Track trials, findings, and clinical evidence as it lands.
Search papers, labs, and topics across Lattice.
University of Rochester
6
0
5
Semantic structure, not just token-level feedback, unlocks significant gains in RL-driven text-to-image prompt engineering.
AI agents can now generate and verify complex 3D worlds using executable code, outperforming leading models in human preference studies.
Inserted objects can now be made "alive" and interact realistically within videos, solving a long-standing challenge in video editing.
Heterogeneous visual agents can boost downstream performance by up to 4.9 points across diverse tasks simply by reading from a shared, self-organizing 2B memory tree—without updating a single host model weight.
Append-only memory guarantees attention collapse in long-horizon video reasoning, but actively rewriting a bounded working memory from an external filesystem boosts hard-subset task accuracy by over 20%.