ER-JEPA: Experience Replay Improves Joint-Embedding Predictive Learning in Language Models
cs.CL, cs.AI
Submitted: 2026-09-29
Updated: 2026-09-29
Terminology
Sources
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- Revisiting Feature Prediction for Learning Visual Representations from Video
- Training Verifiers to Solve Math Word Problems
- Unlocking the Power of Rehearsal in Continual Learning: A Theoretical Perspective
- Learning and Leveraging World Models in Visual Representation Learning
- Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks
- The Llama 3 Herd of Models
- Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning
- Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal
- From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline
- DeepSeek-V3 Technical Report
- Continual Learning of Large Language Models: A Comprehensive Survey
- Finetuned Language Models Are Zero-Shot Learners
- GLM-130B: An Open Bilingual Pre-trained Model
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering