Almanac
model

Moshi

modelactiveprovisionalmoshi-7ca126ac·2 events·first seen 7d ago

Aliases: Moshi

Co-occurring entities

More like this (12)

Recent events (2)

5arXiv · cs.CL·7d ago·source ↗

RL-based alignment improves interactivity in full-duplex spoken dialogue models

Researchers propose a post-training alignment method using reinforcement learning to improve interactivity in full-duplex spoken dialogue models, which can listen and speak simultaneously. The method addresses four canonical axes of interactivity—pause handling, turn-taking, backchanneling, and user interruption—each with axis-specific reward functions, plus an LLM-based reward to prevent semantic degradation. The approach is applied to two open-source models, Moshi and PersonaPlex, showing consistent improvements in both offline and real-time multi-turn evaluation.

6arXiv · cs.CL·2d ago·source ↗

BayLing-Duplex: Native full-duplex speech dialogue using a single autoregressive LLM

Researchers introduce BayLing-Duplex, a speech language model that achieves native full-duplex interaction — simultaneous listening and speaking — using a single autoregressive LLM with no auxiliary VAD or turn-taking module. Built by fine-tuning GLM-4-Voice on 400K samples plus a lightweight DPO stage, it reaches 92% turn-taking success and 100% interruption success on InstructS2S-Eval, and improves speech-response quality substantially over Moshi. The approach adds only special tokens to the standard vocabulary, making it portable across LLM architectures without architectural changes.