Search papers, labs, and topics across Lattice.
2
0
4
3
A single interaction is all it takes for an adversary to manipulate LLM memory systems, steering outputs toward a pre-specified target with alarming precision.
Instruction-following in large reasoning models gets a serious upgrade with RAIN-Merging, a gradient-free technique that merges in instruction-tuned capabilities without wrecking the model's ability to think step-by-step.
