#knowledge-retention News & Analysis

4 articles tagged with #knowledge-retention. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

4 articles

AIBullisharXiv – CS AI · May 77/10

🧠

Memory as a Markov Matrix: Sample Efficient Knowledge Expansion via Token-to-Dictionary Mapping

Researchers propose a novel framework that models language model memory as a Markov transition matrix, enabling efficient incorporation of new knowledge without catastrophic forgetting. The approach requires only linear sample complexity in the number of existing tokens and achieves zero forgetting through minimal parameter updates via an embedding-tuning algorithm.

AINeutralarXiv – CS AI · May 96/10

🧠

Null Space Constrained Contrastive Visual Forgetting for MLLM Unlearning

Researchers present a novel machine unlearning approach for Multimodal Large Language Models that selectively removes target visual knowledge while preserving non-target information across both visual and textual modalities. The method uses contrastive visual forgetting and null space constraints to balance effective forgetting with knowledge retention, extending applicability to continual unlearning scenarios.

AIBullisharXiv – CS AI · Apr 156/10

🧠

Joint Flashback Adaptation for Forgetting-Resistant Instruction Tuning

Researchers propose Joint Flashback Adaptation, a novel method to address catastrophic forgetting in large language models during incremental task learning. The approach uses limited prompts from previous tasks combined with latent task interpolation, demonstrating improved performance across 1000+ instruction-following and reasoning tasks without requiring full replay data.

AINeutralarXiv – CS AI · Mar 37/108

🧠

A Practical Guide to Streaming Continual Learning

Researchers propose Streaming Continual Learning (SCL) as a unified paradigm that combines Continual Learning and Streaming Machine Learning approaches. SCL aims to enable AI systems to both rapidly adapt to new information and retain previously learned knowledge, addressing limitations of existing methods that excel at only one aspect.