Douyin Multimodal Embedding Model Technical Report

Douyin Multimodal Embedding Model Technical Report

The Douyin Multimodal Embedding (DME), a model trained in two stages to combine both strengths, is presented, a model trained in two stages to combine both strengths.

WeMM-Embedding: WeChat Multi-Modal Embedding Technical Report

WeMM-Embedding is presented, a family of universal multimodal embedding models supporting text, images, videos, visual documents, and arbitrarily interleaved multimodal inputs with flexible output dimensions and achieves leading performance on multiple public benchmarks.

MoEMB: Scaling Universal Multimodal Embeddings with Efficient Mixture-of-Experts Models

This work proposes MOEMB, which instead scales UME along the expert axis through mixture-of-experts (MoE), growing encoder capacity while preserving single-vector, non-autoregressive encoding, and conducts the first comprehensive study of adaptive computation for MoE-based embedding.

Quantifying and reducing the modality gap in both contrastive and generative multimodal vision–language models

Retrv-MoE: Scaling Unified Multimodal Retrieval with Sparse Mixture-of-Experts

This work proposes Retrv-MoE, a unified retrieval architecture built upon sparse Mixture-of-Experts (MoE), and theoretically and empirically demonstrates that this conditional computation mechanism provides a structural remedy to optimization interference by decoupling the learning trajectories of conflicting tasks and...

MLLMCLIP: Feature-Level Distillation of MLLM for Robust Vision-Language Representations

Compared to prior CLIP-enhancement methods, MLLMCLIP achieves state-of-the-art compositional accuracy while delivering consistent gains on standard zero-shot classification and image-text retrieval, showing that feature-level distillation strengthens both compositional and general vision-language representation capabil...