Search papers, labs, and topics across Lattice.
Peking University S Stepfun, Beijing University of Posts and Telecommunications
2
0
5
TensorCast reveals that decoupling tensor management from computation can boost performance by over 90% in multi-turn interactions, challenging the status quo of LLM infrastructure.
Forget specialized architectures: StepAudio 2.5 proves a single audio-language foundation, shaped by RLHF, can dominate ASR, TTS, and real-time dialogue simultaneously.
