Tootfinder

Revisiting Hallucination Detection with Effective Rank-based Uncertainty
Rui Wang, Zeming Wei, Guanzhang Yue, Meng Sun
https://arxiv.org/abs/2510.08389 https://

Revisiting Hallucination Detection with Effective Rank-based Uncertainty
Detecting hallucinations in large language models (LLMs) remains a fundamental challenge for their trustworthy deployment. Going beyond basic uncertainty-driven hallucination detection frameworks, we propose a simple yet powerful method that quantifies uncertainty by measuring the effective rank of hidden states derived from multiple model outputs and different layers. Grounded in the spectral analysis of representations, our approach provides interpretable insights into the model's internal re…

SpecGuard: Spectral Projection-based Advanced Invisible Watermarking
Inzamamul Alam, Md Tanvir Islam, Khan Muhammad, Simon S. Woo
https://arxiv.org/abs/2510.07302 https://

SpecGuard: Spectral Projection-based Advanced Invisible Watermarking
Watermarking embeds imperceptible patterns into images for authenticity verification. However, existing methods often lack robustness against various transformations primarily including distortions, image regeneration, and adversarial perturbation, creating real-world challenges. In this work, we introduce SpecGuard, a novel watermarking approach for robust and invisible image watermarking. Unlike prior approaches, we embed the message inside hidden convolution layers by converting from the spa…

Did I mention IC reversing is absolute crack for AuDHD brains?
I should probably put down the EEPROM, at least for a while, and move on to other stuff. But I'm having too much fun.
This is the dangerous part, and the part I have the most trouble with... the problem is so big you'll *never* be done (especially doing it manually without any automation, figuring out what each cell is by hand, etc).
There's always more to discover. Nerd sniping to the 20th power.

The Geometry of Truth: Layer-wise Semantic Dynamics for Hallucination Detection in Large Language Models
Amir Hameed Mir
https://arxiv.org/abs/2510.04933 https://

The Geometry of Truth: Layer-wise Semantic Dynamics for Hallucination Detection in Large Language Models
Large Language Models (LLMs) often produce fluent yet factually incorrect statements-a phenomenon known as hallucination-posing serious risks in high-stakes domains. We present Layer-wise Semantic Dynamics (LSD), a geometric framework for hallucination detection that analyzes the evolution of hidden-state semantics across transformer layers. Unlike prior methods that rely on multiple sampling passes or external verification sources, LSD operates intrinsically within the model's representational…

Neutron star envelopes with machine learning: a single-hidden-layer neural network application
K. Kovlakas, D. De Grandis, N. Rea
https://arxiv.org/abs/2509.03090 https://

Neutron star envelopes with machine learning: a single-hidden-layer neural network application
Thermal and magneto-thermal simulations are an important tool for advancing understanding of neutron stars, as they allow us to compare models of their internal structure and physical processes against observations constraining macroscopic properties such as the surface temperature. A major challenge in the simulations is in modelling of the outermost layers, known as the envelope, exhibiting a drop of many orders of magnitude in temperature and density in a geometrically thin shell. This is of…

Investigating Multi-layer Representations for Dense Passage Retrieval
Zhongbin Xie, Thomas Lukasiewicz
https://arxiv.org/abs/2509.23861 https://arxiv.org/p…

Investigating Multi-layer Representations for Dense Passage Retrieval
Dense retrieval models usually adopt vectors from the last hidden layer of the document encoder to represent a document, which is in contrast to the fact that representations in different layers of a pre-trained language model usually contain different kinds of linguistic knowledge, and behave differently during fine-tuning. Therefore, we propose to investigate utilizing representations from multiple encoder layers to make up the representation of a document, which we denote Multi-layer Represe…

Revealing a hidden magnetic order in the triangular lattice antiferromagnet CuNdO$_2$
Jonathan Gaudet, Dalmau Reig-i-Plessis, Bogeng Wen, Thomas J. Hicken, Jonas A. Krieger, Jan Peter Embs, Hubertus Luetkens, Adam A. Aczel, Stuart A. Calder, Matthew B. Stone, Hae-Young Kee, Alannah M. Hallas
https://arxiv.org/abs/2509.23523

Revealing a hidden magnetic order in the triangular lattice antiferromagnet CuNdO$_2$
We investigate the magnetic ground state of CuNdO$_2$, which is a delafossite with a triangular lattice of magnetic Nd$^{3+}$ ions that are well separated by non-magnetic Cu spacer layers. From inelastic neutron scattering measurements of the crystal electric field, we determine the strong Ising character of the pseudo-spin $\frac{1}{2}$ Nd$^{3+}$ moments. Magnetic susceptibility and heat capacity measurements reveal the onset of long-range antiferromagnetic order at $T_N=0.78$ K. While the mag…

Deep Learning for Model-Free Prediction of Thermal States of Robot Joint Motors
Trung Kien La, Eric Guiffo Kaigom
https://arxiv.org/abs/2509.12739 https://…

Deep Learning for Model-Free Prediction of Thermal States of Robot Joint Motors
In this work, deep neural networks made up of multiple hidden Long Short-Term Memory (LSTM) and Feedforward layers are trained to predict the thermal behavior of the joint motors of robot manipulators. A model-free and scalable approach is adopted. It accommodates complexity and uncertainty challenges stemming from the derivation, identification, and validation of a large number of parameters of an approximation model that is hardly available. To this end, sensed joint torques are collected and…

Deep Equilibrium Convolutional Sparse Coding for Hyperspectral Image Denoising
Jin Ye, Jingran Wang, Fengchao Xiong, Jingzhou Chen, Yuntao Qian
https://arxiv.org/abs/2508.15553 …

Deep Equilibrium Convolutional Sparse Coding for Hyperspectral Image Denoising
Hyperspectral images (HSIs) play a crucial role in remote sensing but are often degraded by complex noise patterns. Ensuring the physical property of the denoised HSIs is vital for robust HSI denoising, giving the rise of deep unfolding-based methods. However, these methods map the optimization of a physical model to a learnable network with a predefined depth, which lacks convergence guarantees. In contrast, Deep Equilibrium (DEQ) models treat the hidden layers of deep networks as the solution…

Unifying Diarization, Separation, and ASR with Multi-Speaker Encoder
Muhammad Shakeel, Yui Sudo, Yifan Peng, Chyi-Jiunn Lin, Shinji Watanabe
https://arxiv.org/abs/2508.20474 htt…

Unifying Diarization, Separation, and ASR with Multi-Speaker Encoder
This paper presents a unified multi-speaker encoder (UME), a novel architecture that jointly learns representations for speaker diarization (SD), speech separation (SS), and multi-speaker automatic speech recognition (ASR) tasks using a shared speech foundational encoder. We leverage the hidden representations from multiple layers of UME as a residual weighted-sum encoding (RWSE) to effectively use information from different semantic levels, contributing to bottom-up alignment between tasks. Th…

Based on Deep Neural Networks: A Machine Learning-Assisted Channel Estimation Method for MIMO Systems
Haoran He
https://arxiv.org/abs/2510.11891 https://ar…

Based on Deep Neural Networks: A Machine Learning-Assisted Channel Estimation Method for MIMO Systems
This paper proposes a machine learning-assisted channel estimation approach for massive MIMO systems, leveraging DNNs to outperform traditional LS and MMSE methods. In 5G and beyond, accurate channel estimation mitigates pilot contamination and high mobility issues that harm system reliability. The proposed DNN architecture includes multi-layer perceptrons with ReLU activation, 3 hidden layers (256, 128, 64 neurons respectively), uses Adam optimizer (learning rate 1e-4) and MSE loss function. I…

Topological Uncertainty for Anomaly Detection in the Neural-network EoS Inference with Neutron Star Data
Kenji Fukushima, Syo Kamata
https://arxiv.org/abs/2508.19683 https://

Topological Uncertainty for Anomaly Detection in the Neural-network EoS Inference with Neutron Star Data
We study the performance of the Topological Uncertainty (TU) constructed with a trained feedforward neural network (FNN) for Anomaly Detection. Generally, meaningful information can be stored in the hidden layers of the trained FNN, and the TU implementation is one tractable recipe to extract buried information by means of the Topological Data Analysis. We explicate the concept of the TU and the numerical procedures. Then, for a concrete demonstration of the performance test, we employ the Neut…