← Library

2026-03-18

7 saved articles

  2. Why AI systems don't learn and what to do about it: Lessons on autonomous learning from cognitive science

    [Submitted on 16 Mar 2026] · arXiv.org

    We critically examine the limitations of current AI models in achieving autonomous learning and propose a learning architecture inspired by human and animal cognition. The proposed framework integrates learning from observation (System A) and learning from active behavior (System B) while flexibly switching between these learning modes as a function of internally generated meta-control signals (System M). We discuss how this could be built by taking inspiration on how organisms adapt to real-wor

  3. Nacrith: Neural Lossless Compression via Ensemble Context Modeling and High-Precision CDF Coding

    [Submitted on 23 Feb 2026 (v1), last revised 24 Feb 2026 (this version, v2)] · arXiv.org

    We present Nacrith, a lossless compression system that combines a 135M-parameter transformer language model (SmolLM2-135M) with an ensemble of lightweight online predictors and a 32-bit arithmetic coder, achieving the best compression results among the systems evaluated in this study on natural language text. Beyond the base LLM-plus-arithmetic-coding paradigm, Nacrith introduces several contributions: (1) a CDF precision upgrade from 2^16 to 2^24 that eliminates ~75% of quantization overhead ca

  4. Aperiodic Structures Never Collapse: Fibonacci Hierarchies for Lossless Compression

    [Submitted on 16 Mar 2026 (v1), last revised 23 Mar 2026 (this version, v2)] · arXiv.org

    We study whether an aperiodic hierarchy can provide a structural advantage for lossless compression over periodic alternatives. We show that Fibonacci quasicrystal tilings avoid the finite-depth collapse that affects periodic hierarchies: usable $n$-gram lookup positions remain non-zero at every level, while periodic tilings collapse after $O(\log p)$ levels for period $p$. This yields an aperiodic hierarchy advantage: dictionary reuse remains available across all scales instead of vanishing bey

  5. Micro-Diffusion Compression - Binary Tree Tweedie Denoising for Online Probability Estimation

    [Submitted on 9 Mar 2026 (v1), last revised 12 Mar 2026 (this version, v3)] · arXiv.org

    We present Midicoth, a lossless compression system that introduces a micro-diffusion denoising layer for improving probability estimates produced by adaptive statistical models. In compressors such as Prediction by Partial Matching (PPM), probability estimates are smoothed by a prior to handle sparse observations. When contexts have been seen only a few times, this prior dominates the prediction and produces distributions that are significantly flatter than the true source distribution, leading