Search papers, labs, and topics across Lattice.
6
0
10
A single capable verifier can dramatically improve terminal agent action reliability, achieving higher success rates at lower costs than simply generating more trajectories.
PhysCaP enables robots to actively infer hidden physical properties, achieving superior manipulation efficiency without additional sensors.
VAORA reduces hallucinated reasoning in VLMs by aligning visual context with action outcomes, leading to better generalization in unseen tasks.
A single universal speech enhancement model can effectively adapt to multiple latency requirements without sacrificing performance, challenging the need for specialized models.
ZPPO reveals that embedding teacher responses in prompts rather than gradients can dramatically boost the performance of small student models on challenging tasks.
SpatialClaw enables agents to dynamically compose and adapt their reasoning strategies, achieving a remarkable 11.2-point accuracy boost over traditional spatial agents.
