Search papers, labs, and topics across Lattice.
6
0
11
0
EviGraph boosts the reliability of autonomous research agents by ensuring every claim is grounded in a validated evidence chain, leading to a 40% increase in claim support.
Synthesizing realistic 3D hand-object interactions from just a single image and text instruction could revolutionize AR/VR applications by enabling seamless integration of dynamic human behaviors.
Native computer use can be achieved at scale, enabling agents to outperform leading systems while significantly enhancing security against adversarial attacks.
Verification of coding agent outputs is now the bottleneck, not generation, and targeted design can significantly enhance performance while curbing reward hacking.
RLVR's reasoning boost isn't just about more data – it's a Goldilocks problem: too easy and LLMs skip the reasoning, too hard and they break down, but just right and they become reasoning powerhouses.
Ditch the costly process supervision: EVOM trains LLMs to generate optimization code by treating solvers as deterministic reward functions, enabling zero-shot solver transfer and efficient adaptation.
