Search papers, labs, and topics across Lattice.
4
0
6
7
FilmBench reveals that leading video generation models fall short of cinematic standards, scoring significantly lower than on traditional benchmarks, which could redefine how we evaluate AI-generated video quality.
Existing text-to-image benchmarks miss the mark on real-world artistic creation, but Qwen-Image-Bench finally provides a creator-centric evaluation that reliably distinguishes state-of-the-art models.
DiT activations are far more amenable to semi-structured sparsity than weights, unlocking significant inference speedups without sacrificing generation quality.
Stop treating diffusion workflows as monolithic black boxes: LegoDiffusion unlocks 3x higher throughput by decomposing them into independently scalable microservices.
