Search papers, labs, and topics across Lattice.
3
0
8
5
Persona conditioning in LLMs can be exploited to amplify inference costs by over 200 times, revealing a critical vulnerability in their deployment.
By verifying its reasoning steps both locally and globally, MiroThinker-H1 achieves state-of-the-art performance in complex research tasks, demonstrating the power of integrated verification for reliable multi-step problem solving.
Reinforcement learning can efficiently merge heterogeneous language models in federated ASR, outperforming genetic algorithms and improving character error rate.
