Search papers, labs, and topics across Lattice.
2
0
5
0
Video-LLMs still struggle to grasp the nuances of esports, failing to break 72% accuracy on a new benchmark designed to test perception and reasoning in fast-paced virtual environments.
Scaling up avatar pre-training to 1M in-the-wild videos unlocks emergent generalization capabilities like relightability and garment support, even without direct supervision.
