Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Affiliation:
2
0
5
0
Directly learning robot action policies from raw video without explicit action labels unlocks scalable world action models.
Non-generative "System One" models can beat closed-source baselines in Chinese decision tasks with a 20x speedup and 15 ms latency, proving encoder-only architectures remain radically underutilized for structured reasoning.