Tencent releases EVIE-Preview-4.5B visual document retrieval model
tencent · hf · 2026-08-17
Tencent released EVIE-Preview-4.5B on Hugging Face, a vision-language model for the visual-document-retrieval pipeline. It uses ColPali/ColBERT-style late-interaction with multi-vector representations on a Qwen3.5 base, targeting document-image retrieval.
Related event: Tencent's EVIE Tops ViDoRe Leaderboard, Cutting Vector Storage 32x(2 posts)→
More from Multimodal
- Seedance 2.5 Generates Photorealistic Tokyo Travel Vlog with Strong Identity Consistency — eyishazyer · 2026-08-17
- Connection Error visual combining Grok Imagine and Seedance 2.0 — creatoroff · 2026-08-17
- Alibaba Releases HappyShrimp 1.0: End-to-End AI Music Generation Model — 智东西 · 2026-08-17
- Seedance 2.5 enables longer generations, shifting AI video workflows to scene direction — umesh_ai · 2026-08-17
- Local offline CUDA tool splits tracks into stems and editable MIDI — Yamapama · 2026-08-17
- AI reimagining of 'The Odyssey' produces crazy visual results — aitrendz_xyz · 2026-08-17