Professor of Machine Learning, School of Computer Science at Carnegie Mellon University, Pittsburgh, USA 

Lead a Neurosymbolic AI Group, CMU

Title:

From Opaque Representations to Causal Concepts: A Unified Theory of Concept Extraction

Abstract:

Modern AI systems encode their knowledge in dense, opaque representations, which is a fundamental barrier to the interpretable, causally grounded reasoning that neuro-symbolic and agentic AI demand. Concept extraction methods like sparse autoencoders attempt to recover meaningful symbolic concepts from these representations, but when should we trust the concepts they find? In this talk, we present a unified theoretical framework that recasts concept extraction as a generative model identification problem, yielding a meta-theorem that reduces identifiability to a simple geometric condition on the intersection of two sets. This result clarifies the guarantees, and failure modes, of widely used unsupervised extraction methods. We then show how the framework extends naturally when we move beyond the purely unsupervised setting: lightweight causal side information, such as known intervention targets or environment labels, can dramatically strengthen identifiability, connecting concept extraction to recent progress in causal representation learning. The upshot is a principled path from raw neural representations to the kind of causally meaningful, human-interpretable concepts that trustworthy neuro-symbolic systems require.

Bio: 

Pradeep Ravikumar is a Professor in the Machine Learning Department, School of Computer Science at Carnegie Mellon University. He is a Sloan Fellow, a Siebel Scholar, a recipient of the NSF CAREER Award, and a co-editor-chief of the Journal of Machine Learning Research. His recent research interests are in neuro-symbolic AI, combining statistical machine learning, and symbolic and causal learning.

Head of Institute, Vienna University of Economics and Business

Professor, Information Systems and Business Engineering, Department for Information Systems and Operations Management, Vienna, Austria

Title: TBD

Abstract:  TBD

Bio: 

Prof. Dr. Marta Sabou is a professor for “Information Systems and Business Engineering” at the Department for Information Systems and Operations Management, WU.

Prior to this she was an FWF Elise-Richter Fellow at the Vienna University of Technology (TU). At TU she lead the Semantic Systems Research Lab which performs foundational and applied research in the area of information systems enabled by semantic (web) technologies. She has also held positions as Research Fellow at the Knowledge Media Institute (Open University, UK), Assistant Professor at the Department of New Media Technology (MODUL University, AT) and Key Expert in Semantic Technologies (Siemens).

Her work is situated at the confluence of Semantic Web and Human Computation research areas. She is an accomplished academic (over 100 peer-reviewed papers, h-index 45) and takes an active role in the Semantic Web research community. She acts as an editorial board member for three journals that publish Semantic Web research (SWJ, IJSWIS, JoDS) and has been engaged in several senior conference organization activities, including: Workshop and Tutorial Chair at ISWC’2022; Knowledge Graph Track co-chair at ESWC’2021; WebScience Track co-chair at WWW’16; Resources Track co-chair at ISWC’16 and program co-chair for ESWC’15 and iSemantics’2013.

Assistant Professor, University of Toronto

Research Scientist, Max Planck Institute 

Founder, EuroSafeAI

Title: Multi-Agent LLMs to Assist Causal Reasoning in Science

Abstract:  TBD

Bio: 

Zhijing Jin (she/her) is an Assistant Professor in Computer Science at the University of Toronto, and also a Research Scientist at Max Planck Institute in Germany. She is a faculty member at the Vector Institute, a CIFAR AI Chair, an ELLIS advisor, and faculty affiliate at CHAI at UC Berkeley, Schwartz Reisman Institute in Toronto, and Future of Life Institute. She co-chairs the ACL Ethics Committee, and the ACL Year-Round Mentorship. Her research focuses on Causal Reasoning with LLMs, and AI Safety in Multi-Agent LLMs. She has received the ELLIS PhD Award, three Rising Star awards, two Best Paper awards at NeurIPS 2024 Workshops, two PhD Fellowships, and a postdoc fellowship. She has authored over 100 papers, many of which appear at top AI conferences (e.g., ACL, EMNLP, NAACL, NeurIPS, ICLR, AAAI), and her work have been featured in CHIP Magazine, WIRED, and MIT News. She co-organizes many workshops (e.g., several NLP for Positive Impact Workshops at ACL and EMNLP, and Causal Representation Learning Workshop at NeurIPS 2024), and leads the Tutorial on Causality for LLMs at NeurIPS 2024, and Tutorial on CausalNLP at EMNLP 2022. See more info at zhijing-jin.com