Search papers, labs, and topics across Lattice.
4
0
8
0
VLM-level feedback can transform language backbone unlearning from unreliable to robust and transferable, achieving unprecedented performance gains.
SeClaw reveals that existing benchmarks fall short in capturing the complexities of agent behavior, enabling a more nuanced evaluation of security risks in autonomous systems.
LLMs can now tell you how unsure they are about their long-form answers, thanks to a new interrogation-based uncertainty metric that actually works.
Solve SMoE load balancing at inference time without retraining by replicating heavily used experts and quantizing underutilized ones, achieving up to 1.4x imbalance reduction.
