Lapito
PulseAugur coverage of Lapito — every cluster mentioning Lapito across labs, papers, and developer communities, ranked by signal.
-
New LAPO method enhances multi-turn search reasoning in AI
Researchers have developed LAPO, a novel method for improving reinforcement learning in multi-turn search reasoning. LAPO uses backward leave-one-turn attribution to evaluate the contribution of each search turn, even i…
-
New research details sample efficiency of Inverse Dynamics Models in imitation learning
A new research paper explores the sample efficiency of Inverse Dynamics Models (IDMs) in semi-supervised imitation learning. The study demonstrates that VM-IDM and IDM labeling methods learn the same policy in a limitin…
-
New MaskLAM Method Enhances Embodied Agent Training
Researchers have developed a new method called MaskLAM to improve the training of embodied agents using latent action models. This technique addresses the issue of action-correlated visual distractors in videos, which c…