Search papers, labs, and topics across Lattice.
Affiliation:
5
0
7
4
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.
Geometry-guided width allocation in Transformers can lead to substantial improvements in model performance, reducing validation loss more effectively than traditional methods.
Retaining only the tangential component of the feed-forward network can preserve model quality while enhancing prediction accuracy in Transformer dynamics.
Drifting Models get a friction boost: DMF matches or beats Optimal Flow Matching on FFHQ image translation while slashing training compute by 16x.
LLM-as-a-Judge accuracy hinges on temperature settings, revealing a task-dependent sweet spot that defies the common practice of fixed values like 0.1 or 1.0.
