We have 3 of 7 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.
It is shown that multi-byte prediction strikes a Pareto-optimal trade-off across multiple generative tasks, instruction following, question answering, summarization, and machine translation, achieving the best trade-off between performance and inference throughput.
The central finding is that aggregate WER hides code switching behavior, and the best system by WER (an ASR model) is statistically indistinguishable from a leading audio LM on WER, yet the audio LM is significantly better on every switch localized metric.
Results show that while ALMs extract high-level meaning from stuttered speech, reasoning degrades significantly with increased usage, and instruction-guided models are instruction-guided to focus on the child, preserve clinically relevant disfluencies, and avoid adult-speech leakage.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
