What’s coming up at #AAAI2024?

The 38th AAAI Conference on Artificial Intelligence (AAAI2024) will take place in Vancouver, and runs from Tuesday 20 February to Tuesday 27 February. Find out about some of the main events that are taking place throughout the conference.

Invited speakers

The following distinguished invited speakers will be presenting at this year’s conference.

• Milind Tambe – ML+Optimization: Driving Social Impact in public health and conservation
• Michael Bronstein – Geometric ML: from Euclid to drug design
• Dieter Fox – Toward Foundational Robot Manipulation Skills
• Pascale Fung – Machines Make Up Stuff: Why Do Generative Models Hallucinate?
• Charles Isbell and Michael L. Littman – AI Education in the Age of AI
• Leslie Pack Kaelbling – The Role of Rationality in Modern AI
• Sarit Kraus – Smart Advice: Intelligent Agents Assisting Humans in the Super AI Era
• Yann LeCun – Objective-Driven AI: Towards Machines that can Learn, Reason, and Plan
• Elizabeth S. Spelke – How Children Learn
• Raquel Urtasun – Accelerating AVs with the next generation of generative AI

AIhub introduction to science communication

We will be holding a science communication training session on Wednesday 21 February. This will comprise a one-hour talk (starting at 2pm), and a two-hour informal drop-in session (starting at 3pm). You can find out more information here.

Tutorial and lab forum

The tutorial and lab forum will take place on 20 and 21 February. The events comprise half-day or quarter-day sessions. The topics covered are listed below, and you can find out more here.

• TH1: AI for emerging inverse problems in computational imaging
• TH2: Beyond Human Creativity: A Tutorial on Advancements in AI Generated Content
• TH3: Language Models Meet World Models
• TH4: Learning under Requirements: Supervised and Reinforcement Learning with Constraints
• TH5: User Simulation for Evaluating Interactive Intelligent Systems
• LH1: Fully Homomorphic Encryption for Privacy-Preserving Machine Learning Using the OpenFHE Library
• LH2: Introduction to MDP Modeling and Interaction via RDDL and pyRDDLGym
• TQ1: Deep Learning Methods for Unsupervised Time Series Anomaly Detection
• TQ3: Towards Out-of-Distribution Generalization on Graphs
• TQ2: Physics-Inspired Geometric Pretraining for Molecule Representation
• TH6: Combinatorial Solving with Provably Correct Results
• TH7: Knowledge Editing for Large Language Models
• TH8: Learning with Multiple Objectives Beyond Bilevel Optimization – New Foundations and Applications
• TH9: Model Reuse: Concepts, Algorithms, and Applications
• TH10: Recent Advance in Physics-Informed Machine Learning
• TH11: Zeroth-Order Machine Learning: Fundamental Principles and Emerging Applications in Foundation Models
• LH3: Measurement Layouts for Capability-oriented AI Evaluation
• TQ4: Disentangled Representation Learning
• TQ5: Distributed Stochastic Nested Optimization for Emerging Machine Learning Models
• TH12: Knowledge-enhanced Graph Learning
• TH13: Large-Scale Graph Neural Networks: Navigating the Past and Pioneering New Horizons
• TH14: Machine learning for discrete optimization: Theoretical guarantees and applied frontiers
• TH15: Privacy-Preserving Techniques for Large Language Models
• TH16: Probabilistic Concept Formation with Cobweb
• LH4: Causal Fairness Analysis
• TQ7: Advances in Robust Time-Series ML: From Theory to Practice
• TQ8: Continual Learning on Graphs: Challenges, Solutions, and Opportunities
• TQ9: Curriculum Learning: Theories, Approaches, Applications and Tools
• TQ10: Graphs Counterfactual Explainability: A Comprehensive Landscape
• LQ1: Enabling trustworthy AI with metadata tracking using Common Metadata Framework
• LQ2: Harnessing Large Language Models for Planning: A Lab on Strategies for Success and Mitigation of Pitfalls
• TH17: Experiments in Computational Social Choice Using Maps of Elections
• TH18: Formalizing Robustness in Neural Networks: Explainability, Uncertainty, and Intervenability
• TH19: Foundations, Practical Applications, and Latest Developments in Causal Decision Making
• TH20: On the role of Large Language Models in Planning
• TH21: Scalability, Robustness, and Optimization of Learning in Large Stochastic Games
• TH22: Trustworthy Machine Learning under Imperfect Data
• TQ11: Aligning Large Language Models to Low-Resource Languages
• LQ3: Digging into the Landscape of Graphs Counterfactual Explainability
• TQ12: Meta-Reinforcement Learning
• TQ13: Recent Advances in Multi-Objective Search

Bridge programme

The bridge programme brings together different communities to explore new opportunities and perspectives. The events will take place on 20 and 21 February, and are as follows:

• B1: AI for Financial Services
• B2: AI for Materials Science
• B3: Artificial Intelligence for Design Problems
• B4: Collaborative AI and modeling of humans
• B5: Constraint Programming and Machine Learning
• B6: Continual Causality
• B8: Exploring the use of Federated Learning for Data-Sensitive applications
• B9: Knowledge-guided Machine Learning: Bridging Scientific Knowledge and AI

Workshops

There are 34 different workshops and these will take place on 26 and 27 February. Click on the workshop titles below to find out more information.

• W1: Are Large Language Models Simply Causal Parrots?
• W2: AI for Credible Elections: A Call To Action with Trusted AI
• W3: AI for Digital Human
• W4: AI for Education: Bridging Innovation and Responsibility
• W5: AI in Finance for Social Impact
• W6: AI to Accelerate Science and Engineering (AI2ASE)
• W7: AI-based Planning for Cyber-Physical Systems (CAIPI)
• W8: AIBED: Artificial Intelligence for Brain Encoding and Decoding
• W9: Artificial Intelligence for Cyber Security (AICS)
• W10: Artificial Intelligence for Operations Research
• W11: Artificial Intelligence for Time Series Analysis (AI4TS): Theory, Algorithms, and Applications
• W12: Artificial Intelligence with Biased or Scarce Data (AIBSD)
• W13: Cooperative Multi-Agent Systems Decision-Making and Learning: From Individual Needs to Swarm Intelligence
• W14: Deployable AI (DAI)
• W16: EIW-III: The 3rd Edge Intelligence Workshop on Large Language and Vision Models
• W17: FACTIFY 3.0 – Workshop Series on Multimodal Fact-Checking and Hate Speech Detection
• W18: Graphs and more Complex Structures For Learning and Reasoning (GCLR)
• W19: Health Intelligence (W3PHIAI-24)
• W20: Human-Centric Representation Learning (HCRL)
• W21: Imageomics: Discovering Biological Knowledge from Images using AI
• W22: Large Language Models for Biological Discoveries
• W23: Learnable Optimization (LEANOPT)
• W24: Machine Learning for Cognitive and Mental Health
• W25: Neuro-Symbolic Learning and Reasoning in the era of Large Language Models (NuCLeaR)
• W26: Privacy-Preserving Artificial Intelligence
• W27: Public Sector Large Language Models: Algorithmic and Sociotechnical Design
• W28: Recommendation Ecosystems: \\ Modeling, Optimization and Incentive Design
• W29: Responsible Language Models (ReLM)
• W30: Scientific Document Understanding
• W31: Sustainable AI
• W32: Synergy of Reinforcement Learning and Large Language Models
• W33: Workshop on Ad Hoc Teamwork
• W34: XAI4DRL: eXplainable Artificial Intelligence for Deep Reinforcement Learning
• W35: XAI4Sci: Explainable machine learning for sciences

Technical programme

Information about the technical programme can be found here.

IAAI-24

The 36th annual conference on innovative applications of artificial intelligence
(IAAI-24) will take place from 22-24 February. View the program here.

EAAI-24

The 14th symposium on educational advances in artificial intelligence (EAAI-24) with take place on 24-25 February. View the program here.

Lucy Smith is Senior Managing Editor for AIhub.

Lucy Smith is Senior Managing Editor for AIhub.