We have 4 of 11 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Realtime spoken interaction demands deep reasoning, prompt responses, and fluid turn-taking. We present StepAudio 3 Realtime, an audio-language foundation model organized around a continuous listen-converse-think-act loop. Deep Perception captures rich acoustic cues to interpret user intent, while Seamless Duplex model...
An adaptive anisotropic learning-rate model is proposed that assigns each rank-one component its own effective learning rate, computed online from training-time signals and mean-normalized per module to preserve the global LR budget.
AUSO (Action-level Unified Skill Optimization), which unifies skill learning and skill use through a progressive, action-aware optimization process, and consistently improves agent performance and out-of-distribution generalization over competitive baselines.
ParaASR is introduced, an ASR system that leverages Multi-Token Prediction (MTP) to let a 4B LLM decoder emit multiple tokens per forward step and shows that decoder scaling, low-latency inference, and long-context transcription need not be competing goals when future-token proposals are anchored by the acoustic signal...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
