Search papers, labs, and topics across Lattice.
4
0
8
1
A training-free multi-agent system for UAV image understanding not only surpasses leading models in accuracy but also addresses fundamental reasoning failures in MLLM applications.
RoboTacDex reveals that a diverse dataset of 6,000 trajectories can significantly improve humanoid robot manipulation across complex tasks.
Achieving trillion-parameter performance with just 35 billion parameters by scaling agent horizons reveals a new frontier in model efficiency.
ViT-based stereo matching can rival CNNs in detail prediction and generalization to arbitrary resolutions with the right architectural choices.
