arXiv Machine Learning June 2, 2026 By Kiran Nayudu, Aswini Nutakki, Sai Vinay Naidu, Ashwin Shanmugasundaram

CRMA: A Spectrally-Bounded Backbone for Modular Continual Fine-Tuning of LLMs

Read the original on arXiv Machine Learning →

arXiv:2606. 00382v1 Announce Type: new Abstract: Sequential fine-tuning of large language models forces a choice: let the shared substrate keep learning and accept catastrophic forgetting, or freeze it after task one and foreclose cross-task refinement.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

4d ago

Neural Succession: A Mesoscopic Theory of Invasion, Coexistence, and Stabilization in Continual Learning

arXiv:2609.36375v1 Announce Type: new Abstract: Continual learning is usually studied through mechanisms that preserve old knowledge. We develop Successional Learning Theory (SLT), a mesoscopic accou...

By Shoaib Ahmed Dipu, Md Salman Shamil, Sayeed Shafayet Chowdhury

arXiv Machine Learning

Aug 18

Metaplasticity as adaptive gradient preconditioning for incremental learning

arXiv:2608. 14634v1 Announce Type: new Abstract: Biological intelligence naturally prevents catastrophic forgetting through Complementary Learning Systems (CLS) theory, a macroscopic consolidation process driven at the local level by synaptic metaplasticity: the continuous, history-dependent neuromodulation of individual synapses.

By Isabelle Aguilar, Zayn Andre Zainal, Omid Kavehei

benchmarks

arXiv AI

Aug 11

ZenBrain: A Neuroscience-Inspired 7-Layer Memory Architecture for Autonomous AI Systems

arXiv:2604. 23878v3 Announce Type: replace Abstract: ZenBrain is a seven-layer, neuroscience-derived memory architecture for LLM agents that unifies fifteen mechanisms - from Two-Factor synaptic consolidation to a Simulation-Selection sleep loop - under a single MemoryCoordinator: nine foundational algorithms plus six Predictive Memory Architecture components.

By Alexander Bering

llms agents benchmarks

arXiv AI

Jul 20

PASs-MoE: Mitigating Misaligned Co-drift among Router and Experts via Pathway Activation Subspaces for Continual Learning

arXiv:2601. 13020v2 Announce Type: replace-cross Abstract: Continual instruction tuning (CIT) requires multimodal large language models (MLLMs) to adapt to a stream of tasks without forgetting prior capabilities.

By Zhiyan Hou, Haiyun Guo, Haokai Ma, Yandu Sun, Yonghui Yang, Jinqiao Wang

llms fine-tuning multimodal benchmarks

arXiv Machine Learning

Aug 24

Nothing Changed but the Model: CellFill -- Bounded In-Cell Learning for Bit-Identical, Revocable Updates to Quantized LLMs

arXiv:2608.20873v1 Announce Type: new Abstract: Every way of teaching a deployed language model something new -- full fine-tuning, adapter merging, model editing -- replaces the released checkpoint,...

By Zifeng Liu, Zhiyong Du, Yaxin Lu, Yiming Mao, Zhenhe Wang, Wenqi Shi, Zhengkun Jing

llms fine-tuning efficiency

arXiv Machine Learning

Aug 13

Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning

arXiv:2608. 11690v1 Announce Type: new Abstract: Continual learning must absorb new tasks without erasing old ones, and replay---mixing a small buffer of past examples into current training---is among the most effective remedies for catastrophic forgetting.

By Tieliang Gong, Zhongbo Zhang, Wen Wen, Yong-Jin Liu

benchmarks safety

One email a morning, machine-written

Related stories

Neural Succession: A Mesoscopic Theory of Invasion, Coexistence, and Stabilization in Continual Learning

Metaplasticity as adaptive gradient preconditioning for incremental learning

ZenBrain: A Neuroscience-Inspired 7-Layer Memory Architecture for Autonomous AI Systems

PASs-MoE: Mitigating Misaligned Co-drift among Router and Experts via Pathway Activation Subspaces for Continual Learning

Nothing Changed but the Model: CellFill -- Bounded In-Cell Learning for Bit-Identical, Revocable Updates to Quantized LLMs

Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning