Search papers, labs, and topics across Lattice.
2
0
4
Context compaction in agentic RL can run up to 5x faster simply by streaming the KV cache instead of flushing it鈥攁ccidentally turning standard LLMs into recurrent agents that preserve evicted context purely through RL.
Defensive poisoning can effectively clear over half of original backdoors in LLMs, but the dynamics of trigger recognition reveal deeper vulnerabilities.
