PersonaPlex
PulseAugur coverage of PersonaPlex — every cluster mentioning PersonaPlex across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
New method suppresses spurious speech in full-duplex LLMs
Researchers have identified and addressed an issue in full-duplex speech LLMs where models like Moshi and PersonaPlex inappropriately initiate speech during prolonged user silence. The problem stems from a sudden spike …
-
New Duplex Cue framework evaluates AI agent adaptation to overlapping speech
A new evaluation framework called Duplex Cue has been introduced to assess how well full-duplex voice agents adapt to overlapping speech from listeners. This framework moves beyond a simple binary of continuing or stopp…
-
New benchmark evaluates implicit instruction following in voice agents
A new benchmark, DuplexSpeechBench-IFEval (DSB-IFEval), has been introduced to evaluate how well full-duplex voice agents can implicitly follow instructions based on roles or personas, rather than explicit commands. The…
-
audio.cpp 0.7 adds Arena UI, 62+ audio models
The audio.cpp project has released version 0.7, significantly expanding its support for audio models to 62 families and over 85 variants. This update introduces an Arena UI, allowing users to compare outputs from multip…
-
NousResearch releases advanced Hermes agent, sparking comparison to top-tier models
NousResearch has released version 0.20 of its Hermes agent, a significant advancement from its initial 0.2 release in mid-March. This development highlights the rapid progress in open-source AI models, moving from early…
-
Thinking Machines previews interaction models for real-time AI collaboration
Thinking Machines has introduced a research preview of interaction models designed for native, real-time collaboration. These models process audio, video, and text simultaneously, allowing for continuous thought, respon…
-
New methods boost full-duplex speech models for better interaction
Researchers have developed new methods to enhance full-duplex speech models, enabling more natural and interactive conversations. One approach focuses on improving interactivity axes like pause handling and turn-taking …