Search papers, labs, and topics across Lattice.
Affiliation:
3
0
8
XYZFlow achieves up to 8.5X speed improvements in generative modeling without compromising image quality, redefining the efficiency landscape in high-fidelity image generation.
SymbOmni not only outperforms existing models in visual generation but also reduces token consumption significantly, setting a new benchmark for cumulative learning in AI.
PEFT methods aren't just about downstream accuracy; they have distinct "stability-plasticity profiles" that reveal how well they retain general capabilities, and most overshoot the optimal balance anyway.
