Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

Hugging Face Unveils MOSS-VL: Open Vision-Language Models for Real-Time Interaction

AI By Crimson AI Hugging Face Papers 18 August 2026 · 00:00 7 views
Share: X Telegram

MOSS-VL, a new open vision-language model family, prioritizes real-time interaction by using gated cross-attention to perceive visual input while generating, achieving strong streaming performance and reduced latency.

Hugging Face Unveils MOSS-VL: Open Vision-Language Models for Real-Time Interaction

Key points

Hugging Face has released the technical report for MOSS-VL, an open vision-language model family designed with real-time interaction as a core capability. The models can perceive visual information while generating responses, a key feature for applications like live video understanding and interactive assistants.

MOSS-VL employs a gated cross-attention mechanism that allows the language decoder to attend to visual frames during generation, without including visual tokens in the decoded sequence. This design enables the model to continuously process incoming visual data while speaking, reducing the time-to-first-token (TTFT) latency.

The training process uses a synthesized interaction corpus to teach the model when to speak, stay silent, or revise its output, and a staged curriculum concentrates real-time-specific training in a final lightweight stage over a strong offline foundation. This approach yields two model variants: MOSS-VL-Instruct for offline tasks and MOSS-VL-Realtime for streaming.

In evaluations, MOSS-VL-Instruct is competitive at comparable scale and leads on temporal-reasoning video benchmarks. MOSS-VL-Realtime achieves the best average performance on three of four streaming benchmarks among open-source models, and sweeps all three proactive behavior subsets, scoring 66.0 vs. 37.5 for the best baseline on OmniMMI Proactive Alerting.

With 11.3B parameters, MOSS-VL widens its TTFT advantage over the same-backbone Qwen3-VL-8B from 2.8x to 5.1x as visual context grows. All five checkpoints, the training curriculum, and real-time inference code are publicly released on GitHub.

BenchmarkMOSS-VL-RealtimeBest Baseline
OmniMMI Proactive Alerting66.037.5
Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 29 Aug 2026

Hugging Face Audit: 110 of 124 AI Evaluations Fail to Support Their Claims

A new commit-bound census of 124 Inspect Evals units reveals that 110 stop before deterministic inference due to missing historica...

4
Research paper
Hugging Face 29 Aug 2026

Aphanta: New Framework Diagnoses When Image Editing Boosts Multimodal Reasoning

Hugging Face researchers introduce Aphanta, a diagnostic framework that evaluates when image-editing intermediates improve multimo...

5
Research paper
Hugging Face 29 Aug 2026

EditaLive! Enables Real-Time Character Video Editing for Live Streaming

Hugging Face researchers introduce EditaLive, a framework for real-time human-centric video editing in live streams, achieving sta...

4