NVIDIA research papers are on fire recently!
This is a dev post classified by Jev as Other (a free resource), kept by the Dev Radar because it carries real work, not commentary.
NVIDIA research papers are on fire recently! Here is another interesting paper where they give full-duplex speech models tool calls. (bookmark it) Commercial duplex voice models complete 31 to 51 percent of grounded customer-service tasks under clean conditions. Text agents like GPT-5 reach 85 percent on the same tasks in text mode. Most of what a voice agent loses, it loses in the speech pipeline. The fix routes the decision out of the speech model. The duplex frontend learns to emit a delegation token, forwards streaming transcripts to a text backend LLM for the tool call, and receive
Posted by elvis (320.4k followers) 1 h ago · 11 likes · 2.1k views · view the original post on X. Kept by the Dev Radar as Other. Tools mentioned: academy.dair.ai.
More dev work like this
- NetEase-Youdao releases Confucius4-R2T2, a true-streaming ASR model for live captions,… — @ModelScope2022
- Wow, Step 5 preview is looking really good on benchmarks. — @ItsmeAjayKV
- How Claude is Uplifting Biomolecular Modeling! #BigData #Analytics #DataScience #AI… — @gp_pulipaka
- Spacetime and Geometry. #BigData #Analytics #DataScience #AI #MachineLearning #IoT #IIoT… — @gp_pulipaka
- 🚨BREAKING: China's StepFun has officially launched Step 5 Preview, a 600B MoE model… — @choblin29
- poor guy claim to have built Jev a year ago but no one cared, and now Jev stole all the… — @kunchenguid
- Laya is the open-source Jev that already beats close Jev on latency and calibration. — @0x0SojalSec
- We’ve evaluated NVIDIA GR00T N1.7 on VLA-Replica! Check out Alex @alexhuang1029's post… — @YuXiang_IRVL
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 15.3k posts from 4.8k X accounts over the last 21 days, 1.7k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-20 10:05 UTC. Full method.