Search papers, labs, and topics across Lattice.
4
0
9
0
A novel defense strategy reduces VLA robot failure rates from 100% to an average of 28.6% against sophisticated physical attacks, highlighting a critical vulnerability in robotic systems.
High-weight neurons in neural networks are not always the most important, with significant contributions also coming from low-weight neurons, reshaping our understanding of neuron roles in model performance.
Forget fixed workflows: SEMAG's self-evolving agents dynamically adapt their coding process and even upgrade their backbone LLM, leading to state-of-the-art code generation performance.
Forget RLHF and massive datasets: SAGE co-evolves reasoning abilities in LLMs using only a small seed set and a clever quartet of self-improving agents.
