Hugging Face Trending Papers
A Drosophila Whole-Connectome Network Can Learn Human-Designed Cognitive Tasks
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv Machine Learning
2d ago
A Drosophila Whole-Connectome Network Can Learn Human-Designed Cognitive Tasks
The study investigates whether a biological wiring diagram can serve as a computational substrate for tasks beyond its evolutionary purpose. Using the MaleCNS v1.0 Drosophila connectome as a fixed recurrent network, the authors train models to perform bounded addition and a grounded relational language task, achieving high accuracy (92.77% for addition and 61.59% for language) that surpasses degree-preserving rewired controls. The results demonstrate that the higher-order structure of the MaleCNS provides a reusable inductive bias for these cognitive tasks.
arXiv Machine Learning
Jun 16
Whole-Brain Connectomic Graph Model Enables Whole-Body Locomotion Control in Fruit Fly
arXiv:2602. 17997v3 Announce Type: replace Abstract: Animals perform coordinated whole-body movements under the control of neural systems shaped by brain-wide connectivity.
arXiv Machine Learning
2d ago
Structure alone supports efficient visual computation in the Drosophila visual system
arXiv:2610.10023v1 Announce Type: cross Abstract: Understanding the extent to which measured synaptic wiring determines computation remains a central challenge. Here, we couple the proofread adult Dr...
arXiv Computation and Language
Sep 15
URCHIN: A Horizontal Spiking Language Model for Data-Constrained Pretraining
arXiv:2609.13899v1 Announce Type: cross Abstract: The BabyLM challenge measures how much language a model can learn from developmentally-plausible, child-scale data rather than internet-scale corpora...
arXiv Machine Learning
Sep 10
Connectome-to-Function: Conditional Generative Latent Representations for Reservoir Computing
arXiv:2609.06093v1 Announce Type: new Abstract: Connectomes, graph-level maps of neurons and their synaptic connections, provide a structural basis for understanding how brain circuits support functi...
arXiv AI
Jun 16
Harnessing cortical geometry, wiring, and function as inductive biases for recurrent neural networks
arXiv:2606. 14975v1 Announce Type: cross Abstract: How the wiring and functional organization of cortex shape recurrent computation remains a central question in both neuroscience and machine learning.