Search papers, labs, and topics across Lattice.
2
0
6
0
Open-source models can now rival GPT-4 in spatial reasoning, thanks to a novel two-stage training framework that grounds LLMs in topological anchors.
Prompt leakage attacks on multi-tenant LLMs are far more efficient than previously thought: a new RL-based method reconstructs prompts with over 12x fewer requests.
