paper-with-me

Papers

STORM: Search-Guided Generative World Models for Robotic Manipulation

2025-12-20 · Wenjun Lin, Jensen Zhang, Kaitong Cai, Keze Wang arxiv

We present STORM (Search-Guided Generative World Models), a novel framework for spatio-temporal reasoning in robotic manipulation that unifies diffusion-based action generation, conditional video prediction, and search-based planning. Unlike prior Vision-Language-Action (VLA) models that rely on abstract latent dynamics or delegate reasoning to language components, STORM grounds planning in explicit visual rollouts, enabling interpretable and foresight-driven decision-making. A diffusion-based VLA policy proposes diverse candidate actions, a generative video world model simulates their visual and reward outcomes, and Monte Carlo Tree Search (MCTS) selectively refines plans through lookahead evaluation. Experiments on the SimplerEnv manipulation benchmark demonstrate that STORM achieves a new state-of-the-art average success rate of 51.0 percent, outperforming strong baselines such as CogACT. Reward-augmented video prediction substantially improves spatio-temporal fidelity and task relevance, reducing Frechet Video Distance by over 75 percent. Moreover, STORM exhibits robust re-planning and failure recovery behavior, highlighting the advantages of search-guided generative world models for long-horizon robotic manipulation.

📄 PDF Abstract BibTeX arXiv:2512.18477

Code (0)

등록된 구현이 없습니다.

Tasks

Video Prediction

Similar Papers 제목 키워드 기반

Robotic Brain Storm Optimization: A Multi-target Collaborative Searching Paradigm for Swarm Robotics

2021-05-27 · Jian Yang, Yuhui Shi

Swarm intelligence optimization algorithms can be adopted in swarm robotics for target searching tasks in a 2-D or 3-D space by treating the target signal strength as fitness values. Many current works in the literature …

Clustering

Masked Generative Priors Improve World Models Sequence Modelling Capabilities

2024-10-10 · Cristian Meo, Mircea Lica, Zarif Ikram, Akihiro Nakano 외

Deep Reinforcement Learning (RL) has become the leading approach for creating artificial agents in complex environments. Model-based approaches, which are RL methods with world models that predict environment dynamics, a…

continuous-controlContinuous ControlDeep Reinforcement LearningInductive Bias+2

STORM: Stepwise Token Optimization with Reward-Guided Beam Search

2026-06-09 · Arthur Satouf, Giulio D'Erasmo, Yuxuan Zong, Habiboulaye Amadou Boubacar 외 arxiv

Modern retrieval increasingly relies on dense and learned-sparse neural models that are effective but require encoding the entire corpus into a specialized index, rebuilt whenever the model changes. Lexical retrievers li…

Using Generative Models to Produce Realistic Populations of UK Windstorms

2025-01-27 · Yee Chun Tsoi, Kieran M. R. Hunt, Len Shaffrey, Atta Badii 외

This study evaluates the potential of generative models, trained on historical ERA5 reanalysis data, for simulating windstorms over the UK. Four generative models, including a standard GAN, a WGAN-GP, a U-net diffusion m…

STORM: Slot-based Task-aware Object-centric Representation for robotic Manipulation

2026-01-28 · Alexandre Chapin, Emmanuel Dellandréa, Liming Chen arxiv

Visual foundation models provide strong perceptual features for robotics, but their dense representations lack explicit object-level structure, limiting robustness and controllability in manipulation tasks. We propose ST…