ICLR 2025PastOther
New Frontiers in Associative Memories
NFAM 2025
- Submission deadline
- Feb 15, 2025, 11:59 UTCimported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (34)
Fetched from OpenReview (v2) on 2026-06-10.
A BIOLOGICALLY PLAUSIBLE ASSOCIATIVE MEMORY NETWORK
Associative Memory Learning Through Redundancy Maximization
Autonomous Memory Rehearsal in Associative Memory Networks and its Implications for Biologically Plausible Continuous Learning
BEYOND DISORDER: UNVEILING COOPERATIVENESS IN MULTIDIRECTIONAL ASSOCIATIVE MEMORIES
Can memory networks play a role in task-specific modulation of neural circuits?
Decision Trees That Remember: Gradient-Based Learning of Recurrent Decision Trees with Memory
Deep Clustering with Associative Memories
Dense Associative Memory with Epanechnikov energy
Dense Hopfield Networks with Hierarchical Memories
Distilled Feedforward Networks Are As Robust as Energy-Based Models trained with Equilibrium Propagation
Effects of Feature Correlations on Associative Memory Capacity
Hebbian Sparse Autoencoder
Hierarchical Episodic Memory in LLMs via Multi-Scale Event Organization
Hierarchical Hopfield Network Decomposition: A Spiked Covariance Framework for Latent Prototype Discovery
How Linearly Associative are Memories in Large Language Models?
In-context denoising with one-layer transformers: connections between attention and associative memory retrieval
Investigating Hopfield networks on graphs: learning invariance and storing orbits
Knowledge Distillation for Random Data: Soft Labels and Similarity Scores May Contain Memorized Information
Learning Memory Mechanisms for Decision Making through Demonstration
Limits of Deep Learning: Sequence Modeling through the Lens of Complexity Theory
Lurie networks with k-contracting dynamics
MemLLM: Finetuning LLMs to Use Explicit Read-Write Memory
Memorization to Generalization: Emergence of Diffusion Models from Associative Memory Networks
Modern Hopfield Networks with Continuous-Time Memories
Multi-channel pattern reconstruction through $L$-directional associative memories
Oscillator associative memories facilitate high-capacity, compositional inference
Pseudo-likelihood produces associative memories able to generalize, even for asymmetric couplings
Re:Frame - Retrieving Experience From Associative Memory
Selective Association in Context Memory for Task-Specific Video Understanding
Sequential Pattern Retrieval: New Representations Inspired by Non-equilibrium Physics and Associative Memory Models
Test-time scaling meets associative memory: Challenges in subquadratic models
The Capacity of Modern Hopfield Networks under the Data Manifold Hypothesis
Training Deep Predictive Coding Networks
Working Memory Attack on LLMs