Search papers, labs, and topics across Lattice.
University of Toronto, Vector Institute
3
0
7
Forget fixed agent slots and quadratic attention: Gamma-World uses simplex embeddings and sparse hubs to generate interactive multi-agent environments with better fidelity and control, even generalizing from 2 to 4 players without retraining.
Achieve subject-driven image generation that actually understands both text prompts and subject identity by squeezing more capacity out of multimodal LLMs.
You can slash the compute cost of visual geometry transformers by 85% without sacrificing accuracy by intelligently pruning redundant tokens across frames and within layers.
