Search papers, labs, and topics across Lattice.
2
0
5
Achieve up to 10.6% performance gains in prompt highlighting while halving fluency costs by steering LLMs with PRISM-Δ, a method that decomposes cross-covariance differences to find discriminative directions.
Visuomotor policies can learn to ignore distracting visual variations simply by preprocessing raw RGB images into task-aware, semantic-geometric representations *before* feeding them to the policy.
