Search papers, labs, and topics across Lattice.
2
16
4
7
Forget finetuning: TTA-Vid adapts video reasoning models to new datasets *during inference* using test-time reinforcement learning, achieving state-of-the-art results without any labels.
A new 2B parameter vision-language model, Granite Vision, rivals larger models on visual document understanding tasks while offering a transparent and commercially-friendly open-source license.
