MOSS-VL Technical Report

• URL: http://arxiv.org/abs/2608.15045v1
• Date: Sat, 15 Aug 2026 05:12:53 GMT
• Title: MOSS-VL Technical Report
• Abstract summary: We present MOSS-VL, an open vision-language model family that treats real-time interaction as a first-class capability.<n>It is co-designed across the stack: the language decoder attends to vision only through gated cross-attention.<n> Offline, MOSS-VL-Instruct is competitive at comparable scale and leads temporal-reasoning video sets.
• Score: 66.58420246189313
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present MOSS-VL, an open vision-language model family that treats real-time interaction -- perceiving while it speaks -- as a first-class capability. It is co-designed across the stack: the language decoder attends to vision only through gated cross-attention, so the model can naturally see incoming frames while generating; a synthesized interaction corpus supervises when to speak, when to stay silent, and when to revise; and a staged curriculum concentrates all real-time-specific training in one light final stage over a strong offline foundation. Offline, MOSS-VL-Instruct is competitive at comparable scale and leads temporal-reasoning video sets. Across four streaming benchmarks, MOSS-VL-Realtime posts the best average on three (second on the fourth) among open-source streaming models, sweeping the three subsets that squarely test proactive behavior -- 66.0 vs. 37.5 for the best baseline on OmniMMI Proactive Alerting. With 11.3B parameters but visual tokens outside the decoded sequence, MOSS-VL widens its time-to-first-token advantage over same-backbone Qwen3-VL-8B from 2.8x to 5.1x as visual context grows. We release all five checkpoints, the training curriculum, and the real-time inference code at https://github.com/OpenMOSS/MOSS-VL.

Related papers

• Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model [60.85752511708308]
  We present Mage-VL, an efficient streaming foundation model for real-time multimodal understanding and interaction.<n>At its core, our custom tokenizer, Mage-ViT, replaces uniform frame sampling by selectively encoding dynamic, entropy-rich regions.<n>We establish AI4AI data pipelines encompassing prompt-code joint optimization for captioning and AI-driven performance diagnosis.
  arXiv  Detail & Related papers  (2026-07-27T17:59:53Z)
• Kwai Keye-VL-2.0 Technical Report [53.82434681649277]
  Keye-VL-2.0 is a multimodal foundation model designed to advance long-video understanding and agentic intelligence.<n>It is the first to adapt DeepSeek Sparse Attention (DSA) to GQA-based multimodal architectures.<n>Cross-Modal Multi-Teacher On-Policy Distillation (MOPD) paired with Context-RL and Video-RL overcomes the algorithmic dilemma of catastrophic forgetting.
  arXiv  Detail & Related papers  (2026-06-09T09:58:08Z)
• OmniVTG: A Large-Scale Dataset and Training Paradigm for Open-World Video Temporal Grounding [55.29748680163419]
  Video Temporal Grounding (VTG) struggles in open-world settings due to limited dataset scale and semantic diversity.<n>We introduce OmniVTG, a new large-scale dataset for open-world VTG.<n>We train the MLLM to first predict, then use its understanding capabilities to reflect on and refine its own predictions.
  arXiv  Detail & Related papers  (2026-04-28T06:34:19Z)
• Kwai Keye-VL Technical Report [80.53170317017147]
  We introduce textbfKwai Keye-VL, a multimodal foundation model for short-video understanding.<n>The development of Keye-VL rests on two core pillars: a massive, high-quality dataset with a strong emphasis on video, and an innovative training recipe.<n>To validate our approach, we conduct extensive evaluations, showing that Keye-VL achieves state-of-the-art results on public video benchmarks and remains highly competitive on general image-based tasks.
  arXiv  Detail & Related papers  (2025-07-02T17:57:28Z)
• Visatronic: A Multimodal Decoder-Only Model for Speech Synthesis [13.702423348269155]
  Video-Text to Speech (VTTS) is a speech generation task conditioned on both its corresponding text and video of talking people.<n>We introduce Visatronic, a unified multimodal decoder-only transformer model that embeds visual, textual, and speech inputs into a shared subspace.<n>We show that Visatronic achieves a 4.5% WER, outperforming prior SOTA methods trained only on LRS3.
  arXiv  Detail & Related papers  (2024-11-26T18:57:29Z)
• Unveiling Encoder-Free Vision-Language Models [62.52803514667452]
  Existing vision-language models (VLMs) mostly rely on vision encoders to extract visual features followed by large language models (LLMs) for visual-language tasks. We bridge the gap between encoder-based and encoder-free models, and present a simple yet effective training recipe towards pure VLMs. We launch EVE, an encoder-free vision-language model that can be trained and forwarded efficiently.
  arXiv  Detail & Related papers  (2024-06-17T17:59:44Z)
• ViLA: Efficient Video-Language Alignment for Video Question Answering [22.972518862771697]
  Our ViLA network addresses both efficient frame sampling and effective cross-modal alignment. Our ViLA network outperforms the state-of-the-art methods on the video question-answering benchmarks.
  arXiv  Detail & Related papers  (2023-12-13T18:58:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.