Improving general text embedding model: Tackling task conflict and data imbalance through model merging

Mingxin Li, Zhijie Nie, Yanzhao Zhang, Dingkun Long, Richong Zhang, Pengjun Xie · arXiv 2410.15035

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

representative citing papers

cs.CL · 2026-01-08 · unverdicted · novelty 4.0

Qwen3-VL-Embedding-8B achieves state-of-the-art performance with a 77.8 overall score on the MMEB-V2 multimodal embedding benchmark.

Showing 1 of 1 citing paper.

Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking cs.CL · 2026-01-08 · unverdicted · none · ref 15
Qwen3-VL-Embedding-8B achieves state-of-the-art performance with a 77.8 overall score on the MMEB-V2 multimodal embedding benchmark.