Tootfinder

Looks interesting. The only thing that hits me hard (and yes, that might be a me problem): I know newsletters are the latest craze, but if there’s one thing I don’t want, then it’s more emails in my inbox. I can haz RSS pls? 😶 /cc @…

Phone 3a: NothingOS 4.0 bringt optionale Werbung auf dem Sperrbildschirm
Das Tech-Start-up Nothing ändert seine Strategie für seine Budget-Modelle: Auf dem Sperrbildschirm zieht mit Android 16 künftig optional Werbung ein.
…

New examples in the study of selectively separable spaces
Alan Dow, Hayden Pecoraro
https://arxiv.org/abs/2509.22590 https://arxiv.org/pdf/2509.22590

New examples in the study of selectively separable spaces
The property of being selectively separable is well-studied and generalizations such as H-separable and wH-separable have also generated much interest. Bardyla, Maesano, and Zdomskyy proved from Martin's Axiom that there are countable regular wH-separable spaces that are not H-separable. We prove there is a ZFC example. Their example was also Fréchet-Urysohn, and we produce two additional examples from weaker assumptions.

Tracking Quantum State Collapse/Decoherence in Real Time via a Superposition Trap
Hardeep Singh, Tim Kovachy
https://arxiv.org/abs/2509.23053 https://arxiv…

Tracking Quantum State Collapse/Decoherence in Real Time via a Superposition Trap
We propose a novel method for probing quantum state collapse and decoherence in real time using a mechanism we term the superposition trap. This approach exploits the continuity equation in quantum mechanics to engineer a configuration that spatially confines only coherent superpositions, while allowing decohered or collapsed states to escape. By monitoring this leakage, the dynamics of collapse processes-whether environmentally induced or intrinsic to objective collapse models-can be experimen…

From Superficial Outputs to Superficial Learning: Risks of Large Language Models in Education
Iris Delikoura (May), Yi. R (May), Fung, Pan Hui
https://arxiv.org/abs/2509.21972 …

From Superficial Outputs to Superficial Learning: Risks of Large Language Models in Education
Large Language Models (LLMs) are transforming education by enabling personalization, feedback, and knowledge access, while also raising concerns about risks to students and learning systems. Yet empirical evidence on these risks remains fragmented. This paper presents a systematic review of 70 empirical studies across computer science, education, and psychology. Guided by four research questions, we examine: (i) which applications of LLMs in education have been most frequently explored; (ii) ho…

IA2: Alignment with ICL Activations Improves Supervised Fine-Tuning
Aayush Mishra, Daniel Khashabi, Anqi Liu
https://arxiv.org/abs/2509.22621 https://arxiv…

IA2: Alignment with ICL Activations Improves Supervised Fine-Tuning
Supervised Fine-Tuning (SFT) is used to specialize model behavior by training weights to produce intended target responses for queries. In contrast, In-Context Learning (ICL) adapts models during inference with instructions or demonstrations in the prompt. ICL can offer better generalizability and more calibrated responses compared to SFT in data scarce settings, at the cost of more inference compute. In this work, we ask the question: Can ICL's internal computations be used to improve the qual…

SpikeMatch: Semi-Supervised Learning with Temporal Dynamics of Spiking Neural Networks
Jini Yang, Beomseok Oh, Seungryong Kim, Sunok Kim
https://arxiv.org/abs/2509.22581 https:/…

SpikeMatch: Semi-Supervised Learning with Temporal Dynamics of Spiking Neural Networks
Spiking neural networks (SNNs) have recently been attracting significant attention for their biological plausibility and energy efficiency, but semi-supervised learning (SSL) methods for SNN-based models remain underexplored compared to those for artificial neural networks (ANNs). In this paper, we introduce SpikeMatch, the first SSL framework for SNNs that leverages the temporal dynamics through the leakage factor of SNNs for diverse pseudo-labeling within a co-training framework. By utilizing…

Domain-Informed Genetic Superposition Programming: A Case Study on SFRC Beams
Mohammad Sadegh Khorshidi, Navid Yazdanjue, Hassan Gharoun, Mohammad Reza Nikoo, Fang Chen, Amir H. Gandomi
https://arxiv.org/abs/2509.21355

Domain-Informed Genetic Superposition Programming: A Case Study on SFRC Beams
This study presents domain-informed genetic superposition programming (DIGSP), a symbolic regression framework tailored for engineering systems governed by separable physical mechanisms. DIGSP partitions the input space into domain-specific feature subsets and evolves independent genetic programming (GP) populations to model material-specific effects. Early evolution occurs in isolation, while ensemble fitness promotes inter-population cooperation. To enable symbolic superposition, an adaptive …

Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining
Boshra Ariguib, Mathias Niepert, Andrei Manolache
https://arxiv.org/abs/2509.22468

Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining
High-quality molecular representations are essential for property prediction and molecular design, yet large labeled datasets remain scarce. While self-supervised pretraining on molecular graphs has shown promise, many existing approaches either depend on hand-crafted augmentations or complex generative objectives, and often rely solely on 2D topology, leaving valuable 3D structural information underutilized. To address this gap, we introduce C-FREE (Contrast-Free Representation learning on Ego…

CCNeXt: An Effective Self-Supervised Stereo Depth Estimation Approach
Alexandre Lopes, Roberto Souza, Helio Pedrini
https://arxiv.org/abs/2509.22627 https://

CCNeXt: An Effective Self-Supervised Stereo Depth Estimation Approach
Depth Estimation plays a crucial role in recent applications in robotics, autonomous vehicles, and augmented reality. These scenarios commonly operate under constraints imposed by computational power. Stereo image pairs offer an effective solution for depth estimation since it only needs to estimate the disparity of pixels in image pairs to determine the depth in a known rectified system. Due to the difficulty in acquiring reliable ground-truth depth data across diverse scenarios, self-supervis…