Image de couverture de livre

Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Lai, Song, Zhao, Haohan, Feng, Rong, Ma, Changyi, Liu, Wenzhuo, Zhao, Hongbo, Lin, Xi, Yi, Dong, Zhang, Qingfu, Liu, Hongbin, Meng, Gaofeng, Zhu, Fei
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Pareto Continual Learning: Preference-Conditioned Learning and Adaption for Dynamic Stability-Plasticity Trade-off
par: Lai, Song, et autres
Publié: (2025)

Practical Continual Forgetting for Pre-trained Vision Models
par: Zhao, Hongbo, et autres
Publié: (2025)

Continual Forgetting for Pre-trained Vision Models
par: Zhao, Hongbo, et autres
Publié: (2024)

Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning
par: Lou, Meng, et autres
Publié: (2026)

VTCBench: Can Vision-Language Models Understand Long Context with Vision-Text Compression?
par: Zhao, Hongbo, et autres
Publié: (2025)

Intent Mismatch Causes LLMs to Get Lost in Multi-Turn Conversation
par: Liu, Geng, et autres
Publié: (2026)

MCITlib: Multimodal Continual Instruction Tuning Library and Benchmark
par: Guo, Haiyang, et autres
Publié: (2025)

Branch-Tuning: Balancing Stability and Plasticity for Continual Self-Supervised Learning
par: Liu, Wenzhuo, et autres
Publié: (2024)

Improved Supervised Fine-Tuning for Large Language Models to Mitigate Catastrophic Forgetting
par: Ding, Fei, et autres
Publié: (2025)

Dynamic Orthogonal Continual Fine-tuning for Mitigating Catastrophic Forgettings
par: Zhang, Zhixin, et autres
Publié: (2025)

CURLoRA: Stable LLM Continual Fine-Tuning and Catastrophic Forgetting Mitigation
par: Fawi, Muhammad
Publié: (2024)

MLLM-CL: Continual Learning for Multimodal Large Language Models
par: Zhao, Hongbo, et autres
Publié: (2025)

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting
par: Sanyal, Sunny, et autres
Publié: (2025)

Mitigating Catastrophic Forgetting with Adaptive Transformer Block Expansion in Federated Fine-Tuning
par: Huo, Yujia, et autres
Publié: (2025)

LLaVA-c: Continual Improved Visual Instruction Tuning
par: Liu, Wenzhuo, et autres
Publié: (2025)

Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning
par: Chen, Liang, et autres
Publié: (2025)

Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting
par: Diao, Muxi, et autres
Publié: (2026)

Fine-tuning Large Language Model for Automated Algorithm Design
par: Liu, Fei, et autres
Publié: (2025)

Spatiotemporal Continual Learning for Mobile Edge UAV Networks: Mitigating Catastrophic Forgetting
par: Lai, Chuan-Chi
Publié: (2026)

Towards Robust LLM Post-Training: Automatic Failure Management for Reinforcement Fine-Tuning
par: Zhang, Lingzhe, et autres
Publié: (2026)

Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning
par: Jiang, Gangwei, et autres
Publié: (2025)

MoFO: Momentum-Filtered Optimizer for Mitigating Forgetting in LLM Fine-Tuning
par: Chen, Yupeng, et autres
Publié: (2024)

Mitigating Forgetting in LLM Fine-Tuning via Low-Perplexity Token Learning
par: Wu, Chao-Chung, et autres
Publié: (2025)

Federated Continual Instruction Tuning
par: Guo, Haiyang, et autres
Publié: (2025)

Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning
par: Du, Yanrui, et autres
Publié: (2024)

L-AutoDA: Leveraging Large Language Models for Automated Decision-based Adversarial Attacks
par: Guo, Ping, et autres
Publié: (2024)

Enhancing Visual Continual Learning with Language-Guided Supervision
par: Ni, Bolin, et autres
Publié: (2024)

PADReg: Physics-Aware Deformable Registration Guided by Contact Force for Ultrasound Sequences
par: Geng, Yimeng, et autres
Publié: (2025)

Mesh-RFT: Enhancing Mesh Generation via Fine-grained Reinforcement Fine-Tuning
par: Liu, Jian, et autres
Publié: (2025)

Balancing Speciality and Versatility: A Coarse to Fine Framework for Mitigating Catastrophic Forgetting in Large Language Models
par: Zhang, Hengyuan, et autres
Publié: (2024)

Global Convergence of Continual Learning on Non-IID Data
par: Zhu, Fei, et autres
Publié: (2025)

Force Sensing Guided Artery-Vein Segmentation via Sequential Ultrasound Images
par: Geng, Yimeng, et autres
Publié: (2024)

Fine-Grained Gradient Restriction: A Simple Approach for Mitigating Catastrophic Forgetting
par: Liu, Bo, et autres
Publié: (2024)

Forget the Data and Fine-Tuning! Just Fold the Network to Compress
par: Wang, Dong, et autres
Publié: (2025)

Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem
par: Wołczyk, Maciej, et autres
Publié: (2024)

Continual Deep Reinforcement Learning to Prevent Catastrophic Forgetting in Jamming Mitigation
par: Davaslioglu, Kemal, et autres
Publié: (2024)

Mitigating Training Imbalance in LLM Fine-Tuning via Selective Parameter Merging
par: Ju, Yiming, et autres
Publié: (2024)

Semi-parametric Memory Consolidation: Towards Brain-like Deep Continual Learning
par: Liu, Geng, et autres
Publié: (2025)

Learn to Memorize and to Forget: A Continual Learning Perspective of Dynamic SLAM
par: Li, Baicheng, et autres
Publié: (2024)

Geometry Conflict: Explaining and Controlling Forgetting in LLM Continual Post-Training
par: Wang, Yuanyi, et autres
Publié: (2026)