Online Label-Free Gradient Matching for Continual Language Model Training
cs.AI, cs.CL
Submitted: 2026-11-02
Updated: 2026-11-02
Terminology
Sources
- Hybrid Memory Replay: Blending Real and Distilled Data for Class Incremental Learning
- Textbooks Are All You Need II: phi-1.5 technical report
- Data-Distill-Net: A Data Distillation Approach Tailored for Reply-based Continual Learning
- Memory-efficient Continual Learning with Prototypical Exemplar Condensation
- Technical Report on Text Dataset Distillation
- Progressive Neural Networks
- The information bottleneck method
- Three scenarios for continual learning
- Dataset Distillation
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents