world-action-models

Tag

Cards List
#world-action-models

BadWAM: When World-Action Models Dream Right but Act Wrong

Hugging Face Daily Papers · 2026-07-16 Cached

BadWAM introduces a framework for adversarial attacks on World-Action Models (WAMs), breaking the alignment between imagination and action via small visual perturbations. The attacks significantly reduce task success rates, exposing a vulnerability in this class of models.

0 favorites 0 likes
#world-action-models

GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch

Hugging Face Daily Papers · 2026-07-15 Cached

GigaWorld-Policy-0.5 is an enhanced World Action Model for robot control that improves training and inference efficiency through a Mixed Action-Conditioned World Modeling strategy and a Mixture-of-Transformers architecture, achieving 85ms latency on a local RTX 4090.

0 favorites 0 likes
#world-action-models

Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots

Hugging Face Daily Papers · 2026-07-02 Cached

Embodied.cpp is a portable C++ inference runtime that enables efficient deployment of vision-language-action and world-action models across heterogeneous edge devices and robots through modular execution layers and optimized inference.

0 favorites 0 likes
#world-action-models

@_akhaliq: World Action Models: A Survey

X AI KOLs Timeline · 2026-06-23 Cached

A survey paper on World Action Models, covering recent advances in AI action and world models.

0 favorites 0 likes
#world-action-models

World Action Models: A Survey

Hugging Face Daily Papers · 2026-06-18 Cached

This survey provides a comprehensive overview of World Action Models (WAMs), predictive-action systems that generate future states for decision-making, and organizes existing works by their required outputs and design choices.

0 favorites 0 likes
#world-action-models

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?

Hugging Face Daily Papers · 2026-06-17 Cached

ImageWAM proposes replacing video generation with pretrained image editing models in world action models for robot control, achieving superior performance while reducing FLOPs to 1/6 and latency to 1/4 of video-based approaches.

0 favorites 0 likes
#world-action-models

Light-WAM: Efficient World Action Models with State-Fusion Action Decoding

Hugging Face Daily Papers · 2026-06-06 Cached

Light-WAM is a lightweight world action model for efficient robot manipulation that uses a compact video backbone and downsampled latent space for future-video supervision, achieving high performance with low inference latency.

0 favorites 0 likes
#world-action-models

Flash-WAM: Modality-Aware Distillation for World Action Models

Hugging Face Daily Papers · 2026-06-03 Cached

Flash-WAM introduces a modality-aware distillation method for world-action models, achieving real-time inference by compressing diffusion to a single step per modality, resulting in 23x speedup.

0 favorites 0 likes
#world-action-models

@tom_doerr: Curated list of Vision-Language-Action and World Action Models research https://github.com/DravenALG/awesome-vla-wam…

X AI KOLs Timeline · 2026-05-22 Cached

Curated GitHub list of Vision-Language-Action and World Action Models research for robotics foundation models.

0 favorites 0 likes
#world-action-models

@DrJimFan: I promise this will be the best 20 min you spend today! Robotics: Endgame, the sequel to my last year's Sequoia AI Asce…

X AI KOLs Timeline · 2026-05-08

In his talk at Sequoia AI Ascent, Dr. Jim Fan presents a roadmap for achieving Physical AGI parallel to LLM success, introducing concepts like video world models, World Action Models (WAM), and the Dexterity Scaling Law, and sharing predictions for the near future.

0 favorites 0 likes
#world-action-models

When to Trust Imagination: Adaptive Action Execution for World Action Models

Hugging Face Daily Papers · 2026-05-07 Cached

This paper introduces FFDC, a lightweight verifier for World Action Models that enables adaptive action chunk sizes by checking consistency between predicted and actual observations, improving efficiency and robustness in robotic manipulation.

0 favorites 0 likes
← Back to home

Submit Feedback