LLM to Agent Safety: Emerging Technical and Societal Risks IVADO Workshop: Deploying Autonomous Agents: Lessons, Risks, and Real-World Impact Nov 2025 Limits of Transformers in Reasoning D.E.Shaw (NYC) Sept 2025 Inference Time Compute / Reasoning The Armenian LLM Summer School 2025 July 2025 OMEGA: Can LLMs Think Outside the Box in Math? Apple Reasoning and Planning Workshop July 2025 Panel on AI Reasoning Cross Future AI & Technology Summit July 2025 Faith and Fate: Limits of Transformers in Reasoning Cross Future AI & Technology Summit July 2025 Computer Use Agents Workshop (ICML 2025) ICML 2025 July 2025 Data in Generative Models Workshop (ICML 2025) ICML 2025 July 2025 Does Scaling Guarantee Trustworthy LLMs? MBUZAI May 2025 Trustworthy Foundation Models Panel MBUZAI Panel with Tomas Mikolov, Hakim Hacid, and Tongliang Liu May 2025 Panel: Women in ML (ICLR 2025) Women in ML April 2025 Podcast: Limits of Transformers Podcast Women in AI March 2025 Causality WorkshopBarbados In-Context Learning in LLMs: Potential and Limits Causality in the Era of Foundation Models Workshop, Barbados Feb 2025 IASEAIParis Red-teaming and Safeguarding LLMs International Association for Safe and Ethical AI (IASEAI), Paris Feb 2025 Inference-time Algorithms for LLMs Panel (NeurIPS 2024) NeurIPS Tutorial Panel w. Jacob Foerster, Noam Brown, Beidi Chen, and Rishabh Agarwal Dec 2024 Language Gamification Panel (NeurIPS 2024) NeurIPS Panel w. Aaron Courville, Alane Suhr, Tom Schaul, Marc Lanctot, Tom Griffiths, and Sam Devlin. Dec 2024 In-Context Learning in LLMs: Potential and Limits Language Gamification Workshop (NeurIPS 2024) Dec 2024 Safety Benchmarks Panel MLCommons Panel w. Ion Stoica, April Chen, and Wan Sie Lee. Dec 2024 Agentic Safety Working Group Mozilla & Columbia Convening Nov 2024 University of Cambridge Faith and Fate: Limits of Transformers LLMs University of Cambridge May 2024 Princeton University Limits of Generative AI Models and Societal Implications Princeton University Dec 2023 Alan Turing InstituteLondon Faith and Fate: Limits of Transformers on Compositionality The Alan Turing Institute Nov 2023 University of Edinburgh Faith and Fate: Limits of Transformers on Compositionality University of Edinburgh Nov 2023 SAIL Workshop Faith and Fate: Limits of Transformers on Compositionality SAIL Workshop Oct 2023 University of Pittsburgh Faith and Fate: Limits of Transformers on Compositionality University of Pittsburgh Oct 2023 FLANN Seminar Faith and Fate: Limits of Transformers on Compositionality FLANN Seminar Sep 2023 Stanford NLPSeminar Towards Building Faithful Conversational Models Stanford NLP Seminar Aug 2022 Amazon ResearchSeattle FaithDial: A Faithful Benchmark for Information-Seeking Dialogue Amazon Research, Seattle June 2022 Google ResearchNew York FaithDial: A Faithful Benchmark for Information-Seeking Dialogue Google Research, NYC May 2022 DeepMindMontréal Evaluating Consistency in Dialogue Systems DeepMind Montreal Dec 2019
