Search papers, labs, and topics across Lattice.
Northwestern University
5
0
7
Local Branch Routing enables language models to leverage contextual evidence for decision-making without the computational burden of full solution searches, leading to substantial improvements in reasoning accuracy.
Current VLMs miss crucial transition-level physics, but APT-Tune teaches them to learn causal transitions without forgetting event-level context.
By focusing on correcting "near-miss" answers, REVES achieves a remarkable +6.5 point improvement over standard RL methods, showcasing a new way to enhance LLM reasoning without extensive computational costs.
Achieving superior annotation efficiency and task success rates, AnnotateAnything revolutionizes how 3D assets are prepared for robot manipulation.
MagicSim revolutionizes robot learning by merging diverse world construction and execution into a single, efficient framework that enhances both evaluation and interaction capabilities.
