Differences

This shows you the differences between two versions of the page.

--- ml:continual_learning [2025/02/01 00:45] – [In NLP] jmflanig
+++ ml:continual_learning [2026/10/02 00:27] (current) – [In NLP] jmflanig
@@ Line 3: / Line 3: @@
 ===== Overviews =====
   * [[https://arxiv.org/pdf/2302.00487|Wang et al 2023 - A Comprehensive Survey of Continual Learning: Theory, Method and Application]]
+  * **In NLP**
+    * [[https://dl.acm.org/doi/pdf/10.1145/3735633|Shi et al 2025 - Continual Learning of Large Language Models: A Comprehensive Survey]]
+    * [[https://dl.acm.org/doi/pdf/10.1145/3716629|Zheng et al 2025 - Towards Lifelong Learning of Large Language Models: A Survey]]
 ===== Papers =====
 ==== In NLP ====
-  * [[https://arxiv.org/pdf/2203.04640|Ermis Memory Efficient Continual Learning with Transformers]]
+  * [[https://arxiv.org/pdf/2203.04640|Ermis et al 2022 - Memory Efficient Continual Learning with Transformers]]
   * [[https://arxiv.org/pdf/2501.13453|Zheng et al 2025 - Spurious Forgetting in Continual Learning of Language Models]] Argues that the drop in performance while doing continued training "often reflects a decline in task alignment rather than knowledge loss"