Search papers, labs, and topics across Lattice.
Affiliation:
3
1
6
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鈥攚ithout updating a single host model weight.
Unconditional image diffusion models can now perform continuous super-resolution without task-specific architectures or retraining, simply by varying the starting timestep.
Even the best LLMs still stumble on Olympiad-level math, and retrieval quality is the bottleneck for retrieval-augmented problem solving, according to the new MathNet benchmark.
