lab Tencent Hunyuan (HF) · 1d ago · src: 3d ago · releases

Tencent releases WeVisDoc-2B and WeVisDoc-4B document parsers

from English

Tencent has released WeVisDoc, an end-to-end document parser for page images fine-tuned from Qwen3-VL models. The system converts page images into structured Markdown, including LaTeX formulas and HTML tables.

WeVisDoc-4B achieves an Overall score of 95.38 on OmniDocBench v1.6 and a mean Overall score of 75.54 across PureDocBench tracks.
It ranks first among compared end-to-end parsers in all four reported settings.
The release includes both WeVisDoc-2B and WeVisDoc-4B model checkpoints.

The models are available for local inference or via a vLLM-based service, supporting Python 3.10+.

Importance 1/3 Trust 1/3 Tencent Hunyuan (HF) Tencent Multimodal Open weights

Read original

lab Tencent Hunyuan (HF) · 1d ago · 4 views

Tencent releases WeVisDoc-4B, an end-to-end document parser

Tencent has released WeVisDoc-4B, an end-to-end document parser for page images that converts pages into structured Markdown with LaTeX formulas and HTML tables. Fine-tuned from Qwen3-VL-4B-Instruct, the model achieves an Overall score of 95.38 on OmniDocBench v1.6 and ranks first among compared parsers across all four reported settings.

lab Tencent Hunyuan (HF) · 25d ago · 45 views

Tencent releases WeMM-Embedding-2B multimodal embedding model

Tencent has released WeMM-Embedding-2B, a universal multimodal embedding model built on Qwen3.5 that accepts text, images, videos, visual documents, and interleaved inputs to return 2,048-dimensional L2-normalized embeddings.

lab Tencent Hunyuan (HF) · 25d ago · 40 views

Tencent releases WeMM-Embedding-4B universal multimodal embedding model

Tencent has released WeMM-Embedding-4B, a universal multimodal embedding model built on Qwen3.5 that accepts text, images, videos, visual documents, and interleaved inputs to return 2,560-dimensional L2-normalized embeddings.

lab Tencent Hunyuan (HF) · 25d ago · 49 views

Tencent releases WeMM-Embedding-9B universal multimodal embedding model

Tencent has released WeMM-Embedding-9B, a universal multimodal embedding model built on Qwen3.5 that accepts text, images, videos, visual documents, and interleaved inputs to return 4,096-dimensional L2-normalized embeddings.

lab Tencent Hunyuan (HF) · 32d ago · 30 views

Tencent releases EVIE-Preview-4.5B multilingual visual document retrieval model

Tencent has released EVIE-Preview-4.5B, a state-of-the-art multilingual Visual Document Retrieval (VDR) model built upon Qwen3.5-4B. The model employs ColBERT-style late interaction with native 128-dimensional multi-vector token embeddings to achieve top-tier performance across ViDoRe benchmarks.