Search papers, labs, and topics across Lattice.
Rice University
3
0
7
SoftmaxGRPO reallocates learning signals to improve performance on challenging prompts, achieving a 68.0% success rate on Poetry with minimal reward overhead.
LLMs can autonomously discover novel neural architectures that achieve state-of-the-art performance in specialized domains, suggesting a path towards automated scientific discovery.
LLMs can now infer plausible stage layouts from unstructured text alone, opening up new possibilities for automated media production.
