跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-23AI 評分39

Ψ-0.6:統一視覺語言世界模型中的自適應思維流

Ψ-0.6: Adaptive Streams of Thought in a Unified Vision-Language World Model

AI 導讀

Ψ-0.6 是一個統一視覺語言世界模型,能在共享推理過程中自適應組合感知、語言、幾何與模擬,以提升空間推理及反事實模擬能力。它在多視角空間推理中零樣本超越領先的開放權重模型,並可透過幾何中間表示進一步提升表現。以任務回饋進行的強化學習可提升視覺問答準確度,且增益能遷移至未見過的基準測試。

正文

Published on Oct 23

Authors:

,

,

,

,

,

,

Abstract

A unified vision-language world model adaptively combines perception, language, geometry, and simulation through interleaved reasoning streams to improve spatial reasoning and counterfactual simulation.

Humans reason about the physical world by flexibly combining different forms of inference as a problem unfolds. Achieving this flexibility is a major open challenge in AI: capabilities often remain separated across specialized models, limiting how they can be composed and jointly adapted to a task. We introduce Ψ-0.6, a unified vision-language world model that adaptively composes perception, language, geometry, and simulation within a shared reasoning process we call streams of thought. These streams interleave images, text, and explicit representations of geometry and motion, all of which the model can generate and interpret through a shared token interface. Ψ-0.6 surpasses leading open-weight models zero-shot on multi-view spatial reasoning, with further gains from reasoning through geometric intermediates. It also supports counterfactual simulation: generating and interpreting imagined scenes to determine, for example, whether moving an object would obstruct a pathway. Reinforcement learning from task feedback jointly optimizes the selection, generation, and use of intermediate representations, improving visual question-answering accuracy with gains that transfer to unseen benchmarks. Ψ-0.6 offers a path toward adaptive physical reasoning -- not only predicting the physical world but also choosing the representations through which to reason.

View arXiv page View PDF Project page GitHub Add to collection

Get this paper in your agent:

hf papers read 2610.32177

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.32177 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.32177 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.32177 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co