Controllable Hypothesis Generation for Abductive Reasoning
Explore CtrlHGen, a novel framework for controllable logical hypothesis generation improving abductive reasoning in knowledge graphs.
InfantAgent-Next: Multimodal AI for Automated Computer Interaction
Discover InfantAgent-Next, a multimodal AI agent using text, images, audio, and video for efficient automated computer interaction and task solving.
Preference Goal Tuning: Efficient Control for Frozen AI Policies
Discover Preference Goal Tuning, a post-training method that optimizes frozen AI policies for better task adaptation and robust performance with minimal da...
Koopman-Assisted Reinforcement Learning for Control Theory
Discover how Koopman-assisted reinforcement learning simplifies complex control systems with state-of-the-art algorithms and improved performance.
Persistent Visual Memory Boosts LVLMs Accuracy & Perception
Discover how Persistent Visual Memory enhances visual perception and accuracy in Large Vision-Language Models by preventing visual signal dilution.