AI Paper Atlas

Research map / Architectures and efficiency / Mixture of experts

TSEmbed: Unlocking Task Scaling in Universal Multimodal Embeddings

Yebo Wu, Feng Liu, Ziwei Xie, Changwang Zhang, Jun Wang, Li Li

ECCV 2026 · Architectures and efficiency › Mixture of experts · approach: Sparse MoE as regularization and attention · 11 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add MoE-LoRA to VLM2VEC dense LoRA (ablation)VLM2VEC (Qwen2-VL-2B) · MMEB ablation (2B)overall score: 59.30 -> 70.20Improved
add MoE-LoRA to VLM2VEC dense LoRA (ablation)VLM2VEC (Qwen2-VL-7B) · MMEB ablation (7B)overall score: 65.80 -> 74.21Improved
add EANS without two-stage warm-up on MoE (ablation)TSEmbed (2B) · MMEB ablation (2B)overall score: 70.20 -> 70.14Hurt
add EANS without two-stage warm-up on MoE (ablation)TSEmbed (7B) · MMEB ablation (7B)overall score: 74.21 -> 74.18No clear effect
add two-stage warm-up before EANS (ablation)TSEmbed (2B) · MMEB ablation (2B)overall score: 70.14 -> 70.52Improved
add two-stage warm-up before EANS (ablation)TSEmbed (7B) · MMEB ablation (7B)overall score: 74.18 -> 74.68Improved
replace B3 with TSEmbedB3 (7B) · MMEB (~7B models)overall score: 72.0 -> 74.7Improved
replace B3 with TSEmbedB3 (2B) · MMEB (~2B models)overall score: 68.1 -> 70.5Improved
replace VLM2VEC with TSEmbed on production ads dataVLM2VEC · Proprietary advertising datasetretrieval gain: +21.87%Improved
vary decay sigma from 2e-5 to 2e-1 (ablation)TSEmbed EANS · MMEB sigma sweepper-task score: within ~1%No clear effect
increase experts N from 4 to 8 (ablation)TSEmbed MoE-LoRA · MMEB expert-number sweepper-task scoreHurt
use N=4 experts instead of N=2 (ablation)TSEmbed MoE-LoRA · MMEB expert-number sweepper-task scoreImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy