Search papers, labs, and topics across Lattice.
OPPO AI Center
3
0
8
Gradient explosions in token-level distillation are tamed by a novel normalization technique, leading to robust improvements in multimodal reasoning tasks.
MiniMax-M2 proves that massive parameter counts don't always translate to better agentic performance; strategic activation of a smaller subset can unlock frontier-level intelligence.
VLMs can achieve up to 4.2x faster inference by simply skipping redundant pixels before they even enter the Vision Transformer.
