Search papers, labs, and topics across Lattice.
2
0
3
Naive agent-generated test feedback degrades SWE-bench performance by reinforcing shared hallucinations, but decoupling test generation from repair through role-specific RL converts a 3.9-point loss into an 11.4-point gain on open-weights models.
Steering vectors from understanding to generation in unified multimodal models can significantly enhance image synthesis, but the reverse direction fails to deliver similar benefits.
