Search papers, labs, and topics across Lattice.
3
0
7
Context-augmented RL lets smaller MLLMs punch *way* above their weight, rivaling much larger models on reasoning tasks while dodging reward hacking.
VLMs can get a +39% boost in downstream reasoning by using translator-guided reinforcement learning to improve geometric perception, a far better result than standard supervised fine-tuning.
Cycle consistency unlocks SOTA cross-view object correspondence in videos without ground-truth annotations, even enabling test-time training.
