Search papers, labs, and topics across Lattice.
The Pennsylvania State University
2
0
3
1
Memory-augmented LLMs get a strategic upgrade: MemMA uses multi-agent reasoning to proactively guide memory construction and repair, leading to significant performance gains.
LLMs analyzing binaries aren't just spitting out tokens – they're exhibiting surprisingly structured reasoning patterns like "early pruning" and "targeted backtracking" that could revolutionize how we understand and control these systems.