Search papers, labs, and topics across Lattice.
3
0
6
Forget specialized architectures: StepAudio 2.5 proves a single audio-language foundation, shaped by RLHF, can dominate ASR, TTS, and real-time dialogue simultaneously.
Hyperfitting's surprising generation improvements aren't just temperature scaling – they stem from a "Terminal Expansion" in the final transformer block that dynamically reorders token ranks.
Forget temperature tuning: Min-$k$ sampling finds the "semantic cliff" in your LLM's logits, delivering robust and high-quality text even when other methods fall apart.
