Cover Image

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Shih-Yang, Dong, Xin, Lu, Ximing, Diao, Shizhe, Belcak, Peter, Liu, Mingjie, Chen, Min-Hung, Yin, Hongxu, Wang, Yu-Chiang Frank, Cheng, Kwang-Ting, Choi, Yejin, Kautz, Jan, Molchanov, Pavlo
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token via Reinforcement Learning
by: Liu, Shih-Yang, et al.
Published: (2025)

BroRL: Scaling Reinforcement Learning via Broadened Exploration
by: Hu, Jian, et al.
Published: (2025)

GDPO-Listener: Expressive Interactive Head Generation via Auto-Regressive Flow Matching and Group reward-Decoupled Policy Optimization
by: Jin, Zhangyu, et al.
Published: (2026)

ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
by: Liu, Mingjie, et al.
Published: (2025)

ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration
by: Su, Hongjin, et al.
Published: (2025)

Universal Deep Research: Bring Your Own Model and Strategy
by: Belcak, Peter, et al.
Published: (2025)

Minifinetuning: Low-Data Generation Domain Adaptation through Corrective Self-Distillation
by: Belcak, Peter, et al.
Published: (2025)

ProfBench: Multi-Domain Rubrics requiring Professional Knowledge to Answer and Judge
by: Wang, Zhilin, et al.
Published: (2025)

Agent Explorative Policy Optimization for Multimodal Agentic Reasoning
by: Kang, Minki, et al.
Published: (2026)

DoRA: Weight-Decomposed Low-Rank Adaptation
by: Liu, Shih-Yang, et al.
Published: (2024)

Small Language Models are the Future of Agentic AI
by: Belcak, Peter, et al.
Published: (2025)

Semantic segmentation with reward
by: Ting, Xie, et al.
Published: (2025)

Nemotron-CLIMB: CLustering-based Iterative Data Mixture Bootstrapping for Language Model Pre-training
by: Diao, Shizhe, et al.
Published: (2025)

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training
by: Liu, Mingjie, et al.
Published: (2025)

ProRL Agent: Rollout-as-a-Service for RL Training of Multi-Turn LLM Agents
by: Zhang, Hao, et al.
Published: (2026)

Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention
by: Hatamizadeh, Ali, et al.
Published: (2026)

MetaGDPO: Alleviating Catastrophic Forgetting with Metacognitive Knowledge through Group Direct Preference Optimization
by: Zhang, Lanxue, et al.
Published: (2025)

DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning
by: Jiang, Guochao, et al.
Published: (2026)

Scaling RL to Long Videos
by: Chen, Yukang, et al.
Published: (2025)

LITA: Language Instructed Temporal-Localization Assistant
by: Huang, De-An, et al.
Published: (2024)

Flextron: Many-in-One Flexible Large Language Model
by: Cai, Ruisi, et al.
Published: (2024)

REC-RL: Referring expression counting via Gaussian and range-based reward optimization
by: Liu, Hui, et al.
Published: (2026)

Autonomous state-space segmentation for Deep-RL sparse reward scenarios
by: Maselli, Gianluca, et al.
Published: (2025)

Just Say What You Want: Only-prompting Self-rewarding Online Preference Optimization
by: Xu, Ruijie, et al.
Published: (2024)

EoRA: Fine-tuning-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation
by: Liu, Shih-Yang, et al.
Published: (2024)

AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One
by: Ranzinger, Mike, et al.
Published: (2023)

FasterViT: Fast Vision Transformers with Hierarchical Attention
by: Hatamizadeh, Ali, et al.
Published: (2023)

Polar: Agentic RL on Any Harness at Scale
by: Xu, Binfeng, et al.
Published: (2026)

TractOracle: towards an anatomically-informed reward function for RL-based tractography
by: Théberge, Antoine, et al.
Published: (2024)

Hymba: A Hybrid-head Architecture for Small Language Models
by: Dong, Xin, et al.
Published: (2024)

GDPO-SR: Group Direct Preference Optimization for One-Step Generative Image Super-Resolution
by: Yi, Qiaosi, et al.
Published: (2026)

LIRE: listwise reward enhancement for preference alignment
by: Zhu, Mingye, et al.
Published: (2024)

Credit card rewards counterpoint
by: Aaron Klein, et al.
Published: (2025)

Science and technology. virtue rewarded
Published: (2002)

Discounting of shared rewards in pigeons
by: Tetsuo Yamaguchi
Published: (2019)

LongMamba: Enhancing Mamba's Long Context Capabilities via Training-Free Receptive Field Enlargement
by: Ye, Zhifan, et al.
Published: (2025)

Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text
by: Lu, Ximing, et al.
Published: (2026)

Episodic Reinforcement Learning with Expanded State-reward Space
by: Liang, Dayang, et al.
Published: (2024)

Adaptive Sharpness-Aware Pruning for Robust Sparse Networks
by: Bair, Anna, et al.
Published: (2023)

RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models
by: Heinrich, Greg, et al.
Published: (2024)