arXiv Machine Learning June 29, 2026 By Evan Gibson Smith, Bashima Islam

Layerwise Progressive Freezing: A Training Scaffold for Depth-Scalable Binary Networks

Read the original on arXiv Machine Learning →

arXiv:2606. 27759v1 Announce Type: new Abstract: Training binary neural networks (BNNs) from scratch is dominated by the straight-through estimator (STE), whose forward/backward mismatch produces severe accuracy degradation as networks deepen.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

fine-tuning

arXiv Machine Learning

Aug 7

Threshold-Based Early Stopping of Accumulations in Neural Networks with Binary Activation

arXiv:2608. 06177v1 Announce Type: new Abstract: Binary neural networks are very attractive for constrained deployment, enabling small footprint and low-power inference.

By Quentin Luquet de Saint-Germain, Massil Ait Abdeslam, Jean Pierre David

arXiv AI

Jul 22

Soft-TransFormers for Continual Learning

arXiv:2411. 16073v4 Announce Type: replace-cross Abstract: Inspired by the Well-initialized Lottery Ticket Hypothesis (WLTH), we introduce Soft-TransFormers (Soft-TF), a continual learning framework that adapts a frozen pre-trained Transformer through task-specific soft subnetworks: real-valued multiplicative masks over the query, key, value, and output projections of selected self-attention layers.

By Haeyong Kang, Chang D. Yoo

llms fine-tuning benchmarks

arXiv AI

4d ago

Cumulative-Goodness Free-Riding in Forward-Forward Networks: Real, Repairable, but Not Accuracy-Dominant

arXiv:2605.06240v2 Announce Type: replace-cross Abstract: Forward-Forward (FF) training lets each layer learn from a local goodness criterion. In cumulative-goodness variants, later layers can inheri...

By Amirhossein Yousefiramandi

arXiv Machine Learning

Jun 5

Neural Collapse Dynamics: Depth, Activation, Regularisation, and Feature Norm Threshold

arXiv:2604. 00230v2 Announce Type: replace Abstract: Neural collapse (NC) -- the convergence of penultimate-layer features to a simplex equiangular tight frame -- is well understood at equilibrium, but the dynamics governing its onset remain poorly characterised.

By Anamika Paul Rupa

arXiv Machine Learning

Jul 27

Hidden Failure Modes of Gradient Modification under Adam in Continual Learning, and Adaptive Decoupled Moment Routing as a Repair

arXiv:2604. 22407v2 Announce Type: replace Abstract: Many continual-learning methods modify gradients upstream (e.

By Yuelin Hu, Zhenbo Yu, Zhengxue Cheng, Wei Liu, Li Song

fine-tuning benchmarks

arXiv Machine Learning

Jun 10

Overcoming Rank Collapse in Feedback Alignment

arXiv:2606. 11123v1 Announce Type: new Abstract: Backpropagation (BP) is widely viewed as biologically implausible, in part because it requires feedback weights to be the transpose of forward weights for error propagation.

By Gauthier Boeshertz, Razvan Pascanu, Claudia Clopath

benchmarks safety

One email a morning, machine-written

Related stories

Threshold-Based Early Stopping of Accumulations in Neural Networks with Binary Activation

Soft-TransFormers for Continual Learning

Cumulative-Goodness Free-Riding in Forward-Forward Networks: Real, Repairable, but Not Accuracy-Dominant

Neural Collapse Dynamics: Depth, Activation, Regularisation, and Feature Norm Threshold

Hidden Failure Modes of Gradient Modification under Adam in Continual Learning, and Adaptive Decoupled Moment Routing as a Repair

Overcoming Rank Collapse in Feedback Alignment