Copertina

Reinforcing VLAs in Task-Agnostic World Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Yucen, Yu, Rui, Zhang, Fengming, Lu, Junjie, Qin, Xinyao, Zhang, Tianxiang, Wang, Kaixin, Zhao, Li
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

How Do VLAs Effectively Inherit from VLMs?
di: Zhang, Chuheng, et al.
Pubblicazione: (2025)

How VLAs (Really) Work In Open-World Environments
di: Rasouli, Amir, et al.
Pubblicazione: (2026)

FOUNDER: Grounding Foundation Models in World Models for Open-Ended Embodied Decision Making
di: Wang, Yucen, et al.
Pubblicazione: (2025)

Scaling Sim-to-Real Reinforcement Learning for Robot VLAs with Generative 3D Worlds
di: Choi, Andrew, et al.
Pubblicazione: (2026)

Task-Agnostic Learning to Accomplish New Tasks
di: Zhang, Xianqi, et al.
Pubblicazione: (2022)

Co-Evolving Latent Action World Models
di: Wang, Yucen, et al.
Pubblicazione: (2025)

Reward Models in Deep Reinforcement Learning: A Survey
di: Yu, Rui, et al.
Pubblicazione: (2025)

Discover, Learn, and Reinforce: Scaling Vision-Language-Action Pretraining with Diverse RL-Generated Trajectories
di: Yang, Rushuai, et al.
Pubblicazione: (2025)

Domain-Agnostic Mutual Prompting for Unsupervised Domain Adaptation
di: Du, Zhekai, et al.
Pubblicazione: (2024)

villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models
di: Chen, Xiaoyu, et al.
Pubblicazione: (2025)

SnapFlow: One-Step Action Generation for Flow-Matching VLAs via Progressive Self-Distillation
di: Luan, Wuyang, et al.
Pubblicazione: (2026)

PathGPT: Reframing Path Recommendation as a Natural Language Generation Task with Retrieval-Augmented Language Models
di: Marcelyn, Steeve Cuthbert, et al.
Pubblicazione: (2025)

Enhancing Graph Neural Networks with Limited Labeled Data by Actively Distilling Knowledge from Large Language Models
di: Li, Quan, et al.
Pubblicazione: (2024)

Task-Agnostic Pre-training and Task-Guided Fine-tuning for Versatile Diffusion Planner
di: Fan, Chenyou, et al.
Pubblicazione: (2024)

HC-GST: Heterophily-aware Distribution Consistency based Graph Self-training
di: Wang, Fali, et al.
Pubblicazione: (2024)

VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference
di: Tang, Jiaming, et al.
Pubblicazione: (2025)

Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta-Reinforcement Learning
di: Qian, Fuyuan, et al.
Pubblicazione: (2026)

How Far is Video Generation from World Model: A Physical Law Perspective
di: Kang, Bingyi, et al.
Pubblicazione: (2024)

Improving Token-Based World Models with Parallel Observation Prediction
di: Cohen, Lior, et al.
Pubblicazione: (2024)

L2M-AID: Autonomous Cyber-Physical Defense by Fusing Semantic Reasoning of Large Language Models with Multi-Agent Reinforcement Learning (Preprint)
di: Xu, Tianxiang, et al.
Pubblicazione: (2025)

VTAM: Video-Tactile-Action Models for Complex Physical Interaction Beyond VLAs
di: Yuan, Haoran, et al.
Pubblicazione: (2026)

Hijacking Large Audio-Language Models via Context-Agnostic and Imperceptible Auditory Prompt Injection
di: Chen, Meng, et al.
Pubblicazione: (2026)

World4RL: Diffusion World Models for Policy Refinement with Reinforcement Learning for Robotic Manipulation
di: Jiang, Zhennan, et al.
Pubblicazione: (2025)

MCLMR: A Model-Agnostic Causal Learning Framework for Multi-Behavior Recommendation
di: Zhang, Ranxu, et al.
Pubblicazione: (2026)

Rethinking Driving World Model as Synthetic Data Generator for Perception Tasks
di: Zeng, Kai, et al.
Pubblicazione: (2025)

Retrieve-then-Steer: Online Success Memory for Test-Time Adaptation of Generative VLAs
di: Zhao, Jianchao, et al.
Pubblicazione: (2026)

Latent Policy Steering with Embodiment-Agnostic Pretrained World Models
di: Wang, Yiqi, et al.
Pubblicazione: (2025)

VLA-0: Building State-of-the-Art VLAs with Zero Modification
di: Goyal, Ankit, et al.
Pubblicazione: (2025)

Model Evolution Framework with Genetic Algorithm for Multi-Task Reinforcement Learning
di: Yu, Yan, et al.
Pubblicazione: (2025)

World-Gymnast: Training Robots with Reinforcement Learning in a World Model
di: Sharma, Ansh Kumar, et al.
Pubblicazione: (2026)

FamiCom: Further Demystifying Prompts for Language Models with Task-Agnostic Performance Estimation
di: Li, Bangzheng, et al.
Pubblicazione: (2024)

Simulus: Combining Improvements in Sample-Efficient World Model Agents
di: Cohen, Lior, et al.
Pubblicazione: (2025)

VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents
di: Wang, Kangrui, et al.
Pubblicazione: (2025)

Reinforcement Learning enhanced Online Adaptive Clinical Decision Support via Digital Twin powered Policy and Treatment Effect optimized Reward
di: Qin, Xinyu, et al.
Pubblicazione: (2025)

Agnostic Reinforcement Learning: Foundations and Algorithms
di: Li, Gene
Pubblicazione: (2025)

Lost in Fog: Sensor Perturbations Expose Reasoning Fragility in Driving VLAs
di: Priyadershi, Abhinaw, et al.
Pubblicazione: (2026)

Ensemble Successor Representations for Task Generalization in Offline-to-Online Reinforcement Learning
di: Wang, Changhong, et al.
Pubblicazione: (2024)

Beyond Visual Safety: Jailbreaking Multimodal Large Language Models for Harmful Image Generation via Semantic-Agnostic Inputs
di: Yu, Mingyu, et al.
Pubblicazione: (2026)

DistJoin: A Decoupled Join Cardinality Estimator based on Adaptive Neural Predicate Modulation
di: Zhang, Kaixin, et al.
Pubblicazione: (2025)

Multi-Task Interactive Robot Fleet Learning with Visual World Models
di: Liu, Huihan, et al.
Pubblicazione: (2024)