Lu-Jun Li

HINT-Plan employs Vision Language Models to anticipate high-level human intentions from third-person image observations, convert them into goal states, and solve joint task-planning problems, and shows the effectiveness of explicitly incorporating inferred human intentions into formal multi-agent task planning for proactive human-aware robot decision-making.

LLMs can maintain long-context performance even with aggressive KV-cache eviction by learning to predict token importance and compressing evicted tokens into a latent memory.