Breaking Topics in AI Conference 2025 Part I скачать в хорошем качестве

Breaking Topics in AI Conference 2025 Part I

Focus Talk 1: Paula Cordero Encinar, Imperial: Sampling by Averaging: A Multiscale Approach to Score Estimation Focus Talk 2: Tolga Birdal, Imperial: Topological Deep Learning: A New Hope for Molecular Modelling and 3D Vision Flash Talk 1: Kevin Han Huang, University College London: Diagonal Symmetrization of Neural Network Solvers for the Many-Electron Schrödinger Equation Flash Talk 2: Cristiana Diaconu, University of Cambridge: Gridded Transformer Neural Processes for Spatio-Temporal Data Flash Talk 3: Hugh Dance, University College London: Efficiently Vectorized MCMC on Modern Accelerators Flash Talk 4: Yedi Zhang, University College London: Training Dynamics of In-Context Learning in Linear Attention Flash Talk 5: Lisa Alazraki, Imperial: Reverse Engineering Human Preferences with Reinforcement Learning