Clinical & Conference Publications

Alzheimer's Research.

Sixteen abstracts certified at the Alzheimer's Association International Conference 2026 in London. Fifteen accepted at AD/PD 2027 in Barcelona. Methods grounded in 29 NeurIPS 2026 workshop papers across drug discovery and biomedical AI.

16 AAIC 2026 Certified Posters 15 AD/PD 2027 Accepted Abstracts 29 NeurIPS 2026 Workshop Papers Certified by the Alzheimer's Association
AAIC 2026 · London

16 Certified Posters — AAIC 2026, London

Sixteen abstracts presented as In-Person Posters at the Alzheimer's Association International Conference® (AAIC®), July 11–15, 2026, London, United Kingdom. All sixteen certified by the Alzheimer's Association via the official cOASIS abstract platform.

AAIC 2026 · LondonConference sitePOSTER

Fluid Biomarkers of Pericyte Injury for Precision Vascular Subtyping

Biomarkers
AAIC 2026 · LondonConference sitePOSTER

Neuro-Symbolic AI for Alzheimer's Disease: Physics-Informed Biomarker Prediction and Verifiable Intervention Planning

Biomarkers
AAIC 2026 · LondonConference sitePOSTER

Neuro-Symbolic Recursive Self-Verification for Alzheimer's Disease Modeling: Anchoring AI in Biological Physics

Biomarkers
AAIC 2026 · LondonConference sitePOSTER

Reinforcement Learning with World Models for Optimizing Alzheimer's Disease Treatment Timing and Dosing

Drug Development
AAIC 2026 · LondonConference sitePOSTER

Reinforcement Learning from Verifiable Rewards in CNS Drug Optimization

Drug Development
AAIC 2026 · LondonConference sitePOSTER

Co-Evolving Virtual Cell Models and Perturbation Planners for Alzheimer's Disease Drug Discovery

Drug Development
AAIC 2026 · LondonConference sitePOSTER

Execution-Grounded AI Scientist for Autonomous Alzheimer's Drug Target Discovery

Drug Development
AAIC 2026 · LondonConference sitePOSTER

Coherence-Validated Causal World Models for Multi-Scale Alzheimer's Disease Progression and Pharmacologic Reversal

Drug Development
AAIC 2026 · LondonConference sitePOSTER

AI-Driven Physicochemical Optimization of Allosteric NAMPT Modulators: From Generative Chemistry to Brain-Penetrant Therapeutics

Drug Development
AAIC 2026 · LondonConference sitePOSTER

Recursively Optimizing AI Swarms for Precision Target Discovery: A Persistent-Memory Approach to Neurodegeneration

Basic Science & Pathogenesis
AAIC 2026 · LondonConference sitePOSTER

Dynamic Causal Discovery: Open-Ended Mapping of Neuroinflammatory Pathways

Basic Science & Pathogenesis
AAIC 2026 · LondonConference sitePOSTER

Iterative Self-Critique for Uncovering Cryptic Epistasis in Alzheimer's: Multi-Hop Genomic Reasoning via Monte Carlo Tree Search

Basic Science & Pathogenesis
AAIC 2026 · LondonConference sitePOSTER

Self-Improving Discovery Agents in AI-Driven Neurodegenerative Disease Research

Basic Science & Pathogenesis
AAIC 2026 · LondonConference sitePOSTER

Hierarchical Disease-State Generators for Neurodegenerative Genomics: Simulating Multi-Omic Interventions

Basic Science & Pathogenesis
AAIC 2026 · LondonConference sitePOSTER

Neuro-Symbolic Ideation Engines for Alzheimer's Therapeutics: Preventing Biological Hallucinations in Autonomous Discovery

Basic Science & Pathogenesis
AAIC 2026 · LondonConference sitePOSTER

Test-Time Scaling and Self-Verification for Precision Alzheimer's Diagnostics: Thinking Slower to Think Better

Clinical Manifestations
AD/PD™ 2027 Barcelona

15 Accepted Abstracts — AD/PD 2027, Barcelona

Fifteen abstracts accepted for Paper Poster + ePoster presentation at the AD/PD™ 2027 International Conference on Alzheimer's & Parkinson's Diseases, Barcelona, Spain, 16–20 March 2027. Accepted, not yet presented. Data sources not publicly described.

AD/PD 2027 · BarcelonaConference siteACCEPTED

Plasma-CSF Concordance of 129 Neurodegeneration Proteins: Only pTau-217 Variants Translate

Biomarkers
AD/PD 2027 · BarcelonaConference siteACCEPTED

Plasma pTau217 Platforms Perform Equivalently and Outperform pTau181 for Detecting CSF Amyloid Positivity

Biomarkers
AD/PD 2027 · BarcelonaConference siteACCEPTED

Plasma pTau217, Aβ42-to-Aβ40 Ratio, NfL, and GFAP Improve CSF Amyloid-Positivity Discrimination Beyond Clinical and Genetic Predictors

Biomarkers
AD/PD 2027 · BarcelonaConference siteACCEPTED

Cross-Platform CSF Proteomics: ACHE and YWHAE Replicate on Aptamer and Mass-Spectrometry Platforms

Proteomics
AD/PD 2027 · BarcelonaConference siteACCEPTED

CSF proteomics study · title available on request

Proteomics
AD/PD 2027 · BarcelonaConference siteACCEPTED

Serum Phosphatidylcholines and Serotonin Differ in Alzheimer Dementia But Add No Incremental Classification Value

Metabolomics
AD/PD 2027 · BarcelonaConference siteACCEPTED

Network Propagation from Alzheimer-Associated Genes Enriches Therapy Controls and Prioritizes Kinase and Phagocytosis Pathways

Genomics
AD/PD 2027 · BarcelonaConference siteACCEPTED

Gradient Boosting Matches Leading TADPOLE Challenge Submissions for Diagnosis But Not for ADAS-COG13 Forecasting

Disease progression modelling
AD/PD 2027 · BarcelonaConference siteACCEPTED

Causal Multimodal Digital Twins for Treatment-Relevant Neurodegeneration Trajectories

Disease progression modelling
AD/PD 2027 · BarcelonaConference siteACCEPTED

Group-Conditional Conformal Calibration Improves APOE4 Homozygote Coverage in Twenty-Four-Month Alzheimer Prognosis

Prognosis
AD/PD 2027 · BarcelonaConference siteACCEPTED

AI-Assisted Protocol Red-Teaming for Alzheimer's and Parkinson's Clinical Trials

Clinical trials
AD/PD 2027 · BarcelonaConference siteACCEPTED

Recursive Causal Discovery for Intervention-Relevant Alzheimer's and Parkinson's Targets

Target discovery
AD/PD 2027 · BarcelonaConference siteACCEPTED

Recursive Self-Driving Laboratories for Grounded Alzheimer's and Parkinson's Discovery

Drug discovery
AD/PD 2027 · BarcelonaConference siteACCEPTED

Neuro-Symbolic Falsification for Auditable Alzheimer's and Parkinson's Therapeutic Science

Drug discovery
AD/PD 2027 · BarcelonaConference siteACCEPTED

A Self-Improving Multimodal Design Stack for Neurodegenerative Therapeutics

Drug discovery
Methods Credentials

NeurIPS 2026 — 29 Workshop Papers

Twenty-nine papers accepted across ten NeurIPS 2026 workshops — the computational methods behind our Alzheimer's research. Drug-discovery and biomedical-reasoning work listed first.

AI for Drug Discovery (AI4DD) · 5 workshop papers

NeurIPS · AI4DDWorkshop siteWORKSHOP

A quarter of ChEMBL's potency labels are bounds — and deleting them costs more than keeping them

Drug DiscoveryChEMBLData Curation
NeurIPS · AI4DDWorkshop siteWORKSHOP

Did Feedback Cause the Gain? A Factored Replay Audit for Molecular Acquisition

Drug DiscoveryActive Learning
NeurIPS · AI4DDWorkshop siteWORKSHOP

Intra-record consistency measures provenance, not curation quality: a refuted audit of TTD

Drug DiscoveryData Auditing
NeurIPS · AI4DDWorkshop siteWORKSHOP

The Generator Is the Shift: A Cost Audit of Conformal Molecular Search

Drug DiscoveryConformal Prediction
NeurIPS · AI4DDWorkshop siteWORKSHOP

The TDC Lipophilicity benchmark is one assay — and a predictor that fits nothing retrieves 834 of 840 held-out labels exactly

Drug DiscoveryBenchmarkingTDC

Agentic AI for Biological Discovery (AgenticLS) · 11 workshop papers

Foundation Models for Temporal Systems (FMTS) · 4 workshop papers

NeurIPS · FMTSWorkshop siteWORKSHOP

Replication and Delayed Feedback in Forecasting Ensembles

ForecastingFoundation Models
NeurIPS · FMTSWorkshop siteWORKSHOP

Scenario Diversity Is Not Failure Foresight: A Frozen Audit of Quality-Diversity Scenario Libraries

ForecastingQuality-Diversity
NeurIPS · FMTSWorkshop siteWORKSHOP

A Self-Improving Forecasting Agent That Chooses Its Own Validation Window: Design Rules from a Two-Stage Pre-Registered Study

ForecastingSelf-Improvement
NeurIPS · FMTSWorkshop siteWORKSHOP

Ranking Is Not a Deployment Policy: Coverage Drift in Learned Reliability Gates for Prediction-Market Inputs

ForecastingDeployment

AI4Science · ASCI · CL4FMAgents · CLEA · CWM · NEmo · AI4ChipDesign · 9 workshop papers

NeurIPS · AI4ScienceWorkshop siteWORKSHOP

Auditing Recursive Model Promotion: Gate Interfaces, Decision Coverage, and Rejection Memory

AI for ScienceModel Auditing
NeurIPS · AI4ScienceWorkshop siteWORKSHOP

Count Every Validation: Auditing Hidden Attempts in Recursive AI Scientists

AI for ScienceValidation
NeurIPS · ASCIWorkshop siteWORKSHOP

Evidence-Gated Claim Ledgers: A Reporting Standard for Pathology Foundation Models

Biomedical AIFoundation Models
NeurIPS · CL4FMAgents ↗PDFWORKSHOP

A Retention-Gated Self-Evolving Memory for LLM Agents: Pre-Registered Backward-Transfer Evidence and Design Rules

Continual LearningMemory
NeurIPS · CLEA ↗PDFWORKSHOP

Change Passports: A Machine-Readable Standard for Auditable Artifact Promotion in Continually-Learning Agents

Continual LearningAuditability
NeurIPS · CWMWorkshop siteWORKSHOP

Belief Ledgers: Claim-Level Continual Revision for World Models

World ModelsContinual Learning
NeurIPS · NEmo ↗PDFWORKSHOP

Recursive World-Model Self-Repair in PDDL Domains: Verifier Coverage Is the Binding Constraint, and Under-Verified Loops Stall Rather Than Diverge

World ModelsSelf-Repair

NeurIPS 2025 workshop · AI for Drug Discovery and Development (AI4D3) · 1 paper

Live Presentations

Presenting at AAAI-26 · Singapore

David Scott Lewis presenting our Alzheimer's AI research at the AAAI 2026 Bridge Program — Singapore Expo.

David Scott Lewis presenting Neuro-Symbolic AI for Alzheimer's Disease at AAAI-26 Singapore Expo
ORAL · AAAI-26 LMReasoning Workshop
"Neuro-Symbolic AI for Alzheimer's Disease" — Physics-Informed Biomarker Prediction & Verifiable Intervention Planning
David Scott Lewis speaking at a scientific meeting
Cell Reports Medicine · January 2026
"Pharmacologic Reversal of Advanced Alzheimer's Disease in Mice" — the foundational paper powering our platform
ICLR 2026 & AAAI 2026 Workshops

2026 Workshop Publications — Alzheimer's & Drug Discovery Methods

Peer-reviewed workshop papers on computational methods: AAAI 2026 Bridge Program, ICLR 2026 workshops (World Models, LLM Reasoning, MLGenX, Gen²) and AI4X 2026. Full inventory on OpenReview.

ICLR 2026 workshops

ICLR · Gen² ↗PDFWORKSHOP

Hierarchical Disease-State Generators for Neurodegenerative Genomics: A Benchmark Proposal for Intervention-Conditioned Multi-omic Generation

GenomicsAlzheimer'sMulti-omics
ICLR · Gen² ↗PDFWORKSHOP

Toward Generative Virtual Cells: Co-Evolving World Models and Perturbation Planners

Virtual CellsPerturbation PlanningWorld Models
ICLR · World Models ↗PDFWORKSHOP

Reinforcement Learning with World Models for Optimizing Alzheimer's Disease Treatment Timing and Dosing

Alzheimer'sRLTreatment Optimization
ICLR · World Models ↗PDFWORKSHOP

Coherence-Validated Causal World Models for Multi-Scale Alzheimer's Disease Progression and Pharmacologic Reversal

Alzheimer'sCausal AIReversal Trajectories
ICLR · LM Reasoning ↗PDFWORKSHOP

Neuro-Symbolic Active Causal Hypothesis Testing for NAD+-Centered Alzheimer's Disease Reversal

Alzheimer'sNAD+Neuro-Symbolic
ICLR · LM Reasoning ↗PDFWORKSHOP

Latent-Implicit Thinking with Proof-Carrying Neuro-Symbolic Outputs for Biomedical Discovery

Biomedical AINeuro-SymbolicLatent Reasoning
ICLR · LM Reasoning ↗PDFWORKSHOP

Autoformalizing Biomedical Text into Verified Knowledge Graph Reasoning: A Neuro-Symbolic Architecture for Alzheimer's Disease

Alzheimer'sKnowledge GraphsAutoformalization
ICLR · MLGenX ↗PDFWORKSHOP

Active Learning for Optimal Experimental Design in Alzheimer's Disease Drug Discovery: Prioritizing NAD+-Enhancing Therapeutic Analogs via Multi-Objective Bayesian Optimization

Alzheimer'sActive LearningNAD+
ICLR · MLGenX ↗PDFWORKSHOP

Agentic Active Causal Discovery for Alzheimer's Disease Reversal: Closing the Genomic Experimental Loop

Alzheimer'sCausal DiscoveryGenomics
ICLR · MLGenX ↗PDFWORKSHOP

Uncertainty-Aware Biomarker Discovery for Alzheimer's Disease Reversal: Bridging Mouse Models and Human Translation with Conformal Prediction

Alzheimer'sBiomarkersConformal Prediction
AAAI 2026 Bridge · LMReasoning ↗PDFORAL

Neuro-Symbolic AI for Alzheimer's Disease: Physics-Informed Biomarker Prediction and Verifiable Intervention Planning

Alzheimer'sBiomarker Prediction
Adjacent Biomedical Research

Broader Drug Discovery & Verified AI-for-Science Portfolio

Peer-reviewed work surrounding the Alzheimer's focus — self-driving labs, phenotypic screening, and the verifier-first framework underlying the platform.

AI4X 2026 · Singapore ↗PDFORAL

ACHT-World: Causal World Models for Closed-Loop Self-Driving Laboratories

Self-Driving LabsCausal World Models
AI4X 2026 · Singapore ↗PDFORAL

Latent World Models of Cell Painting Data for In Silico Phenotypic Screening

Cell PaintingPhenotypic Screening
Foundational Paper

The Foundational Discovery

The peer-reviewed discovery that inspired The Reversal Initiative — demonstrating the potential for pathology reversal in vivo.

Cell Reports Medicine · January 2026

“Pharmacologic reversal of advanced Alzheimer's disease in mice and identification of potential therapeutic nodes in human brain”

Journal: Cell Reports Medicine  ·  Published: January 2026  ·  Model: 5xFAD (aggressive AD model)
Authors: Pieper Lab, Case Western Reserve / Harrington
DOI: 10.1016/j.xcrm.2025.102535
Note: This paper is the work of the Pieper Lab at Case Western Reserve / Harrington Discovery Institute. AIXC is not an author or contributor. We reference it with full attribution as the biological anchor for our computational programme.

Key Findings

Reversed amyloid plaque accumulation
Resolved tau neurofibrillary tangles
Repaired blood-brain barrier integrity
Restored cognitive function in vivo

Collaborate on Alzheimer's Research

Foundations, research labs, and hospitals — bring your scientific question, use our clinical genomics platform.

Partner With Us