Liquid at ICML 2024

ICML Publications co-authored by the Liquid AI Team:

• Mechanistic Design and Scaling of Hybrid Architectures
• State-Free Inference of State-Space Models: The *Transfer Function* Approach
• Position: Future Directions in the Theory of Graph Machine Learning
• The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof (best paper at the HiLD workshop)
• Towards a theory of learning dynamics in deep state space models
• Growing Q-Networks: Solving Continuous Control Tasks with Adaptive Control Resolution
• Large Scale Dataset Distillation with Domain Shift
• LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery
• RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation

‍