Search papers, labs, and topics across Lattice.
University of Waterloo
4
0
10
9
Mid-training with function-aware fill-in-the-middle boosts coding agent performance while preventing capability erosion in non-agentic tasks.
A unified framework reveals how different 3D data representations and learning paradigms interact, paving the way for more efficient and effective applications in 3D vision.
MiniMax-M2 proves that massive parameter counts don't always translate to better agentic performance; strategic activation of a smaller subset can unlock frontier-level intelligence.
Today's best AI agents can only complete 33% of common online tasks like booking appointments or filling out job applications, revealing a significant gap between current capabilities and real-world utility.
