Search papers, labs, and topics across Lattice.
National Laboratory, of the Rockies, Pacific Northwest National Laboratory, Rensselaer Polytechnic Institute, Johns Hopkins University
3
0
7
Ignoring the social dynamics of human-agent collaboration in science could stifle innovation and diversity in research outcomes.
Forget meticulously engineered reward functions – sometimes the simplest accuracy reward is all you need to make VLMs better at physics.
Swapping in the latest LLM backbone doesn't guarantee a better VLM – sometimes it just solves *different* problems.
