Copertina

Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Bredis, George, Dereka, Stanislav, Sinii, Viacheslav, Rakhimov, Ruslan, Gavrilov, Daniil
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Next Embedding Prediction Makes World Models Stronger
di: Bredis, George, et al.
Pubblicazione: (2026)

F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare
di: Plyusov, Daniil, et al.
Pubblicazione: (2026)

Steering LLM Reasoning Through Bias-Only Adaptation
di: Sinii, Viacheslav, et al.
Pubblicazione: (2025)

In-Context Reinforcement Learning for Variable Action Spaces
di: Sinii, Viacheslav, et al.
Pubblicazione: (2023)

Real-World Offline Reinforcement Learning from Vision Language Model Feedback
di: Venkataraman, Sreyas, et al.
Pubblicazione: (2024)

RLVR-World: Training World Models with Reinforcement Learning
di: Wu, Jialong, et al.
Pubblicazione: (2025)

ESSA: Evolutionary Strategies for Scalable Alignment
di: Korotyshova, Daria, et al.
Pubblicazione: (2025)

The Differences Between Direct Alignment Algorithms are a Blur
di: Gorbatovski, Alexey, et al.
Pubblicazione: (2025)

You Do Not Fully Utilize Transformer's Representation Capacity
di: Gerasimov, Gleb, et al.
Pubblicazione: (2025)

Identity Curvature Laplace Approximation for Improved Out-of-Distribution Detection
di: Zhdanov, Maksim, et al.
Pubblicazione: (2023)

Diversifying Deep Ensembles: A Saliency Map Approach for Enhanced OOD Detection, Calibration, and Accuracy
di: Dereka, Stanislav, et al.
Pubblicazione: (2023)

Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy
di: Balagansky, Nikita, et al.
Pubblicazione: (2025)

Towards Autonomous Reinforcement Learning for Real-World Robotic Manipulation with Large Language Models
di: Turcato, Niccolò, et al.
Pubblicazione: (2025)

Safe Reinforcement Learning for Real-World Engine Control
di: Bedei, Julian, et al.
Pubblicazione: (2025)

Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning
di: Wang, Zhaoyang, et al.
Pubblicazione: (2026)

Real-World Reinforcement Learning of Active Perception Behaviors
di: Hu, Edward S., et al.
Pubblicazione: (2025)

FutureWorld: A Live Reinforcement Learning Environment for Predictive Agents with Real-World Outcome Rewards
di: Han, Zhixin, et al.
Pubblicazione: (2026)

Transfer Learning of Surrogate Models via Domain Affine Transformation Across Synthetic and Real-World Benchmarks
di: Pan, Shuaiqun, et al.
Pubblicazione: (2025)

One-shot World Models Using a Transformer Trained on a Synthetic Prior
di: Ferreira, Fabio, et al.
Pubblicazione: (2024)

Policy and World Modeling Co-Training for Language Agents
di: Lu, Ning, et al.
Pubblicazione: (2026)

Agentic Reinforcement Learning for Real-World Code Repair
di: Zhu, Siyu, et al.
Pubblicazione: (2025)

A Production Scheduling Framework for Reinforcement Learning Under Real-World Constraints
di: Hoss, Jonathan, et al.
Pubblicazione: (2025)

Towards Large-Scale In-Context Reinforcement Learning by Meta-Training in Randomized Worlds
di: Wang, Fan, et al.
Pubblicazione: (2025)

In-Context Reinforcement Learning via Communicative World Models
di: Martinez-Lopez, Fernando, et al.
Pubblicazione: (2025)

Continual Reinforcement Learning by Planning with Online World Models
di: Liu, Zichen, et al.
Pubblicazione: (2025)

Trust-Region Behavior Blending for On-Policy Distillation
di: Plyusov, Daniil, et al.
Pubblicazione: (2026)

RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning
di: Lei, Kun, et al.
Pubblicazione: (2025)

Gym4ReaL: A Suite for Benchmarking Real-World Reinforcement Learning
di: Salaorni, Davide, et al.
Pubblicazione: (2025)

Learning Abstract World Model for Value-preserving Planning with Options
di: Rodriguez-Sanchez, Rafael, et al.
Pubblicazione: (2024)

Object-Centric World Models for Causality-Aware Reinforcement Learning
di: Nishimoto, Yosuke, et al.
Pubblicazione: (2025)

Reinforcement Learning from Delayed Observations via World Models
di: Karamzade, Armin, et al.
Pubblicazione: (2024)

Teach Old SAEs New Domain Tricks with Boosting
di: Koriagin, Nikita, et al.
Pubblicazione: (2025)

Uncertainty-Aware Robotic World Model Makes Offline Model-Based Reinforcement Learning Work on Real Robots
di: Li, Chenhao, et al.
Pubblicazione: (2025)

The Pump Scheduling Problem: A Real-World Scenario for Reinforcement Learning
di: Donâncio, Henrique, et al.
Pubblicazione: (2022)

Learning to Model the World with Language
di: Lin, Jessy, et al.
Pubblicazione: (2023)

Novelty Detection in Reinforcement Learning with World Models
di: Zollicoffer, Geigh, et al.
Pubblicazione: (2023)

From Observations to Events: Event-Aware World Model for Reinforcement Learning
di: Peng, Zhao-Han, et al.
Pubblicazione: (2026)

World Models Unlock Optimal Foraging Strategies in Reinforcement Learning Agents
di: Fonseca, Yesid, et al.
Pubblicazione: (2025)

From Learning to Mastery: Achieving Safe and Efficient Real-World Autonomous Driving with Human-In-The-Loop Reinforcement Learning
di: Zeqiao, Li, et al.
Pubblicazione: (2025)

Learning to Play Piano in the Real World
di: Zeulner, Yves-Simon, et al.
Pubblicazione: (2025)