Search papers, labs, and topics across Lattice.
3
0
5
Diffusion models no longer need to simultaneously plan and paint; inserting discrete "visual thought" tokens between VLMs and DiTs decouples high-level semantic reasoning from pixel synthesis for tighter alignment and direct intermediate control.
Reinforcement learning boosts multimodal performance, raising task scores and creating unexpected synergies between image generation and editing.
Frustrated with clunky architecture simulators? Akita offers a breath of fresh air with its focus on developer experience, promising faster prototyping and experimentation.
