Search papers, labs, and topics across Lattice.
3
0
7
2
Training on D3-Gym, a new dataset of real-world scientific tasks with verifiable environments, closes the gap between open-source and proprietary models on ScienceAgentBench by 7.8 points.
Achieve scalable and consistent multi-reference image editing by dynamically serializing reference images into a coherent latent sequence, outperforming existing diffusion-based methods.
Unleashing diffusion models' spatial reasoning potential is now possible without expensive joint training, thanks to a clever plug-and-play framework that leverages MLLMs for layout planning.
