Search papers, labs, and topics across Lattice.
3
0
6
VLMs can learn to actively reason and plan in 3D environments by distilling view graphs from self-exploration trajectories, enabling them to surpass even larger models like GPT-4 Pro and Gemini 1.5 Pro on interactive view planning.
LLM agents can appear to reason well (high entropy) while completely ignoring the input, and mutual information is a far better metric for catching this failure.
Robots can now learn from their mistakes in real-time via a novel reflective planning framework, leading to significant performance gains in long-horizon tasks.
