{"ID":2879772,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.15387","arxiv_id":"2508.15387","title":"DIO: Refining Mutual Information and Causal Chain to Enhance Machine Abstract Reasoning Ability","abstract":"Despite deep learning's broad success, its abstract-reasoning bottleneck persists. We tackle Raven's Progressive Matrices (RPM), the benchmark for pattern, reasoning and problem-solving intelligence. We model the full causal chain image $\\rightarrow$ attributes $\\rightarrow$ progressive patterns $\\rightarrow$ consistency $\\rightarrow$ answer and build the baseline DIO. Yet DIO's mutual-information lower-bound objective does not embed human logic: the bound is loose and statistic-based, ignoring causal subject-object links. We therefore present three refinements. 1) Brando introduces trainable negative options to tighten the variational bound. 2) WORLD replaces generation with a Gaussian-mixture feature model that supplies infinite, weighted negatives, further tightening the bound. 3) DIEGO adds metadata supervision to rectify the \"attributes $\\rightarrow$ patterns\" semantic gap, aligning representations with human rules. These upgrades substantially boost discriminative RPM accuracy and, for the first time, let DIO generate valid answers in open-ended RPM. The work provides causal-driven design guidelines, objective-refinement strategies and cross-modal insights for abstract-reasoning research.","short_abstract":"Despite deep learning's broad success, its abstract-reasoning bottleneck persists. We tackle Raven's Progressive Matrices (RPM), the benchmark for pattern, reasoning and problem-solving intelligence. We model the full causal chain image $\\rightarrow$ attributes $\\rightarrow$ progressive patterns $\\rightarrow$ consisten...","url_abs":"https://arxiv.org/abs/2508.15387","url_pdf":"https://arxiv.org/pdf/2508.15387v7","authors":"[\"Ruizhuo Song\",\"Beiming Yuan\"]","published":"2025-08-21T09:23:51Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}