Search Talks

We present AlphaGeometry2, a significantly improved version of AlphaGeometry introduced in Trinh et al. (2024), which has now surpassed an average gold medalist in solving Olympiad geometry problems. To achieve this, we first extend the original AlphaGeometry language to tackle harder problems involving movements of objects, and problems containing linear equations of angles, ratios, and distances. This, together with support for non-constructive problems, has markedly improved the coverage rate of the AlphaGeometry language on International Math Olympiads (IMO) 2000-2024 geometry problems from 66% to 88%. The search process of AlphaGeometry2 has also been greatly improved through the use of Gemini architecture for better language modeling, and a novel knowledge-sharing mechanism that enables effective communication between search trees. Together with further enhancements to the symbolic engine and synthetic data generation, we have significantly boosted the overall solving rate of AlphaGeometry2 to 84% for all geometry problems over the last 25 years, compared to 54% previously. AlphaGeometry2 was also part of the system that achieved silver-medal standard at IMO 2024 this https URL. Last but not least, we report progress towards using AlphaGeometry2 as a part of a fully automated system that reliably solves geometry problems directly from natural language input.

Exactly solvable models have tremendously helped our understanding of condensed matter systems. A notable number of them are "frustration-free" in the sense that all local terms of the Hamiltonian can be minimized simultaneously. It has been particularly successful at describing the physics of gapped phases of matter, such as symmetry protected topological phases and topologically ordered phases. On the other hand, relatively little has been understood about gapless frustration-free Hamiltonians, and their ability to teach us about more generic systems. In this talk, we derive a constraint on the spectrum of frustration-free Hamiltonians. Their dynamical exponent z, which captures the scaling of the energy gap versus the system size, is bounded from below to be z >= 2. This proves that frustration-free Hamiltonians are incapable of describing conformal critical points with z = 1. Further, by a well-known mapping from Markov processes to frustration-free Hamiltonians, we show that the relaxation time for many Markov processes also scale with z >=2. This improves the previously known bound on the relaxation time scaling of z >= 7/4. The talk is based on works with Rintaro Masaoka and Haruki Watanabe.

Scientific research is facing mounting challenges: overwhelmed reviewers, fragmented expertise, an outdated and inefficient system for allocating resources, and dissemination tools that no longer match the complexity and scale of modern scientific output. In this talk, I speak both as a researcher and as the founder of a successful startup to explore what a more coherent, future-ready scientific ecosystem could look like. Drawing on real prototypes and emerging tools, I’ll outline how we might reshape the way we publish, collaborate, and share not just to fix what’s broken, but to unlock what science could become tomorrow.

In the past two years, the LLM has made significant progress in math and reasoning, but it has not been applied widely in scientific research tasks. In this talk I will give a brief introduction to our on-going efforts on building the first AI scientist platform, where all researchers in different fields can contribute to teaching the AI scientists via contributing benchmarks and contributing specialized tools. We believe that by providing AI with the real-time updates of benchmarks and research tools, we are starting to enter an era with innovation driven by new types of human-AI collaboration.

This talk explores how artificial intelligence could transform theoretical physics over the next 25 years by addressing the crucial challenge of navigating an increasingly complex scientific literature landscape. We introduce Litmaps, a platform leveraging AI and visualization techniques to accelerate literature discovery and insights. We illustrate Litmaps' current capabilities in rapidly identifying relevant connections and advancing theoretical research. We also outline critical engineering challenges, including open access to historical literature, data standardization, and managing uncertainty in AI models. Finally, we highlight the importance of collaboration among physicists, AI researchers, engineers, and entrepreneurs, to realise the AI-enhanced future of theoretical physics research.

From the start of AI, mathematical theorem proving has been an important challenge and technique. We sketch the topics of Automated and Interactive Theorem Proving and present the checking of naturally readable mathematical texts in the Naproche proof system. This involves translations between informal, semi-formal and formal mathematical languages and shows great potential for the use of new AI techniques.