{"id":6914,"date":"2025-09-17T07:02:29","date_gmt":"2025-09-17T07:02:29","guid":{"rendered":"https:\/\/mailitics.com\/index.php\/2025\/09\/17\/2509-12387\/"},"modified":"2025-09-17T07:02:29","modified_gmt":"2025-09-17T07:02:29","slug":"2509-12387","status":"publish","type":"post","link":"https:\/\/mailitics.com\/index.php\/2025\/09\/17\/2509-12387\/","title":{"rendered":"Causal-Symbolic Meta-Learning (CSML): Inducing Causal World Models for Few-Shot Generalization"},"content":{"rendered":"

Causal-Symbolic Meta-Learning (CSML): Inducing Causal World Models for Few-Shot Generalization
\n \t

\n
<\/BR>
\n
\n \t

\n
<\/BR><\/p>\n

arXiv:2509.12387v1 Announce Type: cross
\nAbstract: Modern deep learning models excel at pattern recognition but remain fundamentally limited by their reliance on spurious correlations, leading to poor generalization and a demand for massive datasets. We argue that a key ingredient for human-like intelligence-robust, sample-efficient learning-stems from an understanding of causal mechanisms. In this work, we introduce Causal-Symbolic Meta-Learning (CSML), a novel framework that learns to infer the latent causal structure of a task distribution. CSML comprises three key modules: a perception module that maps raw inputs to disentangled symbolic representations; a differentiable causal induction module that discovers the underlying causal graph governing these symbols and a graph-based reasoning module that leverages this graph to make predictions. By meta-learning a shared causal world model across a distribution of tasks, CSML can rapidly adapt to novel tasks, including those requiring reasoning about interventions and counterfactuals, from only a handful of examples. We introduce CausalWorld, a new physics-based benchmark designed to test these capabilities. Our experiments show that CSML dramatically outperforms state-of-the-art meta-learning and neuro-symbolic baselines, particularly on tasks demanding true causal inference.<\/div>\n

\t

\n
<\/BR>
\n Mohamed Zayaan S
\n \t

\n
<\/BR>
\nGo to original source<\/a>
\n \t

\n
<\/BR><\/p>\n","protected":false},"excerpt":{"rendered":"

Causal-Symbolic Meta-Learning (CSML): Inducing Causal World Models for Few-Shot Generalization arXiv:2509.12387v1 Announce Type: cross Abstract: Modern deep learning models excel at pattern recognition but remain fundamentally limited by their reliance on spurious correlations, leading to poor generalization and a demand for massive datasets. We argue that a key ingredient for human-like intelligence-robust, sample-efficient learning-stems from […]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[62,187,113,112],"tags":[331,3807,199],"class_list":["post-6914","post","type-post","status-publish","format-standard","hentry","category-aimldsaimlds","category-cs-ai","category-cs-lg","category-stat-ml","tag-causal","tag-csml","tag-learning"],"_links":{"self":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/6914"}],"collection":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/comments?post=6914"}],"version-history":[{"count":0,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/6914\/revisions"}],"wp:attachment":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/media?parent=6914"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/categories?post=6914"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/tags?post=6914"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}