Tag
This paper introduces Latent On-Policy Self-Distillation (LOPD), a method that makes the teacher's privileged context learnable end-to-end from experience, providing dense token-level supervision to enhance agent performance and efficiency in agentic tool use and code generation.
GRAB uses a GNN encoder to convert relational tables into latent tokens for frozen LLMs, achieving significant performance gains in multi-table question answering.
Surflo is a feed-forward 3D reconstruction model that compresses unposed RGB views into latent tokens and decodes consistent 3D surface points via flow matching, enabling variable-resolution output and outperforming existing methods in speed.