AAAI-26
ORAL
The Algorithmic Alchemist: Bayesian Optimization Meets Generative AI for Accelerated Drug Discovery
David Scott Lewis, Enrique Zueco, et al.
Drug DiscoveryBayesian OptimizationGenerative AIACHT
AAAI-26
ORAL
Polyculture Agents for Financial AI: Preventing Echo Chambers in Autonomous Trading Systems
David Scott Lewis, Enrique Zueco, et al.
Financial AIMulti-AgentEcho ChambersVAP
AAAI-26
ORAL
Neuro-Symbolic Legal Reasoning with Causal Precedent Graphs
David Scott Lewis, Enrique Zueco, et al.
Legal AINeuro-SymbolicCausal Discovery
AAAI-26
POSTER
Cross-Domain Transfer of Causal Discovery: From Molecular Graphs to Financial Networks
David Scott Lewis, Enrique Zueco, et al.
Cross-DomainCausal TransferACHT
AAAI-26
POSTER
Causal Factor Discovery in Non-Stationary Financial Markets via Interventional Time Series
David Scott Lewis, Enrique Zueco, et al.
Financial AICausal FactorsNon-Stationary
AAAI-26
POSTER
BindCraft-AIXC: Structure-Aware Molecular Generation with Protein Binding Constraints
David Scott Lewis, Enrique Zueco, et al.
Drug DiscoveryBindCraftProtein Binding
AAAI-26
POSTER
Self-Falsification in Multi-Agent Research Pipelines: A Popperian Framework
David Scott Lewis, Enrique Zueco, et al.
Multi-AgentSelf-FalsificationVAP
AAAI-26
POSTER
Accelerated Ceramic Composition Design via Causal Bayesian Optimization
David Scott Lewis, Enrique Zueco, et al.
MaterialsCeramicsBayesian Optimization
AAAI-26
POSTER
Causal World Models for Robotic Manipulation: Bridging Simulation and Reality
David Scott Lewis, Enrique Zueco, et al.
RoboticsWorld ModelsSim-to-Real
AAAI-26
WORKSHOP
CycleResearcher: Autonomous Literature Review with Self-Correcting Citation Graphs
David Scott Lewis, Enrique Zueco, et al.
Research AutomationCitation GraphsMulti-Agent
AAAI-26
WORKSHOP
AI-Scientist v2: 3,000x Acceleration of Experimental Design through Autonomous Hypothesis Generation
David Scott Lewis, Enrique Zueco, et al.
AI-ScientistAutonomous ResearchAcceleration
NeurIPS 2025
POSTER
AI for Drug Discovery and Development (AI4D3): Causal Structure Learning in Protein Interaction Networks
David Scott Lewis, Enrique Zueco, et al.
Drug DiscoverySTRING v12.0Causal Discovery
ELLIS 2025
INVITED
Verified Autonomous Pipelines: Self-Falsification for Trustworthy AI-Driven Research
David Scott Lewis, Enrique Zueco, et al.
VAPSelf-FalsificationTrust
Stanford HAI 2025
INVITED
Domain-Agnostic Causal Discovery: A Unified Framework for Scientific Hypothesis Testing
David Scott Lewis, Enrique Zueco, et al.
ACHTDomain-AgnosticUnified Framework
CIKM 2025
POSTER
Physics-Informed Verification Surrogates for Autonomous Materials Discovery
David Scott Lewis, Enrique Zueco, et al.
MaterialsPINNsSurrogates
IEEE 2025
POSTER
Formal Verification of AI-Generated Legal Arguments via Neuro-Symbolic Integration
David Scott Lewis, Enrique Zueco, et al.
Legal AIFormal VerificationNeuro-Symbolic
AAMAS 2025
POSTER
Polyculture vs. Monoculture: Diversity Metrics for Multi-Agent Verification Systems
David Scott Lewis, Enrique Zueco, et al.
Multi-AgentDiversity MetricsVerification
ISMB 2025
POSTER
Causal Protein Interaction Networks for Target Identification: A STRING v12.0 Case Study
David Scott Lewis, Enrique Zueco, et al.
Drug DiscoverySTRINGTarget ID
IROS 2025
POSTER
Verified Sim-to-Real Transfer for Dexterous Manipulation via Physics-Informed Validation
David Scott Lewis, Enrique Zueco, et al.
RoboticsSim-to-RealDexterous
Stanford FinAI 2025
WORKSHOP
Regime-Aware Causal Factor Models for Robust Portfolio Construction
David Scott Lewis, Enrique Zueco, et al.
Financial AIRegime DetectionPortfolio
NeurIPS Workshop 2025
WORKSHOP
Echo Chamber Detection in LLM-Based Research Agents: Metrics and Mitigation
David Scott Lewis, Enrique Zueco, et al.
LLM AgentsEcho ChambersSafety
ICML Workshop 2025
WORKSHOP
Diffusion Models for Multi-Objective Molecular and Materials Design
David Scott Lewis, Enrique Zueco, et al.
Diffusion ModelsMulti-ObjectiveGeneration
ICLR Workshop 2025
WORKSHOP
Benchmarking Autonomous Scientific Discovery: The AIXC Evaluation Suite
David Scott Lewis, Enrique Zueco, et al.
BenchmarksEvaluationAutonomous Research