Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
2
0
6
Driving models can achieve near-perfect performance with just one denoising step by learning to predict visual motion directly, outperforming multi-step prediction models and achieving 3.29x inference speed.
Forget specialized architectures: StepAudio 2.5 proves a single audio-language foundation, shaped by RLHF, can dominate ASR, TTS, and real-time dialogue simultaneously.