Humans exhibit abstraction learning consistent with prospective compression of future tasks in non-stationary domains, unlike retrospective compression algorithms or LLM-based approaches.
babble: Learning better abstractions with e-graphs and anti-unification
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Prospective Compression in Human Abstraction Learning
Humans exhibit abstraction learning consistent with prospective compression of future tasks in non-stationary domains, unlike retrospective compression algorithms or LLM-based approaches.