Cover Image

What Do Latent Action Models Actually Learn?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Chuheng, Pearce, Tim, Zhang, Pushi, Wang, Kaixin, Chen, Xiaoyu, Shen, Wei, Zhao, Li, Bian, Jiang
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

Learning Additively Compositional Latent Actions for Embodied AI
by: Wei, Hangxing, et al.
Published: (2026)

Policy Filtration for RLHF to Mitigate Noise in Reward Models
by: Zhang, Chuheng, et al.
Published: (2024)

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

IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI
by: Chen, Xiaoyu, et al.
Published: (2024)

Prediction Bottlenecks Don't Discover Causal Structure (But Here's What They Actually Do)
by: Lade, Ankit Hemant, et al.
Published: (2026)

Are Language Models Actually Useful for Time Series Forecasting?
by: Tan, Mingtian, et al.
Published: (2024)

What do Geometric Hallucination Detection Metrics Actually Measure?
by: Yeats, Eric, et al.
Published: (2026)

Rethinking Soft Actor-Critic in High-Dimensional Action Spaces: The Cost of Ignoring Distribution Shift
by: Chen, Yanjun, et al.
Published: (2024)

Solving Continual Offline Reinforcement Learning with Decision Transformer
by: Huang, Kaixin, et al.
Published: (2024)

Beyond Pixel Histories: World Models with Persistent 3D State
by: Garcin, Samuel, et al.
Published: (2026)

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

Do Post-Training Algorithms Actually Differ? A Controlled Study Across Model Scales Uncovers Scale-Dependent Ranking Inversions
by: Li, Xiaoyi
Published: (2026)

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

AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence
by: Liu, Yuliang, et al.
Published: (2025)

What Do Learned Models Measure?
by: Žliobaitė, Indrė
Published: (2026)

What Do World Models Learn in RL? Probing Latent Representations in Learned Environment Simulators
by: Zhang, Xinyu
Published: (2026)

Asking Before Acting: Gather Information in Embodied Decision Making with Language Models
by: Chen, Xiaoyu, et al.
Published: (2023)

Do What You Say: Steering Vision-Language-Action Models via Runtime Reasoning-Action Alignment Verification
by: Wu, Yilin, et al.
Published: (2025)

Hard Prompts Made Interpretable: Sparse Entropy Regularization for Prompt Tuning with RL
by: Choi, Yunseon, et al.
Published: (2024)

Constrained Latent Action Policies for Model-Based Offline Reinforcement Learning
by: Alles, Marvin, et al.
Published: (2024)

Self-Improving World Modelling with Latent Actions
by: Qiu, Yifu, et al.
Published: (2026)

Efficient and Generalized end-to-end Autonomous Driving System with Latent Deep Reinforcement Learning and Demonstrations
by: Tang, Zuojin, et al.
Published: (2024)

Event Fields: Learning Latent Event Structure for Waveform Foundation Models
by: Na, Li, et al.
Published: (2026)

Learning to Select In-Context Demonstration Preferred by Large Language Model
by: Zhang, Zheng, et al.
Published: (2025)

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations
by: Hoang, Huy, et al.
Published: (2025)

Does Your Wildfire Prediction Model Actually Work, or Just Score Well?
by: Xu, Yangshuang, et al.
Published: (2026)

Learning Discrete Concepts in Latent Hierarchical Models
by: Kong, Lingjing, et al.
Published: (2024)

TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning
by: Zheng, Ruijie, et al.
Published: (2023)

Fairness Begins with State: Purifying Latent Preferences for Hierarchical Reinforcement Learning in Interactive Recommendation
by: Lu, Yun, et al.
Published: (2026)

Preferred-Action-Optimized Diffusion Policies for Offline Reinforcement Learning
by: Zhang, Tianle, et al.
Published: (2024)

Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?
by: Ren, Richard, et al.
Published: (2024)

Driving Reaction Trajectories via Latent Flow Matching
by: Shen, Yili, et al.
Published: (2026)

Proximal Action Replacement for Behavior Cloning Actor-Critic in Offline Reinforcement Learning
by: Dong, Jinzong, et al.
Published: (2026)

CLAM: Continuous Latent Action Models for Robot Learning from Unlabeled Demonstrations
by: Liang, Anthony, et al.
Published: (2025)

Learning to Act Robustly with View-Invariant Latent Actions
by: Jeong, Youngjoon, et al.
Published: (2026)

What Do Machine Learning Researchers Mean by "Reproducible"?
by: Raff, Edward, et al.
Published: (2024)

UniVLA: Learning to Act Anywhere with Task-centric Latent Actions
by: Bu, Qingwen, et al.
Published: (2025)

AdaWorld: Learning Adaptable World Models with Latent Actions
by: Gao, Shenyuan, et al.
Published: (2025)

Large Language Model-Powered Evolutionary Code Optimization on a Phylogenetic Tree
by: Zhao, Leyi, et al.
Published: (2026)