AI Engram: In Search of Memory Traces in Artificial Intelligence

Researchers introduce 'AI Engram', a geometric framework to identify and isolate individual memory traces in deep neural networks. This biologically-inspired approach enables surgical manipulation of learned knowledge through simple linear arithmetic without iterative optimization.

Computer Science > Artificial Intelligence

Title:AI Engram: In Search of Memory Traces in Artificial Intelligence

View PDF HTML (experimental)Abstract:Memory formation is fundamental to intelligence, yet whether deep neural networks preserve identifiable memory traces analogous to biological memory units remains an open question. This work introduces a geometric framework to identify such "AI engrams" by formalizing the neuroscientific criteria of specificity, reactivation, sufficiency, and necessity into a constrained inverse problem. We derive a closed-form estimator that isolates individual memory traces from globally entangled parameters, and show that this biologically-derived solution corresponds to a natural gradient update on the parameter manifold. AI engrams enable surgical manipulation of learned knowledge: any subset of memories can be composed or erased through linear arithmetic, without iterative optimization. Experiments ranging from simple MLPs to LLMs demonstrate the causal validity and substantial scalability of AI engrams. Together, these results bridge theories of biological memory and artificial representation learning and offer geometric insight into how deep networks simultaneously support functional specificity within distributed storage.

Source: arXiv cs.AI Recent

More in this category

agentic-systems

Semantics-Enhanced Retrieval-Augmented Time Series Forecasting

Researchers have introduced SERAF, a novel multimodal time series forecasting framework that addresses the limitations of traditional methods under non-stationarity by leveraging dual retrieval over both numerical data and self-generated textual descriptions.

agentic-systems

Risk-Aware LLM Agents for Geospatial Data Retrieval: Design and Preliminary Adversarial Evaluation

Researchers have presented an LLM-driven framework that simplifies the retrieval of remote sensing data from cloud-based geospatial catalogs using natural language. The system integrates three specialized AI agents to optimize performance and mitigate adversarial API manipulation risks.

agentic-systems

Attribute Inference from Interactive Targeted Ads

A new study models how interactive targeted advertising can act as a channel for attribute inference, allowing advertisers to deduce sensitive user data. The researchers propose defense mechanisms like aggregate reporting and randomized disclosure to mitigate these privacy risks.

agentic-systems

Fusion is not one-size-fits-all: Cross-Modal Representation Alignment for Time-to-Event Modeling

Researchers introduce a foundation model-driven framework for cross-modal representation alignment between CT imaging and longitudinal EHR data to improve time-to-event prediction. The study demonstrates that task-aware multimodal alignment is essential for robust generalization and scalable clinical deployment.

agentic-systems

Visual-Seeker: Towards Visual-Native Multimodal Agentic Search via Active Visual Reasoning

Researchers have introduced Visual-Seeker, a pioneering visual-native multimodal search agent that addresses the factual grounding limitations of current AI models. By leveraging active visual reasoning, it outperforms several proprietary models in complex web search tasks.

agentic-systems

CONCORD: Asynchronous Sparse Aggregation for Device-Cloud RAG under Document Isolation

Researchers have proposed CONCORD, an asynchronous sparse aggregation framework for dual-end RAG under document isolation. It significantly improves end-to-end throughput and reduces communication overhead while maintaining high answer quality.

EXPLORE TOPICS