arXiv Machine Learning June 18, 2026 By Zirong Li

GrapNet: A Programmable Dynamic-Architecture Neural Graph Substrate

Read the original on arXiv Machine Learning →

arXiv:2606. 18923v1 Announce Type: new Abstract: Programmability is a missing first-class interface in fixed-tensor neural networks: editing a relation, freezing a subgraph, auditing a local function, or changing the execution backend should be an operation on the neural program rather than ad-hoc parameter surgery.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Aug 11

NeuroAda: Activating Each Neuron's Potential for Parameter-Efficient Fine-Tuning

arXiv:2510. 18940v2 Announce Type: replace-cross Abstract: Existing parameter-efficient fine-tuning (PEFT) methods primarily fall into two categories: addition-based and selective in-situ adaptation.

By Zhi Zhang, Yixian Shen, Congfeng Cao, Ekaterina Shutova

fine-tuning benchmarks

arXiv Machine Learning

Jul 17

NeuronSoup: Evolving Asynchronous, Shared-Neuron Temporal Graphs without Backpropagation

arXiv:2607. 15217v1 Announce Type: cross Abstract: We present NeuronSoup, a neural computation architecture that replaces synchronous layer-by-layer processing with asynchronous, delay-mediated signal propagation through a pool of shared neurons.

By Subodh Kalia

arXiv AI

Jul 3

Do Newer Lightweight CNNs Perform Better Under Resource Constraints? A Controlled Multigenerational Study of Architecture, Initialization, Training Budget, and Efficiency

arXiv:2607. 01984v1 Announce Type: cross Abstract: Newer lightweight convolutional neural networks are often presented as improving predictive performance and deployment efficiency, but such claims require controlled evaluation.

By Tasnim Shahriar

arXiv Machine Learning

Jul 9

Efficient Long-Horizon Learning for Learned Optimization

arXiv:2607. 06772v1 Announce Type: new Abstract: Learned optimization aims to improve upon hand-designed optimizers (e.

By Xiaolong Huang, Benjamin Th\'erien, James Harrison, Eugene Belilovsky

llms computer-vision

arXiv Machine Learning

Jun 11

On the Stability of Growth in Structural Plasticity

arXiv:2605. 15435v2 Announce Type: replace Abstract: Standard deep-learning pipelines usually choose the network architecture before training and keep it fixed throughout optimization.

By Lute Lillo, Nick Cheney

efficiency benchmarks

arXiv Machine Learning

Jun 26

What Survives When You Compress a Recursive Reasoner for the Edge?

arXiv:2606. 26488v1 Announce Type: new Abstract: Recursive reasoning models can solve complex structured tasks with only a few million parameters by repeatedly updating a latent state.

By Pearse Jim, Steven Kolawole, Opegbemi Matthias Busoye, Glory Bagai, Virginia Smith

rag efficiency

Related stories

NeuroAda: Activating Each Neuron's Potential for Parameter-Efficient Fine-Tuning

NeuronSoup: Evolving Asynchronous, Shared-Neuron Temporal Graphs without Backpropagation

Do Newer Lightweight CNNs Perform Better Under Resource Constraints? A Controlled Multigenerational Study of Architecture, Initialization, Training Budget, and Efficiency

Efficient Long-Horizon Learning for Learned Optimization

On the Stability of Growth in Structural Plasticity

What Survives When You Compress a Recursive Reasoner for the Edge?