Search papers, labs, and topics across Lattice.
Affiliation:
6
0
9
3
This work shows that the frozen agent LLM already carries the routing signal in its own forward passes, and that two linear maps suffice to read it out with no skill text in the context, and shows that Gavel (Glance And Verdict from a frozen LLM) reads it in two steps.
A single ranking can adapt to any frame budget, improving accuracy and reducing latency without retraining the model.
AV-AIVAT enables agent evaluations to stop as soon as the evidence is sufficient, achieving a staggering 74x reduction in game requirements while maintaining statistical validity.
Reducing target-muscle activity by up to 48% during dynamic tasks could revolutionize upper-limb exoskeleton design and user experience.
Misalignment between visual evidence and predicted timestamps in video grounding can lead to substantial performance drops, but CAVE effectively bridges this gap with boundary-specific rewards.
Unleashing an LLM's inner creativity or laser-sharp logic is now as simple as turning a knob, thanks to a new distribution-matching method that avoids heuristic rewards.
