Pareto-Optimal Synthesis Planning with MORetro* Algorithm
Discover MORetro*, the multi-objective algorithm optimizing cost, sustainability, toxicity, and yield in chemical synthesis planning.
Model-Driven Policy Optimization with Stochastic Exploration
Discover how Model-Driven Policy Optimization enhances differentiable simulators using adaptive stochastic exploration for superior decision-making.
LiteGUI: Efficient Compact GUI Agents via Reinforcement Learning
Discover LiteGUI, a breakthrough in lightweight GUI agents using reinforcement learning for superior on-device performance and multi-solution task handling...
Efficient Data Selection for Multimodal Models with OST
Discover OST, a novel incremental optimization method that boosts multimodal model training efficiency while cutting costs and improving performance.
Bounded Fitting in Expressive Description Logics Explained
Explore bounded fitting for expressive description logics with PAC guarantees, enabling efficient learning of complex logical formulas in AI.