Papers

Filtered to embodied experience · clear filter

Browse by term

continual learning 83reinforcement learning 50large language models 12benchmarking 11benchmarks 11language models 11vision-language models 11robotics 7natural language processing 6world models 6generative models 5recursive self-improvement 5attention mechanisms 4diffusion Transformers 4multi-agent systems 4multimodal learning 4multimodal models 4on-policy distillation 4self-distillation 4self-supervised learning 4transformers 4video generation 4vision-language-action models 4agent-based systems 3agentic models 3agentic search 3autonomous systems 3coding agents 3diffusion models 3image generation 3

Matching papers

OpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining

59 upvotes · 7 SEP 2026 · Yuran Wang, Siqiao Huang, Mingleyang Li et al.

This paper introduces OpenWAM, an open framework for pretraining world-action models, which inherit knowledge from video-generative priors and generate executable control signals. Practitioners may care about OpenWAM because it provides a modular and controlled way to experiment with different design choices and evaluate their impact.

world-action modelspretrainingembodied experiencegenerative priorscontrol signalsexperimental design