AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Multi-Modal Multi-Task Unified Embedding Model (M3T-UEM): A Task-Adaptive Representation Learning Framework

Rohan Sharma, Changyou Chen, Feng-Ju Chang, Seongjun Yun, Xiaohu Xie, Rui Meng, Dehong Xu, Alejandro Mottini, Qingjun Cui

ICCV 2025 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities · 0 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
use task-aware contrastive loss instead of standard InfoNCE (ablation)M3T-UEM · M-BEIR averageRecall: 52.7 -> 53.9Improved
add task-aware loss (5k-step ablation) (ablation)M3T-UEM · M-BEIR average (5k-step)retrieval average: 37.4 -> 38.0Improved
add two-stage training (alignment then refinement) at equal FLOPs (ablation)M3T-UEM · M-BEIR average (5k-step)retrieval average: 35.7 -> 38.0Improved
use 16 EOS tokens instead of one (ablation)M3T-UEM · M-BEIR average (5k-step)retrieval average: 37.6 -> 38.0Improved
add auxiliary language-modeling loss (ablation)M3T-UEM · M-BEIR average (5k-step)retrieval average: 37.9 -> 38.0No clear effect
use M3T-UEM LLM backbone versus OpenCLIP ViT-g-14 on multilingual retrievalM3T-UEM · Multilingual zero-shot retrievalRecall@5 text-to-image: 41.4 -> 72.9Improved
use M3T-UEM versus OpenCLIP ViT-g-14 on SugarCrepe ReplaceM3T-UEM · SugarCrepe Replaceimage-to-text accuracy: 81.7 -> 88.9Improved
use M3T-UEM versus MM-Embed on M-BEIRM3T-UEM · M-BEIR averageRecall: 52.7 -> 53.9Improved
use M3T-UEM versus ViT-g-14 on throughputM3T-UEM · CIFAR-100 throughputsamples/sec: 20.1 -> 18.9Hurt
use M3T-UEM versus ViT-g-14 on memoryM3T-UEM · inference memoryMB: 8,573 -> 21,778Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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