Search papers, labs, and topics across Lattice.
4
23
7
15
Sentiment in social-media conversations is significantly influenced by discourse moves, with specific interventions capable of mitigating negativity or amplifying hostility.
Gemma 4's unified architecture and reasoning mode enable it to outperform larger models in human-rated tasks while maintaining high efficiency.
Entropy regularization makes planning provably easy: SmoothCruiser achieves polynomial sample complexity in MDPs where standard methods fail.
TrailBlazer offers a computationally efficient Monte-Carlo planning algorithm that drastically reduces sample complexity by focusing exploration on near-optimal state trajectories within an MDP.
