OpenMOSS
PulseAugur coverage of OpenMOSS — every cluster mentioning OpenMOSS across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
Fudan University's MOSS-Live voice system outperforms OpenAI and ByteDance in benchmarks
Fudan University's OpenMOSS team has developed MOSS-Live, a real-time full-duplex voice system. In benchmarks against OpenAI's GPT-Live-1 and ByteDance's Doubao SeedDuplex, MOSS-Live reportedly outperformed on six full-…
-
OpenMOSS releases MOSS-Image text-to-image model
OpenMOSS has released MOSS-Image, a 5-billion parameter text-to-image model. This model utilizes a single-stream diffusion transformer architecture. It was made available on October 16, 2026, under the Apache 2.0 license.
-
MOSS-Image open model hits 1.3M downloads in four days
MOSS-Image, a 5 billion parameter open image generation model, has seen significant adoption with over 1.3 million downloads in its first four days. Developed by MOSI and the OpenMOSS team, the model is built upon a dif…
-
MOSS-Image model surpasses 1 million downloads in four days
The open-source MOSS-Image model, developed by MOSI and OpenMOSS, achieved significant traction shortly after its release. Within four days, it garnered approximately 1.3 million downloads across various repositories. T…
-
Unsloth adds Recursive Flint, MOSS-Image, NVIDIA Nemotron Bolt E4B models
Unsloth has released version 0.1.910-beta, introducing support for several new models including Recursive's Flint and MOSS-Image, as well as NVIDIA's Nemotron Bolt E4B. This update enables users to run these models loca…
-
Chinese 5B image model MOSS-Image goes viral overseas · 1 source tracked
A Chinese-developed 5B parameter image generation model, MOSS-Image, has rapidly gained popularity overseas, achieving over 1.3 million downloads in just four days. The model is praised for its natural image output, att…
-
Open-source MOSS-Image model gains traction for text and layout control
Mossi people and OpenMOSS have released MOSS-Image, a 5-billion parameter text-to-image model. This model is designed for precise control over text rendering and JSON-based layout generation. It rapidly gained popularit…
-
OpenMOSS releases MOSS-Image text-to-image models
OpenMOSS has released two text-to-image models, MOSS-Image-Base and MOSS-Image-SFT, both derived from the MOSS-Image family. These models are designed to support natural language prompts, tag sequences, and JSON layouts…
-
MOSS-VL open vision-language model family enables real-time interaction
The MOSS-VL model family has been introduced as an open vision-language model designed for real-time interaction. It achieves this by incorporating gated cross-attention, allowing the model to process visual information…
-
OpenMOSS-Team releases MOSS-VL-Realtime for continuous video stream understanding
OpenMOSS-Team has released MOSS-VL-Realtime, a new model designed for continuous video stream understanding. Unlike traditional models that process entire videos at once, MOSS-VL-Realtime processes incoming frames in re…
-
Open-source AI pipeline generates game assets locally
A developer has created a comprehensive pipeline for generating game assets using open-source AI models, ported to GGML for local execution. The pipeline includes tools for text-to-speech with voice cloning (OpenMOSS), …
-
Open-Source Audio Model MOSS-Audio Released; Microsoft & OpenAI Terminate AGI Pact
OpenMOSS has released MOSS-Audio 2026, an open-source foundation model capable of processing speech, environmental sounds, and music, while also understanding temporal reasoning. This model reportedly outperforms larger…