Humans exhibit abstraction learning consistent with prospective compression of future tasks in non-stationary domains, unlike retrospective compression algorithms or LLM-based approaches.
InThe Twelfth International Conference on Learning Representations (ICLR)
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
DEFT dynamically generates LLM-proposed biologically-informed features during decision tree construction to achieve interpretable and predictive DNA sequence classification.
RuleChef generates and refines executable rules for NLP tasks using LLMs only at learning time to produce fast, deterministic, and inspectable rule systems.
LLMs perform in-context learning as trajectories through a structured low-dimensional conceptual belief space, with the structure visible in both behavior and internal representations and causally manipulable via interventions.
Denoising Recursion Models train multi-step noise reversal in looped transformers and outperform the prior Tiny Recursion Model on ARC-AGI.
An adaptive compute-optimal strategy for scaling LLM test-time compute achieves over 4x efficiency gains versus best-of-N and lets smaller models outperform 14x larger ones on some problems.
Quiet-STaR lets language models learn token-level rationales from general text, producing zero-shot gains on GSM8K and CommonsenseQA after continued pretraining.