# TI-JEPA: An Innovative Energy-based Joint Embedding Strategy for Text-Image Multimodal Systems

arXiv: https://arxiv.org/abs/2503.06380 · HTML: https://mlsanity.com/paper/2503.06380/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 39 references that are in the map.
- First posted on arXiv 9 Mar 2025.

## Builds on (most cited first, 25 of 25)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Efficient Low-rank Multimodal Fusion with Modality-Specific Factors](https://mlsanity.com/paper/1806.00064/) (2018)
- [Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization](https://mlsanity.com/paper/1807.00230/) (2018)
- [UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning](https://mlsanity.com/paper/2012.15409/) (2020)
- [Contrastive Learning for Neural Topic Model](https://mlsanity.com/paper/2110.12764/) (2021)
- [Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives](https://mlsanity.com/paper/2406.05615/) (2024)
- [Modeling Dynamic Topics in Chain-Free Fashion by Evolution-Tracking Contrastive Learning and Unassociated Word Exclusion](https://mlsanity.com/paper/2405.17957/) (2024)
- [Adaptive Contrastive Learning on Multimodal Transformer for Review Helpfulness Predictions](https://mlsanity.com/paper/2211.03524/) (2022)
- [KDMCSE: Knowledge Distillation Multimodal Sentence Embeddings with Adaptive Angular margin Contrastive Learning](https://mlsanity.com/paper/2403.17486/) (2024)
- [Improving Multimodal Sentiment Analysis: Supervised Angular Margin-based Contrastive Learning for Enhanced Fusion Representation](https://mlsanity.com/paper/2312.02227/) (2023)
- [Topic Modeling as Multi-Objective Contrastive Optimization](https://mlsanity.com/paper/2402.07577/) (2024)
- [DemaFormer: Damped Exponential Moving Average Transformer with Energy-Based Modeling for Temporal Language Grounding](https://mlsanity.com/paper/2312.02549/) (2023)
- [Motion-aware Contrastive Learning for Temporal Panoptic Scene Graph Generation](https://mlsanity.com/paper/2412.07160/) (2024)
- [Encoding and Controlling Global Semantics for Long-form Video Question Answering](https://mlsanity.com/paper/2405.19723/) (2024)
- [MAMA: Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning](https://mlsanity.com/paper/2407.03788/) (2024)
- [Expand BERT Representation with Visual Information via Grounded Language Learning with Multimodal Partial Alignment](https://mlsanity.com/paper/2312.01592/) (2023)
- [Energy-Based Models with Applications to Speech and Language Processing](https://mlsanity.com/paper/2403.10961/) (2024)
- [Multi-Scale Contrastive Learning for Video Temporal Grounding](https://mlsanity.com/paper/2412.07157/) (2024)
- [Enhancing Multimodal Entity Linking with Jaccard Distance-based Conditional Contrastive Learning and Contextual Visual Augmentation](https://mlsanity.com/paper/2501.14166/) (2025)
- [Vision-and-Language Pretraining](https://mlsanity.com/paper/2207.01772/) (2022)

## Built on by (most cited first, 8 of 8)

- [Audio-JEPA: Joint-Embedding Predictive Architecture for Audio Representation Learning](https://mlsanity.com/paper/2507.02915/) (2025)
- [Giving Sensors a Voice: Multimodal JEPA for Semantic Time-Series Embeddings](https://mlsanity.com/paper/2605.31580/) (2026)
- [CrossJEPA: Cross-Modal Joint-Embedding Predictive Architecture for Efficient 3D Representation Learning from 2D Images](https://mlsanity.com/paper/2511.18424/) (2025)
- [Time to Embed: Unlocking Foundation Models for Time Series with Channel Descriptions](https://mlsanity.com/paper/2505.14543/) (2025)
- [The JEPA Paradox in Language: The Geometry of Linguistic Alternatives](https://mlsanity.com/paper/2607.23531/) (2026)
- [AlertBERT: A noise-robust alert grouping framework for simultaneous cyber attacks](https://mlsanity.com/paper/2602.06534/) (2026)
- [The JEPA Predictor: A Transferable Operator for Occluded Feature Completion](https://mlsanity.com/paper/2607.16274/) (2026)
- [Bar-JEPA: Extracting Values from Bar Chart with Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2608.06062/) (2026)

## Abstract (arXiv)

This paper focuses on multimodal alignment within the realm of Artificial Intelligence, particularly in text and image modalities. The semantic gap between the textual and visual modality poses a discrepancy problem towards the effectiveness of multi-modalities fusion. Therefore, we introduce Text-Image Joint Embedding Predictive Architecture (TI-JEPA), an innovative pre-training strategy that leverages energy-based model (EBM) framework to capture complex cross-modal relationships. TI-JEPA combines the flexibility of EBM in self-supervised learning to facilitate the compatibility between textual and visual elements. Through extensive experiments across multiple benchmarks, we demonstrate that TI-JEPA achieves state-of-the-art performance on multimodal sentiment analysis task (and potentially on a wide range of multimodal-based tasks, such as Visual Question Answering), outperforming existing pre-training methodologies. Our findings highlight the potential of using energy-based framework in advancing multimodal fusion and suggest significant improvements for downstream applications.