Image de couverture de livre

F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Plyusov, Daniil, Gorbatovski, Alexey, Shaposhnikov, Boris, Sinii, Viacheslav, Malakhov, Alexey, Korotyshova, Daria, Gavrilov, Daniil
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Trust-Region Behavior Blending for On-Policy Distillation
par: Plyusov, Daniil, et autres
Publié: (2026)

The Differences Between Direct Alignment Algorithms are a Blur
par: Gorbatovski, Alexey, et autres
Publié: (2025)

Steering LLM Reasoning Through Bias-Only Adaptation
par: Sinii, Viacheslav, et autres
Publié: (2025)

ESSA: Evolutionary Strategies for Scalable Alignment
par: Korotyshova, Daria, et autres
Publié: (2025)

Learn Your Reference Model for Real Good Alignment
par: Gorbatovski, Alexey, et autres
Publié: (2024)

Small Vectors, Big Effects: A Mechanistic Study of RL-Induced Reasoning via Steering Vectors
par: Sinii, Viacheslav, et autres
Publié: (2025)

Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success
par: Bredis, George, et autres
Publié: (2025)

Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization
par: Kachaev, Nikita, et autres
Publié: (2025)

Linear Transformers with Learnable Kernel Functions are Better In-Context Models
par: Aksenov, Yaroslav, et autres
Publié: (2024)

Reinforcement learning for question answering in programming domain using public community scoring as a human feedback
par: Gorbatovski, Alexey, et autres
Publié: (2024)

You Do Not Fully Utilize Transformer's Representation Capacity
par: Gerasimov, Gleb, et autres
Publié: (2025)

Don't Forget Imagination!
par: Vityaev, Evgenii E., et autres
Publié: (2025)

On Efficient Scaling of GNNs via IO-Aware Layers Implementations
par: Fomina, Daria, et autres
Publié: (2026)

Teach Old SAEs New Domain Tricks with Boosting
par: Koriagin, Nikita, et autres
Publié: (2025)

Don't Forget Your Reward Values: Language Model Alignment via Value-based Calibration
par: Mao, Xin, et autres
Publié: (2024)

Next Embedding Prediction Makes World Models Stronger
par: Bredis, George, et autres
Publié: (2026)

Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy
par: Balagansky, Nikita, et autres
Publié: (2025)

Benchmarking is Broken -- Don't Let AI be its Own Judge
par: Cheng, Zerui, et autres
Publié: (2025)

From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments
par: Luo, Lijing, et autres
Publié: (2026)

Don't Forget It! Conditional Sparse Autoencoder Clamping Works for Unlearning
par: Khoriaty, Matthew, et autres
Publié: (2025)

In-Context Reinforcement Learning for Variable Action Spaces
par: Sinii, Viacheslav, et autres
Publié: (2023)

Object-Centric Learning with Slot Mixture Module
par: Kirilenko, Daniil, et autres
Publié: (2023)

Improving GFlowNets with Monte Carlo Tree Search
par: Morozov, Nikita, et autres
Publié: (2024)

Re:Frame -- Retrieving Experience From Associative Memory
par: Zelezetsky, Daniil, et autres
Publié: (2025)

KAGE-Bench: Fast Known-Axis Visual Generalization Evaluation for Reinforcement Learning
par: Cherepanov, Egor, et autres
Publié: (2026)

Don't Let It Hallucinate: Premise Verification via Retrieval-Augmented Logical Reasoning
par: Qin, Yuehan, et autres
Publié: (2025)

A New Perspective on Transformers in Online Reinforcement Learning for Continuous Control
par: Kachaev, Nikita, et autres
Publié: (2025)

Don't Forget the Critic: Value-Based Data Rehearsal for Multi-Cyclic Continual Reinforcement Learning
par: Poole, Benjamin, et autres
Publié: (2026)

Don't Let Bandit Feedback Pull Continual LLM-Recommender Updates Off Target
par: Kim, Taesan, et autres
Publié: (2026)

sDPO: Don't Use Your Data All at Once
par: Kim, Dahyun, et autres
Publié: (2024)

Don't Waste Your Time: Early Stopping Cross-Validation
par: Bergman, Edward, et autres
Publié: (2024)

Don't Forget to Connect! Improving RAG with Graph-based Reranking
par: Dong, Jialin, et autres
Publié: (2024)

Don't Let It Fade: Preserving Edits in Diffusion Language Models via Token Timestep Allocation
par: Kim, Woojin, et autres
Publié: (2025)

Facilitating large language model Russian adaptation with Learned Embedding Propagation
par: Tikhomirov, Mikhail, et autres
Publié: (2024)

Performance Insights-based AI-driven Football Transfer Fee Prediction
par: Sulimov, Daniil
Publié: (2024)

Universal time-series forecasting with mixture predictors
par: Ryabko, Daniil
Publié: (2020)

The Ky Fan Norms and Beyond: Dual Norms and Combinations for Matrix Optimization
par: Kravatskiy, Alexey, et autres
Publié: (2025)

Don't Pay Attention
par: Hammoud, Mohammad, et autres
Publié: (2025)

INTRYGUE: Induction-Aware Entropy Gating for Reliable RAG Uncertainty Estimation
par: Bazarova, Alexandra, et autres
Publié: (2026)

SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization
par: Chen, Minghan, et autres
Publié: (2025)