ArXiv TLDR

Elena Burceanu

3 papers · Latest:

Machine Learning

Temporal Taskification in Streaming Continual Learning: A Source of Evaluation Instability

Temporal taskification in streaming continual learning is a critical evaluation variable, as different splits of the same stream can drastically alter benchmark conclusions.

2604.21930
Machine Learning

Fine-Tuning Regimes Define Distinct Continual Learning Problems

Fine-tuning regimes, specifically trainable depth, are critical variables in continual learning, influencing method performance and comparative rankings.

2604.21927
Machine Learning

JumpLoRA: Sparse Adapters for Continual Learning in Large Language Models

JumpLoRA introduces sparse adapters using JumpReLU gating for continual learning in LLMs, effectively preventing catastrophic forgetting and outperforming SOTA.

2604.16171

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.