Exploring Synchrony for Communication in Modular Neural Networks
cs.CV, cs.NI
Submitted: 2026-11-10
Updated: 2026-11-10
Code: https://github.com/kimhc6028/relational-networks
Terminology
Sources
- Relational inductive biases, deep learning, and graph networks
- Winfree Oscillatory Neural Network
- Continuous Thought Machines
- Faith and Fate: Limits of Transformers on Compositionality
- Recurrent Independent Mechanisms
- On the Binding Problem in Artificial Neural Networks
- Scaling Laws for Neural Language Models
- Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention
- Generalization without systematicity: On the compositional skills of sequence-to-sequence recurrent networks
- Object-Centric Learning with Slot Attention
- Complex-Valued Autoencoders for Object Discovery
- Rotating Features for Object Discovery
- An experimental study of the vision-bottleneck in VQA
- Is a Modular Architecture Enough?
- Artificial Kuramoto Oscillatory Neurons
- FiLM: Visual Reasoning with a General Conditioning Layer
- Modular Deep Learning
- Neuronal Synchrony in Complex-Valued Deep Networks
- Linear Transformers Are Secretly Fast Weight Programmers
- Discovering modular solutions that generalize compositionally
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs