RxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination

arXiv 2026 25.8 method

TLDR

RxBrain is an embodied cognition model that combines language reasoning with visual imagination for joint planning, using a unified multimodal architecture and a new benchmark.

Reasoning

Strengths include a novel integration of language and visual imagination for embodied planning, a unified multimodal Mixture-of-Transformers architecture, an automatic pipeline for training data, and a dedicated benchmark. Weaknesses are that the abstract provides no quantitative results or comparisons to baselines, and the experimental details are insufficient to assess performance.

Read-first score

Read-first score 25.8, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 18.

Recency 6%

100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Methodology quality 18%

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=experiment,result

Reproducibility 18%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=none

Topical relevance 29%

25.7

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Citation impact 18%

Uses OpenAlex-shaped citation metadata as a bibliometric attention signal, separate from paper quality. cited_by_count=0

Citation velocity 12%

Citation velocity estimates citations per publication-year to reduce old-paper bias. velocity=0.00

Field roles

Frontier

Rank sensitivity

Stability: volatile; rank range: 64.

Keyword Scores

world dynamics prediction

world model

generative world model

video world model

world simulator

interactive world model

model-based reinforcement learning world model

Resources

Paper