Quanta AI Labs

Tencent · Visual Understanding

Penguin-VL-2B

Compact 2B VLM that initializes its vision encoder from Qwen3-0.6B (not CLIP/SigLIP) to reduce objective mismatch. Temporal Redundancy-Aware (TRA) token compression for video. Outperforms Qwen3-VL-2B on DocVQA (94.1), ChartQA (86.6), and LongVideoBench (59.5).

Open the source ↗

Similar Vision & Image releases

  • WeVisOne-VL

    WeChat Vision, Tencent · Vision-Language Model · Week 44, 2026

  • Nemotron 3.5 Super VL

    NVIDIA · Open Multimodal MoE · Week 43, 2026

  • Vision Demos

    jeremyipark · Sports Vision Demos · Week 41, 2026

  • PixelUMM

    NVIDIA and University of Waterloo · Encoder-Free Unified Model · Week 41, 2026

  • Ovis-Embedding

    ATH-MaaS · Ovis Embedding Models · Week 40, 2026

  • RADAR

    RADAR-Generalist team, published in Science · Abdominal CT Vision Model · Week 40, 2026

More from Tencent

Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.