Exploring Chemical Space with Score-based Out-of-distribution Generation
Score-based generative models have shown promise in molecule generation, but often struggle to create truly novel candidates beyond the training distribution. MOOD (Molecular Out-Of-distribution Diffusion) is a score-based diffusion framework that enables controllable exploration of out-of-distribution chemical space without incurring additional computational costs. By integrating a property prediction network into the reverse-time SDE, MOOD effectively guides the generation toward molecules with desired novel traits such as high binding affinity, drug-likeness, and synthesizability.
Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations
Score-based generative models have achieved strong results in image and molecular generation, but applying them to graph-structured data remains challenging due to the complex interplay between node features and graph topology. In this blog, we explore GDSS (Graph Diffusion via the System of Stochastic differential equations), a model that tackles this problem by jointly modeling the evolution of node attributes and adjacency matrices through a system of coupled stochastic differential equations. Using a permutation-equivariant graph neural network and score matching, GDSS generates graphs that maintain both structural validity and semantic coherence.
Can Reward be a Key for General Intelligence?
Reward maximization has been proposed as a sufficient requirement for general intelligence, unifying abilities such as knowledge acquisition, perception, social interaction, and generalization through a single objective. In this post, I share my personal reflections on both the strengths and the limitations of this claim. To the end, in order to make progress toward general intelligence, I believe that developing methods for selecting effective reward functions and advancing techniques for interpreting learned reward functions will be essential.
Towards a Harmonious Coexistence Between Humans and Nature
The intricate relationship between human and nature has been formed throughout humanity's history. In recent centuries, human’s impact on nature has grown dramatically, leading to a significant degradation in the environment. Fortunately, in the current state, there has been a significant growth of recognition regarding the importance of protecting nature. However, we are still far from reaching the ideal state of coexistence. In order to find out how we could successfully coexist with nature, understanding human-nature interaction in depth should be preceded. Therefore, we will first start looking through the dominant view of human-nature interaction and then further stretch out to the modern view. Finally, we will briefly go through the challenges we are facing once we’re trying to coexist with nature, and the possible solutions that could handle these problems.