Search papers, labs, and topics across Lattice.
6
1
8
8
Achieving over 2x speedups in video generation without sacrificing visual quality, Sol-Attn redefines the efficiency of sparse attention mechanisms.
TOP-D transforms the unstable OPD paradigm into a stable training method that enhances performance without any extra computational burden.
Adversarial purification can be dramatically improved by focusing on patch-level semantics, leading to state-of-the-art performance in defending against adversarial attacks.
MaineCoon achieves a groundbreaking 47.5 FPS in real-time audio-visual generation, redefining the potential for social-interactive AI applications.
Aligning diffusion models with just 100 carefully selected samples can beat state-of-the-art preference optimization methods trained on thousands, and converge up to 220x faster.
By explicitly detecting and escaping "Forbidden Zones" during training, AMD unlocks significant gains in sample fidelity and training robustness for few-step generative models like SDXL.
