The paper demonstrates that neural networks can maintain perfect training accuracy while their training cross‑entropy remains nearly flat at a positive level, a phenomenon observed on modular addition tasks. Using ReLU networks with supported‑Polar hidden updates, normalized output‑layer updates, and weight decay, the authors show that hidden features evolve and held‑out accuracy can rise from zero to above 90% even as cross‑entropy stays flat. Theoretical results for one‑hidden‑layer networks and empirical evidence from deeper networks and transformers confirm that correct classification need not coincide with minimal cross‑entropy, challenging conventional assumptions about loss plateaus.
By Akash Kumar, Karthik Sankaranarayanan
The study investigates why Lund‑plane and Particle Transformer (ParT) jet taggers can perform differently by using model stitching to isolate representation from computation. By linking frozen early layers of one network to frozen late layers of another, the authors show that a known deficit in the primary Lund representation is purely representational, not computational, and that this gap is invisible in AUC but appears in background rejection at low signal efficiency. Rebuilding the representation on the full Cambridge/Aachen declustering tree largely closes the gap, revealing that the primary branch carries most of the discriminative power while secondary splittings mainly make the representation learnable.
By Saurabh Rai, Sanmay Ganguly
arXiv:2602. 13298v4 Announce Type: replace-cross Abstract: This paper presents a controlled comparative study of convolutional neural network (CNN) topology and image classification performance across the architectural families VGG, ResNet, and GoogLeNet, evaluated on CIFAR-10 under a unified training protocol.
By Manfred M. Fischer, Joshua Pitts
The paper compares convolutional neural networks (CNN), Vision Transformers (ViT), and hierarchical Swin Transformers for quark‑gluon jet classification using a three‑channel jet‑image representation. CNN and Swin models outperform ViT, indicating that local jet substructure is crucial for discrimination. The study also shows that block‑wise fine‑tuning, Momentum Contrast pretraining, and a compact Swin variant can improve performance while reducing parameters.
By Daeun Kim, Jaeyoon Cho, Jiwon Lee, Wonjun Jeong, Hyeongwoo Noh, Giyeong Kim, Seunghwan Yang, MinJung Kweon
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:2512. 07420v3 Announce Type: replace-cross Abstract: Jet identification plays a central role in analyzing data from high-energy collider experiments.
By Md Raqibul Islam, Adrita Khan, Mir Sazzat Hossain, Choudhury Ben Yamin Siddiqui, Md. Zakir Hossan, Tanjib Khan, M. Arshad Momen, Amin Ahsan Ali, AKM Mahbubur Rahman
arXiv:2512.10819v2 Announce Type: replace-cross
Abstract: Multiple proton-proton interactions occur in the same bunch crossing at the LHC ("pile-up"), with the mean number of interactions per bunch c...
By Mohammed Aboelela
arXiv:2607. 23377v1 Announce Type: cross Abstract: The largest machine learning models in particle physics are also the most expensive to train, yet the return on scaling a given architecture cannot be estimated before that compute is spent.
By Jan-Lucas Uslu, Benjamin Nachman, Christopher Re
arXiv:2610. 27106v1 Announce Type: cross Abstract: We present the Sparse Particle-interaction Transformer Architecture (SParTA), a modular, scalable, and efficient transformer for jet tagging at high-energy colliders.
By Rajneil Baruah, Subhadeep Mondal, Sunando Kumar Patra, Satyajit Roy
arXiv:2610.15124v1 Announce Type: cross
Abstract: Foundation models need to support diverse inference budgets, yet training a separate model for each budget duplicates pretraining effort. Elastic mod...
By Can Jin, Yan Kang, Yifan Gong, Chongjian Ge, Mingze Xu, Yuanjun Xiong, Dimitris N. Metaxas, Hongwu Peng
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
The paper introduces Right In-Place (RiP) convolution, a memory‑efficient strategy that corrects and generalizes previous in‑place convolution formulations to arbitrary stride, dilation, padding, and rectangular kernels. RiP aligns each layer’s input and output within a shared workspace, enabling safe, row‑major access with minimal memory overhead. Experiments on 10,000 random layers and 84 layers from 25 architectures show no corruption, matching or improving on existing herringbone workspaces while reducing memory usage by up to 24.8% and lowering peak activation memory on Raspberry Pi Pico MCUs by 12.5–33.3% without affecting cycle counts.
By Opegbemi Matthias Busoye, Tolulope Matthew Busoye, Eghonghon-aye Eigbe