Search papers, labs, and topics across Lattice.
5
0
8
5
Sparse updates in on-policy distillation can match full performance with significantly reduced training overhead, challenging conventional wisdom about dense parameter updates.
LLM judges in multi-stakeholder settings suffer from "weighting noise" that gets *worse* as you add more stakeholders, but fixing weights upfront can stabilize the process.
Frontier LLMs still struggle with preference coverage and group fairness when planning travel for multiple users, revealing a critical gap in real-world agent capabilities.
Current reward models struggle to distinguish good vs. bad agent behavior in complex tool-using scenarios, especially over long horizons, revealing a critical gap in alignment research.
Instead of forcing modalities to imitate each other, IIBalance lets each modality contribute according to its intrinsic information budget, leading to better multimodal fusion.
