cs.AI updates on arXiv.org 07月22日 12:34
What if Othello-Playing Language Models Could See?
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文通过Othello游戏探讨了语言模型在视觉输入下的世界理解能力,提出多模态模型VISOTHELLO,通过预测下一步棋局,证明了多模态训练可提高模型性能及内部表示的鲁棒性。

arXiv:2507.14520v1 Announce Type: new Abstract: Language models are often said to face a symbol grounding problem. While some argue that world understanding can emerge from text alone, others suggest grounded learning is more efficient. We explore this through Othello, where the board state defines a simplified, rule-based world. Building on prior work, we introduce VISOTHELLO, a multi-modal model trained on move histories and board images. Using next-move prediction, we compare it to mono-modal baselines and test robustness to semantically irrelevant perturbations. We find that multi-modal training improves both performance and the robustness of internal representations. These results suggest that grounding language in visual input helps models infer structured world representations.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

多模态模型 语言模型 世界理解 Othello 鲁棒性
相关文章