Arkananta@syauqi-nabil-tasri
Research · Works in progress

SwaraTTS: latent flow matching for speech

Deep Learning ResearcherMar 2026Avalon AI x RISTEK UIWorks in progress
  • A low-latency neural speech synthesizer called SwaraTTS utilizes latent flow matching to generate high-quality audio efficiently with minimal solver steps.
PyTorchDiffusionFlow MatchingCNFTTS

About

NH-LoRA is a rehearsal-free class-incremental learning method built on a frozen Vision Transformer and parameter-efficient low-rank adaptation. It separates reusable cross-task knowledge from task-specific expandable memory, then uses a task-aware planner to control structural decisions such as reuse, rank expansion, or new-slot creation. During learning, sparse routing and post-task consolidation help balance plasticity and stability while keeping parameter growth under control.

Links