A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
HDFlow introduces a hierarchical diffusion-flow planning framework for long-horizon robotic assembly, leveraging a structured latent space to improve task decomposition and execution.
Unknown
This paper introduces structured preference optimization to generate and plan long-horizon tasks in vision-language models, improving task decomposition and execution.
Kyujin Han, Seungjoo Shin, Sunghyun Cho
Introduces TriLayer dataset and DBL-Diffusion framework for explicit layered video representation, improving object insertion and layer decomposition.
Tom Dietterich
Introduces the MAXQ decomposition for hierarchical reinforcement learning, enabling faster convergence via state abstractions and recursively optimal policies.