AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Embed-RL: Reinforcement Learning for Reasoning-Driven Multimodal Embeddings

Haonan Jiang, Yuji Wang, Yongjie Zhu, Xin Lu, Wenyu Qin, Meng Wang, Pengfei Wan, Yansong Tang

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Reinforcement learning for visual reasoning · 28 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 embedder-guided RL (EG-RL) stage (ablation)Embed-RL-2B · MMEB-V2 (Embed-RL-2B)overall score: 65.3 -> 66.8Improved
add weighted negative sampling to outcome reward (ablation)Embed-RL-2B · MMEB-V2 (Embed-RL-2B)overall score: 66.5 -> 66.8Improved
add process reward (ablation)Embed-RL-2B · MMEB-V2 (Embed-RL-2B)overall score: 66.0 -> 66.8Improved
add outcome reward (ablation)Embed-RL-2B · MMEB-V2 (Embed-RL-2B)overall score: 65.8 -> 66.8Improved
add reasoning process to T-CoT (ablation)Embed-RL-2B · MMEB-V2 (Embed-RL-2B)overall score: 65.5 -> 66.8Improved
add reasoning process to T-CoT (ablation)Embed-RL-2B · MMEB-V2 video overallscore: 50.5 -> 52.1Improved
add multimodal cues (bounding boxes, keyframes) to T-CoT (ablation)Embed-RL-2B · MMEB-V2 (Embed-RL-2B)overall score: 65.8 -> 66.8Improved
add T-CoT instead of raw input (ablation)Embed-RL-2B · MMEB-V2 (Embed-RL-2B)overall score: 60.2 -> 66.8Improved
add T-CoT instead of raw input (ablation)Embed-RL-2B · MMEB-V2 video overallscore: 43.7 -> 52.1Improved
add T-CoT instead of raw input (ablation)Embed-RL-2B · MMEB-V2 visdoc overallscore: 72.4 -> 74.1Improved
scale embedder from 2B to 4BEmbed-RL · MMEB-V2 (All)score: 66.8 -> 68.1Improved
Embed-RL-4B vs UME-R1-7BEmbed-RL-4B · MMEB-V2 (All)score: 64.5 -> 68.1Improved

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