan, et al.
Pubblicazione: (2025)

Open Problems in Differentiable Social Choice: Learning Mechanisms, Decisions, and Alignment
di: An, Zhiyu, et al.
Pubblicazione: (2026)

DIML: Differentiable Inverse Mechanism Learning from Behaviors of Multi-Agent Learning Trajectories
di: An, Zhiyu, et al.
Pubblicazione: (2026)

MoralReason: Generalizable Moral Decision Alignment For LLM Agents Using Reasoning-Level Reinforcement Learning
di: An, Zhiyu, et al.
Pubblicazione: (2025)

Representational Homomorphism Predicts and Improves Compositional Generalization In Transformer Language Model
di: An, Zhiyu, et al.
Pubblicazione: (2026)

FocalPolicy: Frequency-Optimized Chunking and Locally Anchored Flow Matching for Coherent Visuomotor Policy
di: He, Qian, et al.
Pubblicazione: (2026)

Generative Modeling with Orbit-Space Particle Flow Matching
di: Wang, Sinan, et al.
Pubblicazione: (2026)

HiChunk: Evaluating and Enhancing Retrieval-Augmented Generation with Hierarchical Chunking
di: Lu, Wensheng, et al.
Pubblicazione: (2025)

Lagrangian Flow Matching: A Least-Action Framework for Principled Path Design
di: Du, Shukai, et al.
Pubblicazione: (2026)

FM-IRL: Flow-Matching for Reward Modeling and Policy Regularization in Reinforcement Learning
di: Wan, Zhenglin, et al.
Pubblicazione: (2025)

Power Reinforcement Post-Training of Text-to-Image Models with Super-Linear Advantage Shaping
di: Sun, Haoyuan, et al.
Pubblicazione: (2026)

FlowRL: A Taxonomy and Modular Framework for Reinforcement Learning with Diffusion Policies
di: Gao, Chenxiao, et al.
Pubblicazione: (2026)

Evolving Diffusion and Flow Matching Policies for Online Reinforcement Learning
di: Zhang, Chubin, et al.
Pubblicazione: (2025)

Differential Voting: Loss Functions For Axiomatically Diverse Aggregation of Heterogeneous Preferences
di: An, Zhiyu, et al.
Pubblicazione: (2026)

Reward Bound for Behavioral Guarantee of Model-based Planning Agents
di: An, Zhiyu, et al.
Pubblicazione: (2024)

Beyond Noisy-TVs: Noise-Robust Exploration Via Learning Progress Monitoring
di: Hou, Zhibo, et al.
Pubblicazione: (2025)

Disentangling Uncertainties by Learning Compressed Data Representation
di: An, Zhiyu, et al.
Pubblicazione: (2025)

When Less Latent Leads to Better Relay: Information-Preserving Compression for Latent Multi-Agent LLM Collaboration
di: Li, Yiping, et al.
Pubblicazione: (2026)

Learning Native Continuation for Action Chunking Flow Policies
di: Liu, Yufeng, et al.
Pubblicazione: (2026)

Real-Time Execution of Action Chunking Flow Policies
di: Black, Kevin, et al.
Pubblicazione: (2025)

PaddingFlow: Improving Normalizing Flows with Padding-Dimensional Noise
di: Meng, Qinglong, et al.
Pubblicazione: (2024)

Emerging Technologies
di: Küfeoğlu, Sinan
Pubblicazione: (2022)

Visual Generation Tuning
di: Guo, Jiahao, et al.
Pubblicazione: (2025)

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

Virtual specialness of the double
di: Li, Changqian
Pubblicazione: (2026)

Finite Stature in Graphs of Cube Complexes with Cyclonormal Edges
di: Li, Changqian
Pubblicazione: (2026)

LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification
di: Yang, Penghui, et al.
Pubblicazione: (2025)

Exploring the Impact of Resistance to AI , Cultural Openness and Collaboration on STEM Teachers' Professional Development: A Structural Equation Modelling Study
di: Bo Sun, et al.
Pubblicazione: (2025)