Tag
This paper introduces a novel paradigm, VLM-as-probabilistic-grounder, which models uncertainty in vision-language model groundings as probability distributions for symbolic belief-space planning, enhancing robustness in partially observable settings.
YuE2 is a new AI music generation model using symbolic planning that achieves competitive performance on benchmarks like WildSongBench, outperforming or matching proprietary systems such as Suno v5.
This paper proposes a multi-role reinforcement learning framework using solver feedback to convert natural language into PDDL specifications for symbolic planning, improving success rates and faithfulness compared to existing methods.
YuE2 is an AI model that generates songs by first creating a symbolic score from lyrics and style, then rendering it into audio, achieving frontier quality competitive with Suno.