Image de couverture de livre

GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Gan, Wangjie, Pan, Miao, Xi, Linbo, Zhang, Wenqi, Chen, Jintao, Yin, Jianwei, Zhang, Xuhong
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Ground What You See: Hallucination-Resistant MLLMs via Caption Feedback, Diversity-Aware Sampling, and Conflict Regularization
par: Pan, Miao, et autres
Publié: (2026)

SCHK-HTC: Sibling Contrastive Learning with Hierarchical Knowledge-Aware Prompt Tuning for Hierarchical Text Classification
par: Xiong, Ke, et autres
Publié: (2026)

From Coarse to Fine: Benchmarking and Reward Modeling for Writing-Centric Generation Tasks
par: Ren, Qingyu, et autres
Publié: (2026)

Unbiased Rectification for Sequential Recommender Systems Under Fake Orders
par: Qin, Qiyu, et autres
Publié: (2026)

GFT: Graph Feature Tuning for Efficient Point Cloud Analysis
par: Dhakal, Manish, et autres
Publié: (2025)

Geometrogenesis in GFT: An Analysis
par: Frauca, Álvaro Mozota
Publié: (2023)

The Trajectory Alignment Coefficient in Two Acts: From Reward Tuning to Reward Learning
par: Muslimani, Calarina, et autres
Publié: (2026)

GFT: Graph Foundation Model with Transferable Tree Vocabulary
par: Wang, Zehong, et autres
Publié: (2024)

GFT: Gradient Focal Transformer
par: Kriuk, Boris, et autres
Publié: (2025)

From Macro to Micro: Probing Dataset Diversity in Language Model Fine-Tuning
par: Li, Haoyu, et autres
Publié: (2025)

ToolGate: Contract-Grounded and Verified Tool Execution for LLMs
par: Liu, Yanming, et autres
Publié: (2026)

RewardDS: Privacy-Preserving Fine-Tuning for Large Language Models via Reward Driven Data Synthesis
par: Wang, Jianwei, et autres
Publié: (2025)

Taming Noise-Induced Prototype Degradation for Privacy-Preserving Personalized Federated Fine-Tuning
par: Wang, Yuhua, et autres
Publié: (2026)

SARE: Sample-wise Adaptive Reasoning for Training-free Fine-grained Visual Recognition
par: Yang, Jingxiao, et autres
Publié: (2026)

SVOM/C-GFT: Instrumentation and Performances on the SVOM Alerts
par: Wu, Chao, et autres
Publié: (2026)

PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts
par: Li, Qinfeng, et autres
Publié: (2026)

IN-RIL: Interleaved Reinforcement and Imitation Learning for Policy Fine-Tuning
par: Gao, Dechen, et autres
Publié: (2025)

Do Not Merge My Model! Safeguarding Open-Source LLMs Against Unauthorized Model Merging
par: Li, Qinfeng, et autres
Publié: (2025)

Noise-corrected GRPO: From Noisy Rewards to Unbiased Gradients
par: Mansouri, Omar El, et autres
Publié: (2025)

Unbiased Dynamic Pruning for Efficient Group-Based Policy Optimization
par: Zhu, Haodong, et autres
Publié: (2026)

Generalized Distributional Alignment Games for Unbiased Answer-Level Fine-Tuning
par: Mohri, Mehryar, et autres
Publié: (2026)

Reinforcement Fine-Tuning for History-Aware Dense Retriever in RAG
par: Zhang, Yicheng, et autres
Publié: (2026)

Towards Steering without Sacrifice: Principled Training of Steering Vectors for Prompt-only Interventions
par: Bao, Yuntai, et autres
Publié: (2026)

Unbiased Dynamic Multimodal Fusion
par: Wei, Shicai, et autres
Publié: (2026)

Valid Survey Simulations with Limited Human Data: The Roles of Prompting, Fine-Tuning, and Rectification
par: Krsteski, Stefan, et autres
Publié: (2025)

Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented Imitation
par: Guo, Yihong, et autres
Publié: (2024)

VERIRL: Boosting the LLM-based Verilog Code Generation via Reinforcement Learning
par: Teng, Fu, et autres
Publié: (2025)

CollabEdit: Towards Non-destructive Collaborative Knowledge Editing
par: Zheng, Jiamu, et autres
Publié: (2024)

UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter-Efficient Fine-Tuning of Large Models
par: Zhang, Xueyan, et autres
Publié: (2025)

Enhancing Large Language Model Reasoning with Reward Models: An Analytical Survey
par: Liu, Qiyuan, et autres
Publié: (2025)

Efficient Inference Using Large Language Models with Limited Human Data: Fine-Tuning then Rectification
par: Wang, Lei, et autres
Publié: (2025)

Faithful Bi-Directional Model Steering via Distribution Matching and Distributed Interchange Interventions
par: Bao, Yuntai, et autres
Publié: (2026)

Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate
par: Wang, Yubo, et autres
Publié: (2025)

COLIBRI (SVOM/FM-GFT): Instrumentation and Performances on the SVOM Alerts
par: Basa, S., et autres
Publié: (2026)

Project-Probe-Aggregate: Efficient Fine-Tuning for Group Robustness
par: Zhu, Beier, et autres
Publié: (2025)

SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning
par: Zhang, Jintao, et autres
Publié: (2026)

Meta-Calibration of the Cosmic Magnification Coefficient: Toward Unbiased Weak Lensing Reconstruction by Counting Galaxies
par: Qin, Jian, et autres
Publié: (2025)

From Imitation to Discrimination: Toward A Generalized Curriculum Advantage Mechanism Enhancing Cross-Domain Reasoning Tasks
par: Yang, Changpeng, et autres
Publié: (2025)

LangGrasp: Leveraging Fine-Tuned LLMs for Language Interactive Robot Grasping with Ambiguous Instructions
par: Lin, Yunhan, et autres
Publié: (2025)

On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification
par: Wu, Yongliang, et autres
Publié: (2025)