Search papers, labs, and topics across Lattice.
3
0
5
5
UI-Venus-2 achieves unprecedented environment coverage and task reliability, paving the way for dependable multimodal GUI agents in real-world applications.
Scaling zero RL to a trillion parameters reveals that models can spontaneously develop advanced cognitive behaviors, making traditional heuristics obsolete.
VLMs can be taught to self-correct hallucinations at the token level, leading to substantial gains in reasoning accuracy across diverse benchmarks.
