@leeoxiang: Decision-making models like JEV bring new possibilities to VoiceAgent, and jev is extremely accurate for turn-taking de…
Summary
作者讨论了 JEV 这类决策模型在 VoiceAgent 中的新可能性，认为其在轮次切换检测上非常精准，并列举了若支持判断用户是否说完、是否打断、情绪识别、是否拒绝识别及是否调用工具等能力，可显著提升语音助手体验，甚至无需端到端模型。
Similar Articles
What Jev & Jev-like models are actually good for in phone voice bots
作者以语音 AI 编排平台产品负责人的视角，分析 Jev 及同类分类模型在电话语音机器人中的实际用途，并梳理了 Laya、Clef、CMF、Nimble、Kev 等竞品生态。文章指出单一 LLM 无法独立支撑生产级对话，分类模型在延迟、成本和结构化输出上仍不可或缺。
Chinese-Jev: Bringing System One Model to Chinese-Language Tasks
This paper introduces Chinese-Jev, a System One model designed to improve decision-making accuracy and efficiency for Chinese-language tasks, with domain-specific fine-tuning and a new benchmark, CJ-Bench, for evaluation.
@bojie_li: I want to change my perspective on Jev-type models a bit. When it was first released, I thought it was just a classific…
作者重新评估Jev类模型的价值，认为随着模型足够快和便宜，原本靠if-else拼接的业务逻辑、实时语音交互、计算机操作和机器人决策都可以交给System 1模型处理，形成SOTA后台深思考模型与System 1实时模型分工的新范式。
Been experimenting with Jev — interesting approach to AI agents
The author discusses experimenting with Jev, a tool for AI agents focused on decision-making, which claims significant speed and cost benefits compared to using large language models for all tasks.
@leeoxiang: A real-time decision-making model for audio and video—there are so many possible use cases. We put together a few demos to give everyone a feel for them. This will usher in a wave of VoiceAgent and embodied AI applications. https://realtime-omni.dot.cc
Introduces an online demo site for clef-omni, a real-time audio-video decision-making model. Through eight interactive experiments, the site displays the model’s understanding of audio-video inputs, its decisions, and associated probabilities in real time. The author believes this will help bring VoiceAgent and embodied intelligence applications into practice.