Awesome World Model Hub Papers · Datasets · Projects
← Back to papers

LLM-JEPA: Large Language Models Meet Joint Embedding Predictive Architectures

arXiv 25.9 2025 48.5 method

TLDR

Proposes LLM-JEPA, a JEPA-based training objective for LLMs that outperforms standard methods across models and datasets.

Reasoning

Strengths include a novel application of JEPA to language and strong empirical results across multiple models and datasets. Weaknesses are that the paper focuses solely on language tasks and does not address world modeling or dynamics, limiting relevance to the specified keywords.

Read-first score

Read-first score 48.5, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 0.

Recency 8%
86.7

Uses a gentle age decay so recent papers surface without erasing older foundations. 2025

Reproducibility 25%
85

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=True; dataset=False; markers=code,dataset,github

Methodology quality 25%
80

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=dataset,evaluation,result

Topical relevance 42%
0

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Field roles

FrontierMethodology anchorReproducibility anchor

Rank sensitivity

Stability: volatile; rank range: 749.

Keyword Scores

world model
0
world simulator
0
generative world model
0
interactive world model
0
video world model
0
world dynamics prediction
0
model-based reinforcement learning world model
0

Deep Analysis

Innovations

  • First application of Joint Embedding Predictive Architecture (JEPA) to language models, bridging a gap between vision and language training paradigms.
  • Development of a JEPA-based training objective for LLMs that works for both finetuning and pretraining, outperforming standard input-space reconstruction objectives.

Methodology

The paper proposes LLM-JEPA, which replaces the standard input-space reconstruction objective in LLM training with an embedding-space predictive objective inspired by vision JEPAs. The method is evaluated across multiple datasets (NL-RX, GSM8K, Spider, RottenTomatoes) and model families (Llama3, OpenELM, Gemma2, Olmo) by comparing performance against standard LLM training objectives.

Key Results

LLM-JEPA outperforms standard LLM training objectives by a significant margin across all tested models and datasets, while also demonstrating robustness to overfitting.

Limitations

  • The results are presented as a first step and may be preliminary; the method's effectiveness on a wider range of tasks and larger scales is not yet established.
  • The abstract does not specify the exact architecture or training details, leaving potential implementation challenges unaddressed.

Tags