{"total":12,"items":[{"citing_arxiv_id":"2606.24985","ref_index":297,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Retrieval-Augmented Personalization with Foundation Models for Wearable Stress Detection","primary_cat":"cs.LG","submitted_at":"2026-06-23T14:24:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Retrieval from out-of-domain foundation models enables personalization of a lightweight transformer for stress detection, yielding +3.92% accuracy and +4.76% F1 gains on WESAD without user labels.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.08374","ref_index":15,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Predictive Coding with Bayesian Priors via Proximal Gradients","primary_cat":"eess.SY","submitted_at":"2026-06-06T23:41:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Predictive coding equals proximal gradient descent on MAP problems, with priors setting nonlinearities via proximal operators and yielding leaky firing-rate networks plus hierarchical MRFs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.27929","ref_index":12,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Exploratory Experience Shapes the Geometry of Predictive Representations","primary_cat":"q-bio.NC","submitted_at":"2026-05-27T04:01:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Exploratory experience produces more spatially organized and transition-preserving predictive representations in maze navigation for both agents and mice.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.23819","ref_index":25,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Not Too Generative, Not Too Discriminative: The Human Alignment Sweet Spot","primary_cat":"cs.CV","submitted_at":"2026-05-22T16:21:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Hybrid JEMs at intermediate generative-discriminative balance maximize human alignment on perceptual similarity, gloss, uncertainty, robustness, cue conflict, and feature attribution benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.23035","ref_index":32,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Sparse Autoencoders Map Brain-LLM Alignment onto Cortical Semantic Topography","primary_cat":"cs.CL","submitted_at":"2026-05-21T21:00:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Sparse autoencoders applied to GPT-2 and Llama models recover semantic features accounting for 94% of peak brain encoding performance and map onto distinct cortical semantic regions across three languages.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.20293","ref_index":29,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Closed-form predictive coding via hierarchical Gaussian filters","primary_cat":"cs.LG","submitted_at":"2026-05-19T10:11:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Predictive coding is recast as deep hierarchical Gaussian filters to restore precision-weighted message passing, yielding closed-form inference and online precision learning that matches backpropagation speed on FashionMNIST while outperforming on online and concept-drift tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18118","ref_index":79,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Functional Whole-Brain Models: A New Framework for Unifying Brain Structure and Cognitive Function","primary_cat":"q-bio.NC","submitted_at":"2026-05-18T09:26:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Proposes functional whole-brain models defined by four criteria that integrate empirical connectomes, dynamical realism, and task-performing competence across cognitive domains.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12536","ref_index":30,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Information as Maximum-Caliber Deviation: A bridge between Integrated Information Theory and the Free Energy Principle","primary_cat":"q-bio.NC","submitted_at":"2026-05-03T07:22:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"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.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Rao and Ballard[27], implements anEvidence Lower Bound (ELBO)[217] maximization with approximate posterior q. The negated ELBO constitutes the free energy functional[28]. The concept of arecognition distributionwas introduced, which drives the selection ofm q given parameters U(0),U (1),x (1) and modelsinference.Slower change over time on parametersU (0),U (1) is understood to constitute learning[28]. This framing was later generalized[30, 32] and has since become a dominant way to frame predictive coding[39, 47]. Given any generative modelp(o, x;θ) =p(o|x;θ)p(x;θ)and approximated posteriorq(o|x;λ),predictive coding now commonly refers to the hypothesis that the brain performs gradient descent onθ,λto maximize the ELBO of q[32]. However, variational Bayes is not strictly necessary for the original framework[27]."},{"citing_arxiv_id":"2604.22275","ref_index":12,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Early Preconfiguration Failure: A Novel Predictor of the Repetitive Subconcussion","primary_cat":"q-bio.NC","submitted_at":"2026-04-24T06:41:18+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"EEG measures of early cortical preconfiguration dynamics distinguish repetitive subconcussion patients from healthy controls and chronic TBI cases.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.07745","ref_index":25,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"The Cartesian Cut in Agentic AI","primary_cat":"cs.AI","submitted_at":"2026-04-09T03:03:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"LLM agents use a Cartesian split between learned prediction and engineered control, enabling modularity but creating sensitivity and bottlenecks unlike integrated biological systems.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Future of Humanity Institute, University of Oxford, 2019.url: https://www.fhi.ox.ac.uk/wp-content/uploads/Reframing_Superintelligence. pdf(visited on 01/22/2026). [24] Jiazhan Feng et al. \"ReTool: Reinforcement Learning for Strategic Tool Use in LLMs\". In:International Conference on Learning Representations (ICLR). Poster. 2026.url: https://openreview.net/forum?id=tRk1nofSmz. [25] Karl Friston. \"A theory of cortical responses\". In:Philosophical Transactions of the Royal Society B: Biological Sciences360.1456 (2005), pp. 815-836.doi:10 . 1098 / rstb.2005.1622.url:https://doi.org/10.1098/rstb.2005.1622. [26] Luyu Gao et al. \"PAL: Program-aided Language Models\". In:arXiv(2022).doi:10. 48550/arXiv.2211.10435. arXiv:2211.10435 [cs."},{"citing_arxiv_id":"2604.03263","ref_index":21,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"LPC-SM: Local Predictive Coding and Sparse Memory for Long-Context Language Modeling","primary_cat":"cs.CL","submitted_at":"2026-03-12T21:21:51+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LPC-SM is a hybrid architecture separating local attention, persistent memory, predictive correction, and control with ONT for memory writes, showing loss reductions on 158M-parameter models up to 4096-token contexts.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2507.13941","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Shared representations in brains and models reveal a two-route cortical organization during scene perception","primary_cat":"q-bio.NC","submitted_at":"2025-07-18T14:13:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"RSA on 7T fMRI during natural scene viewing identifies ventromedial and lateral occipitotemporal representational routes for scene context versus animate content, with differential alignment to vision and language models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}