Tootfinder

PredNext: Explicit Cross-View Temporal Prediction for Unsupervised Learning in Spiking Neural Networks
Yiting Dong, Jianhao Ding, Zijie Xu, Tong Bu, Zhaofei Yu, Tiejun Huang
https://arxiv.org/abs/2509.24844

PredNext: Explicit Cross-View Temporal Prediction for Unsupervised Learning in Spiking Neural Networks
Spiking Neural Networks (SNNs), with their temporal processing capabilities and biologically plausible dynamics, offer a natural platform for unsupervised representation learning. However, current unsupervised SNNs predominantly employ shallow architectures or localized plasticity rules, limiting their ability to model long-range temporal dependencies and maintain temporal feature consistency. This results in semantically unstable representations, thereby impeding the development of deep unsupe…

TFW you’ve got your computer on your lap and a ray of low winter sun comes in at a shallow angle and it’s suddenly obvious that your screen and keys are horribly filthy.

Deep vs. Shallow: Benchmarking Physics-Informed Neural Architectures on the Biharmonic Equation
Akshay Govind Srinivasan, Vikas Dwivedi, Balaji Srinivasan
https://arxiv.org/abs/2510.04490

Deep vs. Shallow: Benchmarking Physics-Informed Neural Architectures on the Biharmonic Equation
Partial differential equation (PDE) solvers are fundamental to engineering simulation. Classical mesh-based approaches (finite difference/volume/element) are fast and accurate on high-quality meshes but struggle with higher-order operators and complex, hard-to-mesh geometries. Recently developed physics-informed neural networks (PINNs) and their variants are mesh-free and flexible, yet compute-intensive and often less accurate. This paper systematically benchmarks RBF-PIELM, a rapid PINN varian…

Reading Between the Lines: Scalable User Feedback via Implicit Sentiment in Developer Prompts
Daye Nam, Malgorzata Salawa, Satish Chandra
https://arxiv.org/abs/2509.18361 https:…

At some point, DOPs should stop going for even shallower depth of field or even weirder anamorphic lens distortion. I'm feeling like an old guy complaining about how "you can't see anything on the screen! It's too dark". Only I'm like "nothing is in focus anymore you doofuses!"
Yes, this is a subtoot about #Brick on

Vision-Free Retrieval: Rethinking Multimodal Search with Textual Scene Descriptions
Ioanna Ntinou, Alexandros Xenos, Yassine Ouali, Adrian Bulat, Georgios Tzimiropoulos
https://arxiv.org/abs/2509.19203

Vision-Free Retrieval: Rethinking Multimodal Search with Textual Scene Descriptions
Contrastively-trained Vision-Language Models (VLMs), such as CLIP, have become the standard approach for learning discriminative vision-language representations. However, these models often exhibit shallow language understanding, manifesting bag-of-words behaviour. These limitations are reinforced by their dual-encoder design, which induces a modality gap. Additionally, the reliance on vast web-collected data corpora for training makes the process computationally expensive and introduces signif…

Confidence-gated training for efficient early-exit neural networks
Saad Mokssit, Ouassim Karrakchou, Alejandro Mousist, Mounir Ghogho
https://arxiv.org/abs/2509.17885 https://…

Confidence-gated training for efficient early-exit neural networks
Early-exit neural networks reduce inference cost by enabling confident predictions at intermediate layers. However, joint training often leads to gradient interference, with deeper classifiers dominating optimization. We propose Confidence-Gated Training (CGT), a paradigm that conditionally propagates gradients from deeper exits only when preceding exits fail. This encourages shallow classifiers to act as primary decision points while reserving deeper layers for harder inputs. By aligning train…

Probing the Ground State of the Antiferromagnetic Heisenberg Model on the Kagome Lattice using Geometrically Informed Variational Quantum Eigensolver
Abdellah Tounsi, Nacer Eddine Belaloui, Abdelmouheymen Rabah Khamadja, Takei Eddine Fadi Lalaoui, Mohamed Messaoud Louamri, David E. Bernal Neira, Mohamed Taha Rouabah
https://arxiv.org/abs/2…

Probing the Ground State of the Antiferromagnetic Heisenberg Model on the Kagome Lattice using Geometrically Informed Variational Quantum Eigensolver
This work investigates the nature of the ground state of the antiferromagnetic Heisenberg model on minimal kagome cells -- a triangle and a star -- using the variational quantum eigensolver (VQE) algorithm on real quantum hardware. We demonstrate that the ground state preparation is achievable using a shallow hardware-efficient quantum circuit with a naturally Euclidean parameter space. Our custom ansatz is capable of accurately recovering essential properties such as the spin correlation terms…