ciwGAN and fiwGAN models trained on isolated words spontaneously generate concatenated multi-word outputs and display early compositionality precursors.
hub Canonical reference
and Chater, Nick , year =
Canonical reference. 100% of citing Pith papers cite this work as background.
24
Pith papers citing it
Background
100% of classified citations
hub tools
citation-role summary
background 5
citation-polarity summary
verdicts
UNVERDICTED 24roles
background 5polarities
background 5representative citing papers
Analysis of 500k ChatGPT logs shows over one-third of conversations generate fiction, dominated by power users with repetitive and niche patterns.
Defines memetic capture as AI-driven cultural disempowerment and outlines the CPGF policy architecture combining metrics, democratic assemblies, pluralistic standards, and transnational coordination.
LLM societies in Nomic show non-monotonic collective adaptation peaking at mid-scales, with smaller models rule-inert and larger ones restrictive.
3D-VLA is a new embodied foundation model that uses a 3D LLM plus aligned diffusion models to generate future images and point clouds for improved reasoning and action planning in 3D environments.
Transformers on impossible-language variants show gradual grammatical sensitivity loss but sharp long-sentence generation failures, supporting generative deficiency as a link to non-attestation.
Multi-source prediction-powered inference aggregates multiple pseudo-labeled datasets via weights chosen to minimize asymptotic confidence-region volume, with asymptotic normality and comparisons to single-source and target-only baselines shown for both homogeneous and heterogeneous (covariate/domai
Presents a new annotated resource of 1,482 tweets for enthymeme detection that studies label variation instead of eliminating it, with preliminary evidence that disagreement-aware training improves model performance.
Agentic Redux claims provably correct LLM agent executions on suitable domains via typed lambda calculus with full decision logging, demonstrated on healthcare compliance and security disclosure with supporting code.
Iterated learning theory predicts and LLM experiments confirm non-monotonic compositionality during self-training, reframing model collapse as cultural transmission with matching human regularization patterns.
Information defined as maximum-caliber deviation derives IIT 3.0 cause-effect repertoires from constrained entropy maximization and equates to prediction error under CLT and LDT.
Transportability methods can transport causal effects from experimental samples to broader target populations in software engineering by leveraging observational data to improve external validity.
A critical incident technique study with 142 participants identifies mechanisms by which games create or block agender euphoria and supplies empirically grounded design criteria for gender-neutral play.
ABot-M0 unifies heterogeneous robot data into a 6-million-trajectory dataset and introduces Action Manifold Learning to predict stable actions on a low-dimensional manifold using a DiT backbone.
Proposes CAC prompting to benchmark language models on syntactic and discourse properties of determiners against child acquisition data, finding large models approach but do not match human performance on both.
An unsupervised method detects domain shifts via localized density anomaly search in feature space, attributes the shift to a minimal subspace, and extracts balanced subsets from two unlabeled datasets.
CaloArt achieves top FPD, high-level, and classifier metrics on CaloChallenge datasets 2 and 3 while keeping single-GPU generation at 9-11 ms per shower by combining large-patch tokenization, x-prediction, and conditional flow matching.
The method uses multi-view diffusion priors and action manifold learning to resolve depth ambiguity and improve action prediction in VLA robotic manipulation models, reporting higher success rates than baselines on LIBERO, RoboTwin, and real-robot tasks.
Neo, a cGAN, super-resolves HSC images to HST-like quality and improves galaxy morphological parameter accuracy by factors of 2-10.
Argues that LLM guardrails generate unethical reality gaps by shifting epistemic risk to users and that ethical AI can become unethical when it prioritizes institutional reassurance over accurate perception.
Introduces 'undone computer science' as a lens for spotting neglected research questions arising from the sociological, economic, and political organization of the field.
NaviGNN combines RL and GNNs in multi-agent simulations to achieve 7.8-8.4 minute average commutes, over 89% satisfaction, and above 91% reachability in extreme urban morphologies.
Empirical finance is limited to ex post causal inference because self-reference in markets makes unidirectional causation unstable or fallacious.
A late-fusion gradient-boosting pipeline with LLM semantic features is submitted to the EXIST 2026 lab for sexism identification in memes and videos, showing mixed generalization from development to test data.
citing papers explorer
-
Basic syntax from speech: Spontaneous concatenation in unsupervised deep neural networks
ciwGAN and fiwGAN models trained on isolated words spontaneously generate concatenated multi-word outputs and display early compositionality precursors.
-
AI Fiction in the Wild
Analysis of 500k ChatGPT logs shows over one-third of conversations generate fiction, dominated by power users with repetitive and niche patterns.
-
When transformers learn "impossible" languages, what do they learn?
Transformers on impossible-language variants show gradual grammatical sensitivity loss but sharp long-sentence generation failures, supporting generative deficiency as a link to non-attestation.
-
A Resource for Enthymeme Detection in Controversial Political Discourse
Presents a new annotated resource of 1,482 tweets for enthymeme detection that studies label variation instead of eliminating it, with preliminary evidence that disagreement-aware training improves model performance.
-
Model Collapse as Cultural Evolution
Iterated learning theory predicts and LLM experiments confirm non-monotonic compositionality during self-training, reframing model collapse as cultural transmission with matching human regularization patterns.
-
Measuring Form and Function in Language Models
Proposes CAC prompting to benchmark language models on syntactic and discourse properties of determiners against child acquisition data, finding large models approach but do not match human performance on both.